Towards Collaborative Simultaneous Localization and Mapping: a Survey of the Current Research Landscape

08/18/2021 ∙ by Pierre-Yves Lajoie, et al. ∙ University of Oxford Corporation de l'ecole Polytechnique de Montreal 0

Motivated by the tremendous progress we witnessed in recent years, this paper presents a survey of the scientific literature on the topic of Collaborative Simultaneous Localization and Mapping (C-SLAM), also known as multi-robot SLAM. With fleets of self-driving cars on the horizon and the rise of multi-robot systems in industrial applications, we believe that Collaborative SLAM will soon become a cornerstone of future robotic applications. In this survey, we introduce the basic concepts of C-SLAM and present a thorough literature review. We also outline the major challenges and limitations of C-SLAM in terms of robustness, communication, and resource management. We conclude by exploring the area's current trends and promising research avenues.

READ FULL TEXT VIEW PDF
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.

1 Introduction

Collaborative Simultaneous Localization and Mapping (C-SLAM), also known as multi-robot SLAM, has been studied extensively with early techniques dating back as far as the early 2000s (e.g. [Jennings et al., 1999, Fox et al., 2000, Thrun, 2001, Williams et al., 2002, Fenwick et al., 2002]). These techniques were introduced only a short time after the inception of single-robot SLAM by researchers who were already envisioning collaborative perception of the environment. Although they were small-scale proofs of concept, they laid the foundations that still shape the field nowadays.

After years of confinement to laboratory settings, C-SLAM technologies are finally coming to fruition into industry applications, ranging from warehouse management to fleets of self-driving cars. Those long awaited success stories are a strong indicator that C-SLAM technologies are poised to permeate other fields such as marine exploration [Paull et al., 2014, Bonin-Font and Burguera, 2020], cooperative object transportation [Rioux et al., 2015], or search and rescue operations [Tian et al., 2020c, Lee et al., 2020].

SLAM is the current method of choice to enable autonomous navigation, especially in unknown and GPS-denied environments. SLAM provides an accurate representation of the robot surroundings which can in turn enable autonomous control and decision making. Similarly, in multi-robot systems, C-SLAM enables collaborative behaviors by building a collective representation of the environment and a shared situational awareness.

Moreover, many ambitious applications remain for multi-robot systems, such as the exploration of other planets [Vitug, 2021, Ebadi et al., 2021]. To reach those moonshot goals, ongoing trends in the research community aim to push the boundaries of multi-robot systems towards increasingly larger teams, or swarms of robots [Beni, 2004, Kegeleirs et al., 2021], which potentially allow parallel operations that are more efficient and versatile. However, this is still largely uncharted territory since current multi-robot applications either involve very few robots or rely upon large amounts of centralized computation in server clusters. Current C-SLAM techniques are no exception. They are prone to deteriorated performance when the team size increases above a few robots, and could be infeasible when minimal or no prior information is available about the operating environment.

Even though C-SLAM-enabled swarms of robots are still far from reality, C-SLAM remains a useful tool when operating as few as two autonomous robots. In exploration and mapping applications, even small teams can yield a significant boost in performance compared to a single robot system [Simmons et al., 2000]. Notably, autonomous mapping using C-SLAM has recently received a lot of attention due to the latest DARPA Subterranean Challenge [DARPA, 2020] and its potential applications in space technologies [Bezouska and Barnhart, 2019].

Figure 1: Collaborative Simultaneous Localization and Mapping Illustration

Thus, this paper presents a survey of the relevant literature on the topic of C-SLAM, aiming to give a complete overview of the main concepts, current developments, open challenges, and new trends in the field. We hope it will help new as well as established researchers to evaluate the state-of-the-art and offer valuable insights to guide future design choices and research directions. Compared to previous reviews [Saeedi et al., 2016, Rone and Ben-Tzvi, 2013], this paper provides an update on the tremendous progress in the past five years. It also aims for a broader overview of the field than surveys covering specific C-SLAM subproblems such as map merging [Lee et al., 2012], practical implementations [Kshirsagar et al., 2018], particle filter techniques [Gupta and Conrad, 2019], vision-based techniques [Zou et al., 2019], and search and rescue applications [Queralta et al., 2020].

1.1 Outline

The rest of this paper consists of seven sections covering the main C-SLAM subfields of research presented in Table 1: Section 2 presents an overview of the single robot SLAM problem; Section 3 explains the core difference with C-SLAM; Section 4 explores the different modules of the C-SLAM front-end and their challenges; Section 5 introduces the C-SLAM back-end and discusses the different inference techniques; Section 6 presents the available benchmarking datasets; Section 7 discusses the ongoing and future trends in the fields; and Section 8 concludes the survey and discusses future research avenues.

SLAM Odometry
Intra-Robot Loop Closures

Pose Estimation

C-SLAM Front-End Direct Inter-Robot Loop Closures
Indirect Inter-Robot Loop Closures
Communication Constraints
Map Representation
C-SLAM Back-End

Extended Kalman Filters

Particle Filters
Pose Graph Optimization
Perceptual Aliasing Mitigation
Trends Active C-SLAM
Semantic C-SLAM
Dynamic environments
Cloud Robotics
Augmented Reality
Table 1: Collaborative Simultaneous Localization and Mapping Subfields of Research

2 What is SLAM?

At its core, SLAM is a joint estimation of a robot’s state and a model of its surrounding environment, with the key assumption that a moving robot performs the data collection sequentially. On one hand, the robot’s state comprises its pose (position and orientation) and possibly other quantities such as sensors’ calibration parameters. On the other hand, the environment model (i.e., the map

) consists of representations of landmarks, built with processed data from the robot’s exteroceptive sensors such as cameras or lidars. This makes SLAM an essential part of many applications that require building an accurate map of the surrounding environment, whether it be for collision-free navigation, scene understanding, or visual inspection by a remote human operator. Since dead-reckoning approaches (e.g. IMU, wheel or visual odometry) drift over time due to noise accumulation, the environment map in SLAM is also used internally to correct the robot trajectory when known areas are re-visited. The recovered links between previously visited locations are called loop closures. SLAM is useful when neither an a priori map nor localization information are available, when a map needs to be built, or long-term accurate localization estimates are required. Common scenarios include robotics applications without external positioning systems, such as the exploration of unknown indoor environments, caves, mines, or other planets.

2.1 Single-Robot SLAM problem

Formally, the overall goal of SLAM is to maximize the posterior of the map and robot state. We can formulate this with the state variables of both the landmarks (map) and the robot, and the set of measurements acquired by the moving robot [Thrun et al., 2005]:

(1)

This estimation problem is solved by either updating the current state at each time step given the new observations (i.e., filtering) or optimizing over the whole trajectory and past observations (i.e., smoothing).

Although filtering in SLAM is still an active research topic, current state-of-the-art techniques are mostly based on smoothing [Cadena et al., 2016, Rosen et al., 2021]. The common formulation for smoothing techniques is a Maximum A Posteriori (MAP) estimation problem that leverages the moving robot assumption by introducing a prior distribution (e.g. obtained by odometry) over the robot trajectory.

Thus, the SLAM problem for a single robot () can be expressed as finding , the solution of the MAP problem:

(2)

The decomposition of the posterior distribution is obtained with Bayes’ theorem:

is the likelihood of the measurements given a certain , and is the prior distribution of the robot motion state. Intuitively, the SLAM problem finds the set of state variables (environment landmarks and robot poses) that is most likely to produce the measurements given a prior estimation .

It is important to also note that SLAM is closely related to the well-studied problem of bundle adjustment in Structure from Motion for which we refer the reader to [Özyeşil et al., 2017].

2.2 SLAM Architecture

SLAM systems are commonly divided into a front-end and a back-end, each involving different fields of research. The front-end is in charge of perception-related tasks, such as feature extraction and data association which are both related to fields such as computer vision and signal processing. The back-end produces the final state estimates using the front-end’s outputs. The back-end uses tools from the fields of optimization, probability theory and graph theory. In practice, the front-end processes the sensor data to generate ego-motion, loop closure, and landmark measurements, while the back-end performs the joint estimation of the map and the robot state. Figure 

2 provides an overview of a common SLAM structure in which the robot trajectory is represented as a graph of poses at consecutive discrete times (i.e., a pose graph) and the map as a set of observed landmarks [Cadena et al., 2016]. In a 3D pose graph, the nodes are the robot poses comprised of a rotation matrix and a translation , and the edges represent the relative measurements between the poses [Barfoot, 2017].

Figure 2: Single-robot SLAM Overview

Single-robot SLAM still faces many challenges that consequently apply to C-SLAM such as its long-term use, its robustness to perception failures and incorrect estimates, or its need for performance guarantees [Cadena et al., 2016]. To circumvent those limitations in their specific settings, SLAM and C-SLAM developers often have to adapt the architecture and consider some trade-offs between the sensors capabilities, the onboard computing power, and available memory.

3 What is Collaborative SLAM?

Many tasks can be performed faster and more efficiently by using multiple robots instead of a single one. Whether SLAM is used to provide state estimation to support an application (e.g. estimate each robot’s position to plan for actions), or whether it is at the core of the task (e.g. mapping an environment), it is beneficial and sometimes necessary to extend SLAM solutions into coordinated C-SLAM algorithms rather than performing single-robot SLAM on each robot.

C-SLAM algorithms aim to combine data collected on each individual robot into globally consistent estimates of a common map and of each robot’s state. This coordination allows each robot to benefit from experience of the full team, leading to more accurate localization and mapping than multiple instances of single-robot SLAM. However, this coordination introduces many new features and challenges inherent to multi-robot systems.

3.1 Multi-robot systems

In multi-robot systems, data collection and state estimation are no longer entirely located on a single entity, so there is an inevitable need for communication between the agents (i.e., robots, base stations, etc.) which is the crux of the problem.

Moreover, multi-robot systems have additional properties to consider when designing C-SLAM systems, and taxonomies can be defined to classify approaches and highlight their benefits and tradeoffs. The taxonomy proposed in

[Dudek et al., 1993] presents considerations that are well suited to the C-SLAM problem. It distinguishes approaches according to the following aspects:

Team size

The number of robots in the system. Larger teams usually perform tasks more efficiently but may be harder to coordinate.

Communication range

Direct communication between robots is limited by their spatial distribution and the communication medium. In some cases, robots might be unable to communicate for long periods of time, while in others they might always be in range of another robot.

Communication topology

The topology of the communication network affects how robots can communicate with one another. For example, they might be limited to either broadcast or one-to-one messages.

Communication bandwidth

The bandwidth of the communication channel affects what information robots can afford to share.

System reconfigurability

The robots will move and are likely to change spatial configuration over time. This can affect the communication topology and bandwidth.

Team unit processing ability

Individual robot’s computational capability can affect the computation cost of C-SLAM approaches and the distribution of computation tasks.

Team composition

Robots can be homogeneous or heterogeneous over several aspects such as locomotion methods and available sensors.

The main differences between most C-SLAM techniques in the literature lie in the properties of the multi-robot system considered, especially their resource management strategy. One subclass of multi-robot systems particularly relevant to the future of C-SLAM are swarm robotics systems [Brambilla et al., 2013], which are inspired by social animals. Two main characteristics are required for swarm-compatibility in C-SLAM: robots’ sensing and communication capabilities must be local, and robots can not have access to centralized control and/or to global knowledge. Such systems would present considerable benefits: they would have robustness to the loss of individual units, and they could scale well to large numbers of robots.

3.2 C-SLAM Problem definition

When all robots’ initial states are known or can be estimated, the C-SLAM problem is a simple extension of the single-robot SLAM MAP problem that includes all the robots’ states, measurements, and additional inter-robot measurements linking different robots’ maps. In a setup with two robots (, ), where and are the state variables from robot and to be estimated, and are the set of measurements gathered by robot and independently, is the set of inter-robot measurements linking both robot maps containing relative pose estimates between one pose of robot and one of robot in their respective trajectories, and , are the solutions, the problem can be formulated as:

(3)

However, when the relative starting locations and orientations of the robots cannot be determined, the initial guess of the robots states is not available. In that case, there are infinite possible initial alignments between the multiple robot trajectories. Therefore, in absence of a prior distribution, C-SLAM is reduced to the following Maximum Likelihood Estimation (MLE) problem.

(4)

The C-SLAM problem formulation is still evolving to this day and progress still needs to be made to achieve an efficient decentralized, distributed and robust implementation. To give some perspective, Figure 3 presents some major milestones in the evolution of the C-SLAM problem over time. More details on these milestone works are provided in the following sections.

Figure 3: C-SLAM Problem Major Milestones

3.3 C-SLAM systems key properties

3.3.1 Centralized, Decentralized and Distributed

Different C-SLAM solutions might be preferred depending on the properties of a given multi-robot system. One useful and common distinction focuses on how the computation tasks are shared within the team. To that end, most C-SLAM techniques are characterized using the terms centralized, decentralized and distributed [Leung, 2012]. By this classification, in a centralized system, some core computation tasks are done by one specific robot or a base station. Conversely, in a decentralized system, the computation can be performed by any one or more of the robots in the team. Aside from the centralized/decentralized classification, a system is distributed if the computation load is divided among the robots. The two notions are independent. Therefore, a system could be centralized and distributed at the same time, if, for example, each robot performs parts of the computation, but a central node is required to merge the individual results from all the robots.

The preferred choice of centralization and distribution of a C-SLAM solution is strongly connected to the multi-robot system’s team size, communication topology, communication bandwidth and team unit processing ability. A swarm-compatible C-SLAM solution would need to be both decentralized and distributed.

3.3.2 Global versus Local

Another important distinction in C-SLAM, and in multi-robot systems in general, is the difference between the global and local perspectives. The local perspective is the default point of view in single-robot SLAM. Accordingly, the pose and map estimates are expressed in an internal reference frame which is usually the starting location of the robot’s mission. However, in C-SLAM, one has to consider the global perspective of the system since the pose and map of each robot need to be expressed in a shared global reference frame. This means that every landmark can be expressed within the same coordinates system by every robot in the team. Otherwise, shared information (e.g. position of observed landmarks) would have no significance to the receiving robot due to the representation being in another unknown local reference frame. Establishing this global reference frame using C-SLAM allows the robots to collectively perceive the environment and benefit from each other’s observations.

To achieve this global understanding, one could either solve C-SLAM directly from the global perspective or solve it from a local perspective that is later aligned to the global reference frame. In the first option, the estimator has an omniscient view of the entire team of robots: it performs the estimation given perfect knowledge of the measurements of each robot. These measurements can be raw or preprocessed, and shared on demand depending on the communication limits. This approach is best suited for centralized systems.

Unfortunately, solving C-SLAM from the global perspective quickly becomes intractable as the number of robots increases [Saeedi et al., 2016]. Thus, a better solution for scalability is to solve C-SLAM from the local perspective [Cieslewski et al., 2018]. This means that each robot only has access to its own data and partial information from its neighbors. Therefore, it cannot solve the C-SLAM problem for all the robots at once, but it aims for a local solution for each robot that is consistent with its neighbors. Then, iteratively and over time, with the robots gradually improving their estimates given the neighbors’ latest data, local techniques converge to local solutions that are mutually consistent across the team of robots. So, upon convergence, the individual robots reach a common understanding and their local maps are aligned with the common (global) reference frame. Figure 4 provides examples of the C-SLAM problem and output in both perspectives.

(a) Global Perspective in C-SLAM
(b) Local Perspective in C-SLAM
Figure 4: Illustration of the global and local perspectives approaches to solve the C-SLAM estimation problem.
C-SLAM from the Global Perspective

Many seminal C-SLAM works are centralized and solve the estimation problem in eq. 4 from the global perspective. In those approaches, the robots are essentially reduced to mobile sensors whose data is collected and processed on a single computer. Examples of techniques solving C-SLAM from the global perspective include [Andersson and Nygards, 2008, Kim et al., 2010] that gather all the robots’ measurements at a central station to compute the global map. [Lázaro et al., 2013] improves this solution by marginalizing unnecessary nodes in the local pose graphs so only a few condensed measurements need to be shared to the central computer. Other centralized approaches [Forster et al., 2013, Schmuck and Chli, 2017, Schmuck and Chli, 2019] perform C-SLAM with monocular cameras, successfully solving the associated 3D estimation challenges, while [Loianno et al., 2015] focuses on micro-aerial vehicles constraints. [Deutsch et al., 2016] proposes a framework to reuse existing single robot SLAM solutions for C-SLAM. The same idea is explored in [Li et al., 2018], in which a popular single-robot SLAM technique [Mur-Artal and Tardós, 2017] is converted into C-SLAM. [Karrer et al., 2018, Karrer and Chli, 2018] integrate inertial measurements from IMUs in their centralized C-SLAM systems. [Jiménez et al., 2018] proposes that the central node spreads the resulting map across the robots to limit the memory usage.

Improving upon the centralized methods, some techniques do not rely on a single computer, but can use different robots or base stations for the computation. This way, the system can adapt itself to the failure of one node or communication link and complete the mission. Some decentralized systems solve the C-SLAM problem from the global perspective and provide a single estimate comprised of data from the whole robotic team, with a typical solution being replicated servers among the robots [Bailey et al., 2011]. Alternatively, the full mapping data is sent to every robot for redundancy and a subset of robots is designated for computation [Saeedi et al., 2011a, Bresson et al., 2013, Saeedi et al., 2015].

C-SLAM from the Local Perspective

Solving the C-SLAM problem from the local perspective is radically different, but offers major benefits in terms of computation, communication and privacy [Choudhary et al., 2017a, Cieslewski et al., 2018]. Such systems are usually distributed and solve the estimation problem from eq. 4 partially on each robot. As shown in Figure 3(b), each robot computes its own local map and uses partial information from other robots as well as inter-robot measurements to achieve a local solution. Over several iterations with its neighbors, each robot’s resulting local solution converges to a solution consistent with the global reference frame. These techniques mitigate communication and computation bottlenecks since the loads are spread across the robot team [Pfingsthorn et al., 2008]. As one would expect, distributed and local techniques come with many additional challenges that need to be tackled such as complex bookkeeping, information double counting or synchronization issues.

3.4 C-SLAM architecture

In C-SLAM, as well as in single-robot SLAM, the front-end handles perception-related tasks and the back-end generates state estimates using all measurements gathered. However, in C-SLAM, the front-end and back-end computations do not necessarily occur fully on a single robot anymore depending on the sensing, communication, and estimation strategies. For example, in a centralized system, all robots could send their sensor data directly to a single unit which would then perform the front-end and back-end steps for the whole team. While in a decentralized and distributed setup, a robot could perform feature extraction on its own and communicate with other robots for data association and state estimation. Every part of a C-SLAM system can be subject to distribution or decentralization.

In addition, the front-end needs to find links and relative measurements between the individual maps. Therefore, the front-end must also perform data association to detect and compute inter-robot loop closures, which will be detailed in Section 4. It follows that the back-end must generate estimates combining the individual and shared measurements as described in Section 5.

4 C-SLAM Front-End

Although the division between the front-end and the back-end is sometimes blurry due to the presence of feedback loops between the two processes, a typical C-SLAM front-end is in charge of producing landmark estimates, odometry measurements, and both intra-robot and inter-robot loop closures.

Odometry measurements aim to capture the translation and rotation of a robot from one time step to the next. Common techniques measure wheel movements, integrate from an IMU, and/or perform geometric matching between consecutive images or laser-scans. Intra-robot loop closures are the measurements used by a SLAM system to relocalize itself and reduce its estimate error caused by odometry drift. Using place recognition, the system can detect previously visited locations and compute relative measurements between them. In other words, intra-robot loop closures are estimates relating non-consecutive poses in the robot trajectory that observed the same places. Since the computing of odometry and intra-robot loop closure measurements can be fully done locally on each robot, the approaches used are the same in both SLAM and C-SLAM. Thus, we refer the reader to [Mohamed et al., 2019, Cadena et al., 2016, Lowry et al., 2016] for surveys of the current techniques.

Conversely, inter-robot loop closures relate poses of different robots trajectories. They are the seams that stitch together the estimates from multiple robots: they draw connections between the individual robots’ local maps to build the global understanding of the environment. Generating inter-robot loop closures is the main focus of contributions to the front-end of C-SLAM systems, and key to ensure consistency of the estimates.

4.1 Direct vs Indirect Inter-Robot Loop Closures Measurements

Inter-robot loop closures can be classified as direct or indirect [Kim et al., 2010]. Direct inter-robot loop closures occur when two robots meet, and they are able to estimate their current relative location with respect to each other through direct sensing. Indirect inter-robot loop closures are produced by looking back into maps to find partial overlaps for places that have been visited by both robots. Given these measurements, the robots can estimate the relative transformation between their maps. In general, indirect inter-robot loop closures detection produce more measurements and usually achieve a higher accuracy, but require more communication and processing. Indeed, the detection process is often the communication bottleneck of C-SLAM given the large amount of data required to compare landmarks between the individual local maps [Tardioli et al., 2015].

4.1.1 Direct Inter-Robot Loop Closures

The idea of direct inter-robot loop closures is to compute the relative pose between two or more robots when they physically meet in the same location. This is usually done through direct sensing of one another. For example, [Kim et al., 2010] operated a quadcopter and a ground robot and the latter was equipped with a checkerboard pattern that could be detected by the quadcopter’s camera. [Zhou and Roumeliotis, 2006] used a combination of direct and indirect detection approaches, where colored cylinders were installed to be detected by omnidirectional cameras. In addition, [Gentner et al., 2018, Boroson et al., 2020, Cao and Beltrame, 2020] propose to replace visual loop closures by Ultra-Wide Band (UWB) measurements from beacons onboard the robots. Given a few distance measurements provided by the UWB sensors, the robots can estimate their current relative pose with respect to each other and establish a common reference frame.

4.1.2 Indirect Inter-Robot Loop Closures

Indirect inter-robot loop closure detection is the extension of single-robot loop closure detection to multiple maps. In fact, approaches to find indirect inter-robot loop closures often rely on the same core algorithms as intra-robot loop closures. The first challenge is the loop closures detection, which consists of detecting overlaps between the individual maps. This task is usually handled by a place recognition module which can efficiently compare new observations against previous sections of the robots’ maps. Following place recognition matches, geometric estimation is performed to compute the relative pose between the two places.

In the case of visual sensors, the place recognition problem has been studied extensively [Lowry et al., 2016]. The seminal work of visual bags of binary words [Galvez-López and Tardos, 2012]

is still popular, but newer approaches based on deep learning, such as NetVLAD

[Arandjelović et al., 2018], are more accurate and data-efficient. Loop closure relative pose measurements can be computed using visual features matching and multi-view geometry [Hartley and Zisserman, 2003].

Finding inter-robot overlaps is a harder task with 3D point clouds given the dense data that need to be shared and the lack of expressive features to perform place recognition. To that end, compact and robust global point cloud descriptors [Uy and Lee, 2018] can be relied upon to compare point clouds for place recognition. Other approaches extract features from the point cloud that can serve for place recognition while providing initial guesses for later geometric alignments [Ebadi et al., 2021], or even directly compute loop closure measurements [Dubé et al., 2017a]. While the classical Iterative Closest Point method [Besl and McKay, 1992] is still commonly used in single robot SLAM to compute relative pose measurements between two matching point clouds, it is not well suited for multi-robot operation due to its reliance on a good initial guess, which is usually not available between the robots’ local maps. Therefore, a common solution is to use submaps matching for both stereo cameras [Schuster et al., 2015, Schulz et al., 2019] and lidars [Dubé et al., 2017b, Dubois et al., 2020b, Ebadi et al., 2021]. During this process, multiple laser scans or 3D point clouds are clustered into submaps which can in turn be registered more efficiently.

4.2 Map Representation

When designing large systems, the choices of map representation could affect computation load, memory usage, and communication bandwidth. First, it is important to note that an explicit map is not always required. For example, when the sole objective is collaborative localization, a feature map can be sufficient. In those cases, each robot locally tracks landmarks, or features, and searches for correspondences in other robots’ feature maps to obtain indirect inter-robot loop closure measurements. This way, the robots can operate in the same reference frame without the computation and communication burden of building an interpretable map model.

When required, the chosen map representation depends on the mission objective and environment. For example, in the case of ground robots in flat indoor environments, a 2D map might be sufficient [Caccavale and Schwager, 2018]. In those scenarios, occupancy grid maps have been shown to be a compact and more accurate solution [Martin and Emami, 2010, Saeedi et al., 2011a] than feature-based maps [Benedettelli et al., 2010]. However, 3D representations are sometimes required (e.g. for rough terrain navigation) at the cost of more computation, storage, and communication, which can be difficult to handle when resources are limited on the robots. Given the communication constraints in C-SLAM systems, compact or sparse representations, such as topological maps [H. Jacky Chang et al., 2007, Saeedi et al., 2014], are often preferred. In the same vein, some works aim for semantic-based representations in the form of sparse maps of labelled regions [Choudhary et al., 2017b]. Map representations can also affect long-term operations due to the increasing size of the map in memory [Zhang et al., 2018a], which is also a challenge in single-robot SLAM.

4.3 Efficient and Robust Communication

One of the core implementation differences between SLAM and C-SLAM is the need for communication and coordination within the robotic team. For efficiency, the required bandwidth needs to be minimal, and the communication network needs to be robust to robot failures and different topologies.

The exchanges of sensor data or representations relied upon to compute the inter-robot loop closures (Section 4.1.2) are generally the communication bottleneck of a C-SLAM system [Tardioli et al., 2015]. Robots need to share enough data to detect if other robots have visited the same area, and then estimate a map alignment using overlaps of their maps. Hence, contributions to the front-end of C-SLAM systems often consist in mechanisms to perform the search efficiently over a team considering communication constraints.

4.3.1 Efficient Data Sharing

While some early techniques simply share all the data from one robot to another, new sensors produce increasingly rich and dense data. The days of raw sensor data transmission are over and most current techniques in the literature opt for some sort of compression or reduction. Even among the early techniques [Nettleton et al., 2006], the idea of a communication budget has been explored. More recently, the topic has gathered more attention with new techniques carefully coordinating the exchange of data when two robots meet each other accounting for the available communication and computation resources [Giamou et al., 2018, Tian et al., 2018a, Tian et al., 2018b, Tian et al., 2020a]

. One idea is to compress generated maps using self-organizing maps obtained through unsupervised learning

[Saeedi et al., 2011b, Best and Hollinger, 2020]. The use of compact representations has also been explored with high-level semantic features: [Choudhary et al., 2017b] relies on objects as landmarks, needing to communicate only object labels and poses to other robots, and [Ramtoula et al., 2020] presents a compact object-based descriptor relying on the configuration of objects in a scene to perform place recognition. In addition to making representations compact, it is useful to ensure that only helpful information is shared. Hence, [Kepler and Stilwell, 2020] introduces a novelty metric so that only sufficiently novel measurements compared to the existing map are transmitted.

The problem has been extensively studied specifically for visual C-SLAM: [Tardioli et al., 2015] proposes to share visual vocabulary indexes instead of feature descriptors to reduce the required bandwidth. Other approaches focus on scalable team-wide place recognition by assigning each robot with a predetermined range of words from a pretrained visual bag of words [Cieslewski and Scaramuzza, 2017b], or regions of full-image descriptors [Cieslewski and Scaramuzza, 2017a]. [Dymczyk et al., 2015, Contreras and Mayol-Cuevas, 2017] remove landmarks that are not necessary for localization, [Opdenbosch and Steinbach, 2019] introduces a new coding to efficiently compress features, and [Dubois et al., 2019] proposes data sharing algorithms specialized for visual inertial C-SLAM.

In some extreme cases, communication is severely limited due to the properties of the transmission medium or the large distance between the robots: [Paull et al., 2014, Paull et al., 2015] explore the special case of underwater operations with low bandwidth acoustic communication, and [Schulz et al., 2019] considers long distance radio modules with very limited bandwidth to build the collaborative map through small incremental updates.

4.3.2 Network Topology

Another important aspect to consider is the network topology. Current techniques either assume full connectivity, multi-hop connectivity or are rendezvous-based. Full connectivity means that each robot can directly communicate with all other robots at any time such as in [Cieslewski and Scaramuzza, 2017a, Cieslewski and Scaramuzza, 2017b]. Multi-hop connectivity implies that robots can only share information with their neighbors and it might require multiple neighbor-to-neighbor transmissions to reach all robots [Aragüés et al., 2010, Montijano et al., 2013]. Rendezvous-based communication means that the robots share data only when they meet and, therefore, do not require any connectivity maintenance. Rendezvous-based C-SLAM also offers the opportunity to perform direct inter-robot loop closure detection during the encounters [Zhou and Roumeliotis, 2006].

The impact of the network topology is especially important during the inference step because disconnections or multi-hop paths can lead to inconsistencies or synchronization issues. Thus, [Leung et al., 2011b, Leung et al., 2012] examine the conditions that allow distributed inference to reach the same result as a centralized equivalent approach. Another approach [Quraishi et al., 2016] leverages the progress in the field of distributed computing to improve the robustness to connectivity losses, while [Tuna et al., 2015] evaluates the use of Wireless Sensor Network-based communication which is less reliable and predictable, but offers a flexible architecture with self-organization capabilities.

4.4 Heterogeneous Sensing

In many applications, the teams of robots are composed of different platforms equipped with different onboard sensors. Heterogeneous sensing comes with the additional challenge of matching map data in different representation to perform relocalization and/or map fusion. To this end, a recent study evaluated the repeatability of existing keypoint detectors between data from stereo cameras and lidars For example, when matching data from both stereo cameras and lidars, one needs to chose repeatable 3D feature representations that are consistent despite the differences in density and field-of-view [Boroson and Ayanian, 2019]. Another approach is to use an intermediate map representation that can be produced by different kinds of sensors [Koch and Lacroix, 2016]. For example, [Käslin et al., 2016] proposes to compare elevation maps that are invariant to sensor choice: lidars or cameras.

4.5 Non-Conventional Sensing

While most C-SLAM techniques use the typical SLAM sensors (i.e., lidars and monocular, RGB-D, or stereo cameras), many recent research works have explored the use of non-conventional sensors: [Choi et al., 2014] uses omnidirectional (i.e., fish-eye) cameras, [Waniek et al., 2015] performs C-SLAM with event-based vision sensors, and [Morales and Kassas, 2018] integrates ambient radio signals (i.e., signals of opportunity) into their system. In a similar vein, [Liu et al., 2020] leverages existing WiFi access points in most indoor environments to perform loop closures based on their radio signal fingerprint. There is also an ongoing trend of leveraging semantic information obtained through deep learning to perform loop closure detection as explored in Section 7.2.

5 C-SLAM Back-End

As mentioned before, the role of the C-SLAM back-end is to estimate the state of the robot and the map given the front-end measurements. The difference with single-robot SLAM is the presence of inter-robot measurements, the need to reach consensus, and the potential lack of an initial guess since the global reference frame and the starting positions of the robots are usually initially unknown. Nevertheless, similar to single-robot solvers, C-SLAM back-ends are roughly divided in two main categories of inference techniques: filtering-based and smoothing-based. Although filtering-based approaches were the most common among the early techniques (e.g. EKF [Rekleitis et al., 2003] and particle filters [Madhavan et al., 2004]), smoothing-based approaches quickly gained in popularity and are currently considered as superior in most applications [Strasdat et al., 2012]. This section provides an overview of the different categories of estimation workhorses for C-SLAM and presents examples from the literature.

5.1 Filtering-Based Estimation

Filtering approaches are often characterized as online in the sense that only the current robot pose is estimated and all previous poses are marginalized out [Thrun et al., 2005] at each time step. Consequently, the estimation of the posterior in eq. 1 at time only depends on the posterior at time and the new measurements.

The classical filtering technique for nonlinear problems (i.e., all problems in robotics except trivial ones) is the Extended Kalman Filter (EKF). It has been applied to C-SLAM in various ways among which the information filter method presented in [Thrun and Liu, 2005]. In a nutshell, EKF are Gaussian filters that circumvent the linear assumptions of Kalman filters through linearization (i.e., local linear approximation); however, the linearization process potentially leads to inconsistencies when the noise is too large. A major advantage of EKF techniques [Thrun and Liu, 2005, Sasaoka et al., 2016, Luft et al., 2016, Schuster et al., 2019] over smoothing techniques is that the covariance matrix is available without requiring additional computation, which can be useful for feature tracking or active exploration. For example, one could prioritize the exploration in the most uncertain directions. Yet, an explicit covariance matrix is rarely required, so alternative filtering techniques seek to avoid its computation, such as the smooth variable structure filters approach presented in [Demim et al., 2017].

Building on the EKF, Rao-Blackwellized Particle Filters (RBPF) [Doucet et al., 2000] are another popular filtering approach for the C-SLAM problem. Techniques, such as [Howard, 2006], use samples (particles) to represent the posterior distribution in eq. 1 and perform variable marginalization using an EKF which drastically reduce the size of the sampling space. [Carlone et al., 2011] extends on [Howard, 2006] and improves its consistency while making it fully distributed. [Gil et al., 2010] adapts RBPF to visual C-SLAM and [Dörr et al., 2016] showcases the potential of RBPF C-SLAM for industrial applications.

5.2 Smoothing-Based Estimation

Besides the linearization error, another drawback of filtering techniques is that the marginalization of past pose variables leads to many new links among the remaining variables. Indeed, the elimination of each pose variable leads to interdependence between every landmark variables to which it was connected. As a result, the variables become increasingly coupled and this leads to more computation. However, in smoothing, there is less marginalization required which means that the variables will stay sparsely connected. This sparsity is exploited by modern solvers to yield significant speed-ups [Strasdat et al., 2012]. In addition, unlike filtering-based approaches, smoothing techniques improve their accuracy by revisiting past measurements instead of only working from the latest estimate. Hence, filtering techniques fell out of favor due to the better performance of smoothing both in terms of accuracy and efficiency [Strasdat et al., 2012]. Moreover, in the context of C-SLAM, the sparsity reduces the amount of data to be exchanged during the estimation process [Paull et al., 2015].

In the following, we present a general smoothing formulation for pose-graph C-SLAM with two robots in which the map landmarks are marginalized into odometry and loop closure measurements.

First, assuming that the measurements noises are uncorrelated, we can factorize eq. 4 as follows:

(5)

where is the likelihood of measurement given the subset of variable on which it is solely dependent, is the likelihood of measurement given the subset of variable on which it is solely dependent, is the likelihood of measurement given the subset of variable and . There are measurements related only to state variables from robot , measurements related only to state variables from robot , and measurements related to state variables from both robots.

Second, assuming that the measurements are disturbed by zero-mean Gaussian noise with information matrix (i.e., inverse of the covariance), we can express the individual measurement likelihood as

(6)

where is a function that maps the state variables to the measurements.

Third, since maximizing the likelihood is equivalent to minimizing the negative log-likelihood, we obtain the following nonlinear least squares formulation of problem 4:

(7)

This nonlinear least squares problem can be solved either on a single computer or in a distributed fashion. In the centralized case, one can simply use single-robot pose graph optimization solvers [Agarwal et al.,, Kümmerle et al., 2011, F. Dellaert et al.,, Rosen et al., 2019]. Incremental single-robot solvers can also be adapted for the centralized C-SLAM problem to continuously update the global pose graph with the latest measurements from the robots [Dong et al., 2015].

Among the distributed solvers, many early techniques used Gaussian elimination [Cunningham et al., 2010, Cunningham et al., 2013, Cunningham et al., 2012]. Although popular, those approaches require the exchange of dense marginals which means that the communication cost is quadratic on the number of inter-robot measurements. Furthermore, those approaches rely on linearization, so they require complex bookkeeping to ensure the consistency at the linearization point within the team of robots. To reduce the complexity, [Nerurkar et al., 2009] introduces a distributed marginalization scheme to limit the size of the optimization problem.

More recently, the approach in [Choudhary et al., 2017a] leverages the Distributed Gauss-Seidel algorithm introduced in [Bertsekas and Tsitsiklis, 1989] to solve eq. 7. This technique avoids complex bookkeeping and information double-counting in addition of satisfying privacy constraints by exchanging minimal information on the robot individual trajectories.

Riemannian gradient descent has also been considered extensively to solve the C-SLAM problem [Knuth and Barooah, 2012, Knuth and Barooah, 2013]. Approaches in [Tron and Vidal, 2009, Tron and Vidal, 2014, Tron et al., 2016] introduce a multi-stage distributed Riemannian consensus protocol with convergence guarantees to globally optimal solutions in noiseless scenarios. Expanding on those ideas, a recent technique [Tian et al., 2021], based upon a sparse semidefinite relaxation, provides exactness guarantees even in the presence of moderate measurement noise. Moreover, this latter technique has been extended to consider asynchronous scenarios and parallel computation [Tian et al., 2020b], which are often critical to deal with communication delays inherent to multi-robot systems.

5.3 Other Estimation Techniques

Other estimation techniques have been proposed for C-SLAM. Among them, the distributed Jacobi approach has been shown to work for 2D poses [Aragues et al., 2011]. [Franceschelli and Gasparri, 2010, Aragues et al., 2012] look into consensus-based algorithms and prove their convergence across teams of robots. Also, apart from the solver itself, researchers have studied which measurement and noise models are the best suited for C-SLAM [Indelman et al., 2012].

We observe that more exciting new directions are still being discovered, considering that recent approaches such as [Tian et al., 2021] have been shown to outperform, both in accuracy and convergence rate, the well established Distributed Gauss-Seidel pose graph optimization method [Choudhary et al., 2017a] reused in many state-of-the-art C-SLAM systems such as [Cieslewski et al., 2018, Lajoie et al., 2020, Wang et al., 2019]. Those promising approaches also include the majorization-minimization technique from [Fan and Murphey, 2020]

and the consensus-based 3D pose estimation technique inspired by distributed formation control from

[Cristofalo et al., 2019, Cristofalo et al., 2020].

5.4 Perceptual Aliasing Mitigation

As it is the case in single robot SLAM, loop closure detection is vulnerable to spurious measurements, i.e., outliers, due to perceptual aliasing

[Sünderhauf and Protzel, 2012, Agarwal et al., 2013, Latif et al., 2013, Lajoie et al., 2019]. This phenomenon occurs when two different places are conflated as the same during the place recognition process. This motivates the need for robust techniques that can detect and remove those outliers to avoid dramatic distortions in the C-SLAM estimates. Outliers mitigation might also help against adversarial attacks by rejecting spurious measurements injected by a nefarious agent.

The classic approach to remove outliers is to use the RANSAC algorithm [Fischler and Bolles, 1981] to find a set of mutually consistent measurements [Dong et al., 2015]. While RANSAC works well in centralized settings, it is not adapted to distributed systems. Therefore, researchers recently explored other ways of detecting outliers such as leveraging extra information from the wireless communication channels during a rendezvous between two robots [Wang et al., 2019]. Since such approaches work only for direct inter-robot loop closures, there is a need for general robust data association in the back-end. To that end, [Indelman et al., 2014]

uses expectation maximization to infer which inter-robot measurements are inliers and which ones are outliers. However, probably the most popular approach currently in C-SLAM is the use of pairwise consistency maximization to search for the maximal clique of pairwise consistent measurements among the inter-robot loop closures

[Mangelson et al., 2018]. [Lajoie et al., 2020] introduces a distributed implementation of this technique which does not require any additional communication when paired with distributed pose graph optimization, while [Chang et al., 2020] proposes an incremental version, and [Do et al., 2020] extends the pairwise consistency evaluation with a data similarity metric. It is important to note that those latest approaches only apply to smoothing-based C-SLAM since, unlike filtering, it allows the removal of past measurements from the estimation.

6 Benchmarking C-SLAM

Despite the tremendous progress in the field during the last decade, C-SLAM techniques face tough challenges in terms of reproducibility and benchmarking. C-SLAM systems involve multiple software modules and lots of different hardware components, making it hard to replicate perfectly. While standardized benchmarking approaches have been emerging for single-robot SLAM [Bujanca et al., 2019], such systematic evaluation techniques are still lacking for C-SLAM.

Moreover, only a few datasets dedicated to C-SLAM exist. [Leung et al., 2011a] consists of 9 monocular camera subdatasets and [Dubois et al., 2020a] is dedicated to stereo-inertial C-SLAM. Therefore, the common approach to evaluate C-SLAM solutions is to split single robot SLAM datasets into multiple parts and to associate each one to a robot. When splitting the dataset, careful attention has to be given to ensure the presence of overlaps between the parts for loop closing. In addition, one should avoid overlaps near the cutting points, where the viewpoint and lighting conditions are exactly the same since they depict the same place viewed by the robot at the same point in time: this kind of overlaps is highly unrealistic in multi-robot operations. One of the most used dataset in the literature is the KITTI self-driving car dataset comprised of lidar and stereo camera data [Geiger et al., 2012]. New datasets of interest include KITTI360 [Xie et al., 2016] which adds fish-eye cameras and the very large Pit30M lidar and monocular camera dataset that contains over 30 million frames [Martinez et al., 2020].

7 Ongoing and Future Trends

This section presents trending ideas in the research community to improve C-SLAM. Those new trends push the boundaries of what C-SLAM can do and offer an exciting view of the field’s future.

7.1 Active C-SLAM

The concept of active SLAM comes from the powerful idea that while SLAM naturally improves path planning and control, those can also improve SLAM. In C-SLAM, gains can also be made by leveraging the coordination between the mapping robots. Having feedback loops to the C-SLAM algorithm allows path planning optimization for faster coverage and mapping of the environment [Bryson and Sukkarieh, 2007, Bryson and Sukkarieh, 2009]. To achieve those goals, [Mahdoui et al., 2020] aims to minimize the global exploration time and the average travelled distance. Other examples of the coupling between path planning and SLAM include [Trujillo et al., 2018] which shows the advantages of UAVs flying in formation for monocular C-SLAM, and [Pei et al., 2020] which uses deep Q-learning to decide whether a robot should localize the others or continue exploring on its own.

Active C-SLAM can also increase the estimation accuracy. To that end, [Dinnissen et al., 2012]

uses reinforcement learning to determine the best moment to merge the local maps, and

[Kontitsis et al., 2013] leverages instead the covariance matrix computed by the EKF-based inference engine to select trajectories that reduces the map uncertainty. Similarly, [Atanasov et al., 2015] develops a theoretical approach to design a sensor control policy which minimizes the entropy of the estimation task, while [Chen et al., 2020] proposes to broadcast the weakest nodes in the C-SLAM pose graph topology to actively increase the estimation accuracy.

7.2 Semantic C-SLAM

With the rise of deep learning and its impressive semantic inference capabilities, a lot of interest have been directed towards semantic mapping in which the environment is interpreted using class labels (i.e., person, car, chair, etc.).

This idea was first applied to C-SLAM in [Wu et al., 2009] which detects blobs of colors as salient landmarks in the robots maps. [Choudhary et al., 2017b] later leverages deep learning-based object detection to perform object-based C-SLAM. Representing maps as a collection of objects is very compact and therefore well suited for systems with tight communication constraints. However, those object-based techniques rely heavily upon the presence of many objects of the known classes in the environment (i.e., classes in the training data). Thus, they do not generalize well to arbitrary settings.

The other preferred approach for semantic C-SLAM is to annotate maps of the environment with class labels. For example, [Frey et al., 2019, Ramtoula et al., 2020] use constellations of landmarks each comprised of a 3D point cloud, a class label and an appearance descriptor. [Tchuiev and Indelman, 2020] considers the joint estimation of object labels and poses in addition to the robots poses. [Chang et al., 2020] builds globally consistent local metric maps that are enhanced with local semantic labelling.

7.3 Dynamic Environments

Another inherent problem in multi-robot system is the presence of moving objects in the environment (e.g. people, vehicles, or other moving robots). This is a substantial issue since SLAM techniques rely on the tracking of static landmarks. To solve this problem, [Lee and Lee, 2009] proposes the simple idea of pointing the cameras towards the ceiling when operating indoors with ground robots. [Zou and Tan, 2013] proposes instead to classify dynamic points using the reprojection error and to keep only the static points for estimation. In a different vein, [Moratuwage et al., 2013, Moratuwage et al., 2014, Battistelli et al., 2017] and more recently [Gao et al., 2020] extend upon the Rao-Blackwellized particle filters framework to track moving features and remove them from the estimation process. Those works use Random-Finite-Sets which were originally developed for multi-target tracking. This way, they manage to incorporate data association, landmark appearance and disappearance, missed detections, and false alarms in the filtering process.

7.4 Cloud Robotics

Recent research suggest that C-SLAM could efficiently leverage the recent progress in cloud computing. The connection between the two fields is somewhat intuitive. Why perform all the processing on robots with limited resources when we could use powerful remote clusters of servers instead? For example, [Riazuelo et al., 2014] offloads the expensive map optimization and storage to a server in the cloud. [Yun et al., 2017] proposes a cloud robotics framework for C-SLAM based on available commercial platforms. Using a similar approach, [Zhang et al., 2018b] manages to perform C-SLAM with up to 256 robots. This is orders of magnitude more than the current techniques based on onboard computation can achieve.

However, while cloud techniques solve the problem of limited computing power onboard the robots, they still face the issue of limited communication bandwidth which is exacerbated when many robots transmit their data through a single internet link. Hence, instead of using remote servers, [Gouveia et al., 2015] proposes to use a subset of a team of robots to act as a computing cluster to free other robots from the heavy computation burden. Such moving clusters performing computing closer to the sources of data are in accordance with the edge computing paradigm [Satyanarayanan, 2017] to save bandwidth and reduce response time.

7.5 Augmented Reality

Apart from the well known UAV or self-driving cars applications, Augmented Reality (AR) is probably one of the biggest field of application of SLAM. Indeed, SLAM makes markerless AR applications possible by building a map of the surrounding environment which is essential to overlay digital interactive augmentations. In other words, SLAM is required to make AR work in environments without motion capture, localization beacons or predetermined markers. In the foreseeable future, AR applications and games will push for multi-agent collaboration and this is where C-SLAM comes into play [Egodagamage and Tuceryan, 2017, Egodagamage and Tuceryan, 2018]. To that end, [Morrison et al., 2016] proposes a centralized approach in which virtual elements are shared by all agents, and [Sartipi et al., 2019] introduces a decentralized AR technique with smartphones, making use of the visual and inertial sensors already present in those devices.

Some other techniques also look at the tremendous potential of AR for intuitive robotic control. [Sidaoui et al., 2019] adds a human in the loop equipped with an AR system to edit and correct the map produced by a robot during a mission. Interestingly, [Yu et al., 2020] goes for an opposite approach in which humans, equipped with smartphones, map an environment and get feedback from a central server to indicate which unscanned areas still need to be explored.

8 Conclusions

In this paper, we presented the core ideas behind Collaborative Simultaneous Localization and Mapping and provided a survey of existing techniques. First, we introduced the basic concepts of a C-SLAM system. We provided explanations and bits of historical context to better understand the astonishing progress recently made in the field. Then, we presented the building blocks of a typical C-SLAM system and the associated techniques in the literature. We also touched upon the difficulties of reproducibility and benchmarking. Afterwards, we explored new trends and challenges in the field that will certainly receive a lot more interests in the future. In summary, we focused on providing a complete overview of the C-SLAM research landscape.

We have shown, through numerous examples, how C-SLAM systems are varied and need to match closely the application requirements: sparse or dense maps, precise or topological localization, the number of robots involved, the networking limitations, etc. We wish for this survey to be a useful tool for C-SLAM practionners looking for adequate solutions to their specific problems.

Nevertheless, despite the current growing interest for C-SLAM applications, it is still a young topic of research and many fundamental problems have to be resolved before the advance of C-SLAM-based commercial products. In particular, we believe that current systems scale poorly and are often limited to very few robots. So, a lot of work is still required to achieve large teams of robots building maps and localizing themselves collaboratively. We also note the growing interest for semantic C-SLAM to make robotic maps more interpretable and more actionable. Scene understanding techniques in the computer vision field could bring more compact and expressive environment representations into the SLAM system, which potentially increase the map readability while reducing the communication burden. Furthermore, the rise of AR, in conjunction with C-SLAM and semantics, will offer incredible opportunities of innovation in the fields of robotics, mobile sensing, and entertainment.

Acknowledgments

This work was partially supported by a Canadian Space Agency FAST Grant, a Vanier Canada Graduate Scholarships Award, the Arbour Foundation, the EPSRC Centre for Doctoral Training in Autonomous Intelligent Machines and Systems [EP/S024050/1], and Oxbotica.

References

  • [Agarwal et al., 2013] Agarwal, P., Tipaldi, G. D., Spinello, L., Stachniss, C., and Burgard, W. (2013). Robust map optimization using dynamic covariance scaling. In 2013 IEEE International Conference on Robotics and Automation, pages 62–69.
  • [Agarwal et al., ] Agarwal, S., Mierle, K., and Others. Ceres Solver — A Large Scale Non-linear Optimization Library. http://ceres-solver.org/.
  • [Andersson and Nygards, 2008] Andersson, L. A. A. and Nygards, J. (2008). C-SAM: Multi-Robot SLAM using square root information smoothing. In 2008 IEEE International Conference on Robotics and Automation, pages 2798–2805.
  • [Aragues et al., 2011] Aragues, R., Carlone, L., Calafiore, G., and Sagues, C. (2011). Multi-agent localization from noisy relative pose measurements. In 2011 IEEE International Conference on Robotics and Automation, pages 364–369.
  • [Aragues et al., 2012] Aragues, R., Cortes, J., and Sagues, C. (2012). Distributed Consensus on Robot Networks for Dynamically Merging Feature-Based Maps. IEEE Transactions on Robotics, 28(4):840–854.
  • [Aragüés et al., 2010] Aragüés, R., Montijano, E., and Sagüés, C. (2010). Consistent data association in multi-robot systems with limited communications. In In Robotics: Science and Systems, pages 97–104.
  • [Arandjelović et al., 2018] Arandjelović, R., Gronat, P., Torii, A., Pajdla, T., and Sivic, J. (2018). NetVLAD: CNN Architecture for Weakly Supervised Place Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(6):1437–1451.
  • [Atanasov et al., 2015] Atanasov, N., Ny, J. L., Daniilidis, K., and Pappas, G. J. (2015). Decentralized active information acquisition: Theory and application to multi-robot SLAM. In 2015 IEEE International Conference on Robotics and Automation (ICRA), pages 4775–4782.
  • [Bailey et al., 2011] Bailey, T., Bryson, M., Mu, H., Vial, J., McCalman, L., and Durrant-Whyte, H. (2011). Decentralised cooperative localisation for heterogeneous teams of mobile robots. In 2011 IEEE International Conference on Robotics and Automation, pages 2859–2865.
  • [Barfoot, 2017] Barfoot, T. D. (2017). State Estimation for Robotics. Cambridge University Press, Cambridge.
  • [Battistelli et al., 2017] Battistelli, G., Chisci, L., and Laurenzi, A. (2017). Random Set Approach to Distributed Multivehicle SLAM. IFAC-PapersOnLine, 50(1):2457–2464.
  • [Benedettelli et al., 2010] Benedettelli, D., Garulli, A., and Giannitrapani, A. (2010). Multi-robot SLAM using M-Space feature representation. In 49th IEEE Conference on Decision and Control (CDC), pages 3826–3831.
  • [Beni, 2004] Beni, G. (2004). From swarm intelligence to swarm robotics. In Proceedings of the 2004 International Conference on Swarm Robotics, SAB’04, pages 1–9, Berlin, Heidelberg. Springer-Verlag.
  • [Bertsekas and Tsitsiklis, 1989] Bertsekas, D. and Tsitsiklis, J. (1989). Parallel and Distributed Computation. Englewood Cliffs, NJ: Prentice-Hall.
  • [Besl and McKay, 1992] Besl, P. J. and McKay, N. D. (1992). A method for registration of 3-D shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(2):239–256.
  • [Best and Hollinger, 2020] Best, G. and Hollinger, G. (2020). Decentralised Self-Organising Maps for Multi-Robot Information Gathering. 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), page 8.
  • [Bezouska and Barnhart, 2019] Bezouska, W. and Barnhart, D. (2019). Decentralized Cooperative Localization with Relative Pose Estimation for a Spacecraft Swarm. In 2019 IEEE Aerospace Conference, pages 1–13.
  • [Bonin-Font and Burguera, 2020] Bonin-Font, F. and Burguera, A. (2020). Towards Multi-Robot Visual Graph-SLAM for Autonomous Marine Vehicles. Journal of Marine Science and Engineering, 8(6):437.
  • [Boroson et al., 2020] Boroson, E., Hewitt, R., and Ayanian, N. (2020). Inter-Robot Range Measurements in Pose Graph Optimization. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), page 8.
  • [Boroson and Ayanian, 2019] Boroson, E. R. and Ayanian, N. (2019). 3D Keypoint Repeatability for Heterogeneous Multi-Robot SLAM. In 2019 International Conference on Robotics and Automation (ICRA), pages 6337–6343.
  • [Brambilla et al., 2013] Brambilla, M., Ferrante, E., Birattari, M., and Dorigo, M. (2013). Swarm robotics: a review from the swarm engineering perspective. Swarm Intelligence, 7(1):1–41.
  • [Bresson et al., 2013] Bresson, G., Aufrère, R., and Chapuis, R. (2013). Consistent multi-robot decentralized SLAM with unknown initial positions. In Proceedings of the 16th International Conference on Information Fusion, pages 372–379.
  • [Bryson and Sukkarieh, 2007] Bryson, M. and Sukkarieh, S. (2007). Co-operative Localisation and Mapping for Multiple UAVs in Unknown Environments. In 2007 IEEE Aerospace Conference, pages 1–12.
  • [Bryson and Sukkarieh, 2009] Bryson, M. and Sukkarieh, S. (2009). Architectures for Cooperative Airborne Simultaneous Localisation and Mapping. Journal of Intelligent and Robotic Systems, 55(4):267–297.
  • [Bujanca et al., 2019] Bujanca, M., Gafton, P., Saeedi, S., Nisbet, A., Bodin, B., O’Boyle, M. F. P., Davison, A. J., Kelly, P. H. J., Riley, G., Lennox, B., Luján, M., and Furber, S. (2019). SLAMBench 3.0: Systematic Automated Reproducible Evaluation of SLAM Systems for Robot Vision Challenges and Scene Understanding. In 2019 International Conference on Robotics and Automation (ICRA), pages 6351–6358.
  • [Caccavale and Schwager, 2018] Caccavale, A. and Schwager, M. (2018). Wireframe mapping for resource-constrained robots. In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 1–9.
  • [Cadena et al., 2016] Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I., and Leonard, J. J. (2016). Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age. IEEE Transactions on Robotics, 32(6):1309–1332.
  • [Cao and Beltrame, 2020] Cao, Y. and Beltrame, G. (2020). VIR-SLAM: Visual, Inertial, and Ranging SLAM for single and multi-robot systems. arXiv:2006.00420 [cs].
  • [Carlone et al., 2011] Carlone, L., Kaouk Ng, M., Du, J., Bona, B., and Indri, M. (2011). Simultaneous Localization and Mapping Using Rao-Blackwellized Particle Filters in Multi Robot Systems. Journal of Intelligent & Robotic Systems, 63(2):283–307.
  • [Chang et al., 2020] Chang, Y., Tian, Y., How, J. P., and Carlone, L. (2020). Kimera-Multi: A System for Distributed Multi-Robot Metric-Semantic Simultaneous Localization and Mapping. arXiv:2011.04087 [cs].
  • [Chen et al., 2020] Chen, Y., Zhao, L., Lee, K. M. B., Yoo, C., Huang, S., and Fitch, R. (2020). Broadcast Your Weaknesses: Cooperative Active Pose-Graph SLAM for Multiple Robots. IEEE Robotics and Automation Letters, 5(2):2200–2207.
  • [Choi et al., 2014] Choi, Y.-W., Kwon, K.-K., Lee, S.-I., Choi, J.-W., and Lee, S.-G. (2014). Multi-robot Mapping Using Omnidirectional-Vision SLAM Based on Fisheye Images. ETRI Journal, 36(6):913–923.
  • [Choudhary et al., 2017a] Choudhary, S., Carlone, L., Nieto, C., Rogers, J., Christensen, H. I., and Dellaert, F. (2017a). Distributed mapping with privacy and communication constraints: Lightweight algorithms and object-based models. The International Journal of Robotics Research, 36(12):1286–1311.
  • [Choudhary et al., 2017b] Choudhary, S., Carlone, L., Nieto, C., Rogers, J., Liu, Z., Christensen, H. I., and Dellaert, F. (2017b). Multi Robot Object-Based SLAM. In Kulić, D., Nakamura, Y., Khatib, O., and Venture, G., editors, 2016 International Symposium on Experimental Robotics, Springer Proceedings in Advanced Robotics, pages 729–741, Cham. Springer International Publishing.
  • [Cieslewski et al., 2018] Cieslewski, T., Choudhary, S., and Scaramuzza, D. (2018). Data-Efficient Decentralized Visual SLAM. In 2018 IEEE International Conference on Robotics and Automation (ICRA), pages 2466–2473.
  • [Cieslewski and Scaramuzza, 2017a] Cieslewski, T. and Scaramuzza, D. (2017a). Efficient decentralized visual place recognition from full-image descriptors. In 2017 International Symposium on Multi-Robot and Multi-Agent Systems (MRS), pages 78–82.
  • [Cieslewski and Scaramuzza, 2017b] Cieslewski, T. and Scaramuzza, D. (2017b). Efficient Decentralized Visual Place Recognition Using a Distributed Inverted Index. IEEE Robotics and Automation Letters, 2(2):640–647.
  • [Contreras and Mayol-Cuevas, 2017] Contreras, L. and Mayol-Cuevas, W. (2017). O-POCO: Online point cloud compression mapping for visual odometry and SLAM. In 2017 IEEE International Conference on Robotics and Automation (ICRA), pages 4509–4514.
  • [Cristofalo et al., 2019] Cristofalo, E., Montijano, E., and Schwager, M. (2019). Consensus-based Distributed 3D Pose Estimation with Noisy Relative Measurements. In 2019 IEEE 58th Conference on Decision and Control (CDC), pages 2646–2653, Nice, France. IEEE.
  • [Cristofalo et al., 2020] Cristofalo, E., Montijano, E., and Schwager, M. (2020). GeoD: Consensus-based Geodesic Distributed Pose Graph Optimization. arXiv:2010.00156 [cs, eess].
  • [Cunningham et al., 2013] Cunningham, A., Indelman, V., and Dellaert, F. (2013). DDF-SAM 2.0: Consistent distributed smoothing and mapping. In 2013 IEEE International Conference on Robotics and Automation, pages 5220–5227.
  • [Cunningham et al., 2010] Cunningham, A., Paluri, M., and Dellaert, F. (2010). DDF-SAM: Fully distributed SLAM using Constrained Factor Graphs. In 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 3025–3030.
  • [Cunningham et al., 2012] Cunningham, A., Wurm, K. M., Burgard, W., and Dellaert, F. (2012). Fully distributed scalable smoothing and mapping with robust multi-robot data association. In 2012 IEEE International Conference on Robotics and Automation, pages 1093–1100, St Paul, MN, USA. IEEE.
  • [DARPA, 2020] DARPA (2020). DARPA Subterranean Challenge. https://www.subtchallenge.com/.
  • [Demim et al., 2017] Demim, F., Nemra, A., Louadj, K., Hamerlain, M., and Bazoula, A. (2017). Cooperative SLAM for multiple UGVs navigation using SVSF filter. Automatika, 58(1):119–129.
  • [Deutsch et al., 2016] Deutsch, I., Liu, M., and Siegwart, R. (2016). A framework for multi-robot pose graph SLAM. In 2016 IEEE International Conference on Real-Time Computing and Robotics (RCAR), pages 567–572.
  • [Dinnissen et al., 2012] Dinnissen, P., Givigi, S. N., and Schwartz, H. M. (2012). Map merging of Multi-Robot SLAM using Reinforcement Learning. In 2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pages 53–60.
  • [Do et al., 2020] Do, H., Hong, S., and Kim, J. (2020). Robust Loop Closure Method for Multi-Robot Map Fusion by Integration of Consistency and Data Similarity. IEEE Robotics and Automation Letters, 5(4):5701–5708.
  • [Dong et al., 2015] Dong, J., Nelson, E., Indelman, V., Michael, N., and Dellaert, F. (2015). Distributed real-time cooperative localization and mapping using an uncertainty-aware expectation maximization approach. In 2015 IEEE International Conference on Robotics and Automation (ICRA), pages 5807–5814.
  • [Dörr et al., 2016] Dörr, S., Barsch, P., Gruhler, M., and Lopez, F. G. (2016). Cooperative longterm SLAM for navigating mobile robots in industrial applications. In 2016 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI), pages 297–303.
  • [Doucet et al., 2000] Doucet, A., de Freitas, N., Murphy, K. P., and Russell, S. J. (2000).

    Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks.

    In

    Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence

    , UAI ’00, pages 176–183, San Francisco, CA, USA. Morgan Kaufmann Publishers Inc.
  • [Dubé et al., 2017a] Dubé, R., Dugas, D., Stumm, E., Nieto, J., Siegwart, R., and Cadena, C. (2017a). Segmatch: Segment based place recognition in 3d point clouds. In 2017 IEEE International Conference on Robotics and Automation (ICRA), pages 5266–5272. IEEE.
  • [Dubé et al., 2017b] Dubé, R., Gawel, A., Sommer, H., Nieto, J., Siegwart, R., and Cadena, C. (2017b). An online multi-robot SLAM system for 3D LiDARs. In 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 1004–1011.
  • [Dubois et al., 2019] Dubois, R., Eudes, A., and Frémont, V. (2019). On Data Sharing Strategy for Decentralized Collaborative Visual-Inertial Simultaneous Localization And Mapping. In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 2123–2130.
  • [Dubois et al., 2020a] Dubois, R., Eudes, A., and Frémont, V. (2020a). AirMuseum: A heterogeneous multi-robot dataset for stereo-visual and inertial Simultaneous Localization And Mapping. In 2020 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI), pages 166–172.
  • [Dubois et al., 2020b] Dubois, R., Eudes, A., Moras, J., and Fremont, V. (2020b). Dense Decentralized Multi-Robot SLAM Based on Locally Consistent TSDF Submaps. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), page 8.
  • [Dudek et al., 1993] Dudek, G., Jenkin, M., Milios, E., and Wilkes, D. (1993). A taxonomy for swarm robots. In Proceedings of 1993 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS’93), volume 1, pages 441–447. IEEE.
  • [Dymczyk et al., 2015] Dymczyk, M., Lynen, S., Cieslewski, T., Bosse, M., Siegwart, R., and Furgale, P. (2015). The gist of maps - summarizing experience for lifelong localization. In 2015 IEEE International Conference on Robotics and Automation (ICRA), pages 2767–2773.
  • [Ebadi et al., 2021] Ebadi, K., Palieri, M., Wood, S., Padgett, C., and Agha-mohammadi, A.-a. (2021). DARE-SLAM: Degeneracy-Aware and Resilient Loop Closing in Perceptually-Degraded Environments. arXiv:2102.05117 [cs].
  • [Egodagamage and Tuceryan, 2017] Egodagamage, R. and Tuceryan, M. (2017). A Collaborative Augmented Reality Framework Based on Distributed Visual Slam. In 2017 International Conference on Cyberworlds (CW), pages 25–32.
  • [Egodagamage and Tuceryan, 2018] Egodagamage, R. and Tuceryan, M. (2018). Distributed monocular visual SLAM as a basis for a collaborative augmented reality framework. Computers & Graphics, 71:113–123.
  • [F. Dellaert et al., ] F. Dellaert et al. Georgia Tech Smoothing And Mapping (GTSAM). http://gtsam.org/.
  • [Fan and Murphey, 2020] Fan, T. and Murphey, T. (2020). Majorization Minimization Methods for Distributed Pose Graph Optimization with Convergence Guarantees. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 5058–5065, Las Vegas, NV, USA. IEEE.
  • [Fenwick et al., 2002] Fenwick, J. W., Newman, P. M., and Leonard, J. J. (2002). Cooperative concurrent mapping and localization. In Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292), volume 2, pages 1810–1817 vol.2.
  • [Fischler and Bolles, 1981] Fischler, M. A. and Bolles, R. C. (1981). Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6):381–395.
  • [Forster et al., 2013] Forster, C., Lynen, S., Kneip, L., and Scaramuzza, D. (2013). Collaborative monocular SLAM with multiple Micro Aerial Vehicles. In 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 3962–3970.
  • [Fox et al., 2000] Fox, D., Burgard, W., Kruppa, H., and Thrun, S. (2000). A Probabilistic Approach to Collaborative Multi-Robot Localization. Autonomous Robots, 8(3):325–344.
  • [Franceschelli and Gasparri, 2010] Franceschelli, M. and Gasparri, A. (2010). On agreement problems with gossip algorithms in absence of common reference frames. In 2010 IEEE International Conference on Robotics and Automation, pages 4481–4486.
  • [Frey et al., 2019] Frey, K. M., Steiner, T. J., and How, J. P. (2019). Efficient Constellation-Based Map-Merging for Semantic SLAM. In 2019 International Conference on Robotics and Automation (ICRA), pages 1302–1308.
  • [Galvez-López and Tardos, 2012] Galvez-López, D. and Tardos, J. D. (2012). Bags of Binary Words for Fast Place Recognition in Image Sequences. IEEE Transactions on Robotics, 28(5):1188–1197.
  • [Gao et al., 2020] Gao, L., Battistelli, G., and Chisci, L. (2020). Random-Finite-Set-Based Distributed Multirobot SLAM. IEEE Transactions on Robotics, 36(6):1758–1777.
  • [Geiger et al., 2012] Geiger, A., Lenz, P., and Urtasun, R. (2012). Are we ready for autonomous driving? The KITTI vision benchmark suite. In

    2012 IEEE Conference on Computer Vision and Pattern Recognition

    , pages 3354–3361, Providence, RI. IEEE.
  • [Gentner et al., 2018] Gentner, C., Ulmschneider, M., and Jost, T. (2018). Cooperative simultaneous localization and mapping for pedestrians using low-cost ultra-wideband system and gyroscope. In 2018 IEEE/ION Position, Location and Navigation Symposium (PLANS), pages 1197–1205.
  • [Giamou et al., 2018] Giamou, M., Khosoussi, K., and How, J. P. (2018). Talk Resource-Efficiently to Me: Optimal Communication Planning for Distributed Loop Closure Detection. In 2018 IEEE International Conference on Robotics and Automation (ICRA), pages 3841–3848.
  • [Gil et al., 2010] Gil, A., Reinoso, Ó., Ballesta, M., and Juliá, M. (2010). Multi-robot visual SLAM using a Rao-Blackwellized particle filter. Robotics and Autonomous Systems, 58(1):68–80.
  • [Gouveia et al., 2015] Gouveia, B. D., Portugal, D., Silva, D. C., and Marques, L. (2015). Computation Sharing in Distributed Robotic Systems: A Case Study on SLAM. IEEE Transactions on Automation Science and Engineering, 12(2):410–422.
  • [Gupta and Conrad, 2019] Gupta, R. U. and Conrad, J. M. (2019). A Survey on Multi-robot Particle Filter SLAM. In 2019 SoutheastCon, pages 1–5.
  • [H. Jacky Chang et al., 2007] H. Jacky Chang, C. S. George Lee, Y. Charlie Hu, and Yung-Hsiang Lu (2007). Multi-robot SLAM with topological/metric maps. In 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 1467–1472.
  • [Hartley and Zisserman, 2003] Hartley, R. and Zisserman, A. (2003). Multiple View Geometry in Computer Vision. Cambridge University Press, USA, second edition.
  • [Howard, 2006] Howard, A. (2006). Multi-robot Simultaneous Localization and Mapping using Particle Filters. The International Journal of Robotics Research, 25(12):1243–1256.
  • [Indelman et al., 2012] Indelman, V., Gurfil, P., Rivlin, E., and Rotstein, H. (2012). Graph-based distributed cooperative navigation for a general multi-robot measurement model. The International Journal of Robotics Research, 31(9):1057–1080.
  • [Indelman et al., 2014] Indelman, V., Nelson, E., Michael, N., and Dellaert, F. (2014). Multi-robot pose graph localization and data association from unknown initial relative poses via expectation maximization. In 2014 IEEE International Conference on Robotics and Automation (ICRA), pages 593–600.
  • [Jennings et al., 1999] Jennings, C., Murray, D., and Little, J. J. (1999). Cooperative robot localization with vision-based mapping. In Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C), volume 4, pages 2659–2665 vol.4.
  • [Jiménez et al., 2018] Jiménez, A. C., García-Díaz, V., González-Crespo, R., and Bolaños, S. (2018). Decentralized Online Simultaneous Localization and Mapping for Multi-Agent Systems. Sensors, 18(8):2612.
  • [Karrer and Chli, 2018] Karrer, M. and Chli, M. (2018). Towards Globally Consistent Visual-Inertial Collaborative SLAM. In 2018 IEEE International Conference on Robotics and Automation (ICRA), pages 3685–3692.
  • [Karrer et al., 2018] Karrer, M., Schmuck, P., and Chli, M. (2018). CVI-SLAM—Collaborative Visual-Inertial SLAM. IEEE Robotics and Automation Letters, 3(4):2762–2769.
  • [Käslin et al., 2016] Käslin, R., Fankhauser, P., Stumm, E., Taylor, Z., Mueggler, E., Delmerico, J., Scaramuzza, D., Siegwart, R., and Hutter, M. (2016). Collaborative localization of aerial and ground robots through elevation maps. In 2016 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), pages 284–290.
  • [Kegeleirs et al., 2021] Kegeleirs, M., Grisetti, G., and Birattari, M. (2021). Swarm SLAM: Challenges and Perspectives. Frontiers in Robotics and AI, 8.
  • [Kepler and Stilwell, 2020] Kepler, M. and Stilwell, D. (2020). An Approach to Reduce Communication for Multi-Agent Mapping Applications. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
  • [Kim et al., 2010] Kim, B., Kaess, M., Fletcher, L., Leonard, J., Bachrach, A., Roy, N., and Teller, S. (2010). Multiple relative pose graphs for robust cooperative mapping. In 2010 IEEE International Conference on Robotics and Automation, pages 3185–3192.
  • [Knuth and Barooah, 2012] Knuth, J. and Barooah, P. (2012). Collaborative 3D localization of robots from relative pose measurements using gradient descent on manifolds. In 2012 IEEE International Conference on Robotics and Automation, pages 1101–1106.
  • [Knuth and Barooah, 2013] Knuth, J. and Barooah, P. (2013). Collaborative localization with heterogeneous inter-robot measurements by Riemannian optimization. In 2013 IEEE International Conference on Robotics and Automation, pages 1534–1539.
  • [Koch and Lacroix, 2016] Koch, P. and Lacroix, S. (2016). Managing environment models in multi-robot teams. In 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 5722–5728.
  • [Kontitsis et al., 2013] Kontitsis, M., Theodorou, E. A., and Todorov, E. (2013). Multi-robot active SLAM with relative entropy optimization. In 2013 American Control Conference, pages 2757–2764.
  • [Kshirsagar et al., 2018] Kshirsagar, J., Shue, S., and Conrad, J. M. (2018). A Survey of Implementation of Multi-Robot Simultaneous Localization and Mapping. In SoutheastCon 2018, pages 1–7.
  • [Kümmerle et al., 2011] Kümmerle, R., Grisetti, G., Strasdat, H., Konolige, K., and Burgard, W. (2011). G2o: A general framework for graph optimization. In 2011 IEEE International Conference on Robotics and Automation, pages 3607–3613.
  • [Lajoie et al., 2019] Lajoie, P.-Y., Hu, S., Beltrame, G., and Carlone, L. (2019). Modeling Perceptual Aliasing in SLAM via Discrete–Continuous Graphical Models. IEEE Robotics and Automation Letters, 4(2):1232–1239.
  • [Lajoie et al., 2020] Lajoie, P.-Y., Ramtoula, B., Chang, Y., Carlone, L., and Beltrame, G. (2020). DOOR-SLAM: Distributed, Online, and Outlier Resilient SLAM for Robotic Teams. IEEE Robotics and Automation Letters, 5(2):1656–1663.
  • [Latif et al., 2013] Latif, Y., Cadena, C., and Neira, J. (2013). Robust loop closing over time for pose graph SLAM. The International Journal of Robotics Research, 32(14):1611–1626.
  • [Lázaro et al., 2013] Lázaro, M. T., Paz, L. M., Piniés, P., Castellanos, J. A., and Grisetti, G. (2013). Multi-robot SLAM using condensed measurements. In 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 1069–1076.
  • [Lee et al., 2012] Lee, H., Seung-Hwan Lee, Tae-Seok Lee, Doo-Jin Kim, and Lee, B. (2012). A survey of map merging techniques for cooperative-SLAM. In 2012 9th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), pages 285–287.
  • [Lee and Lee, 2009] Lee, H. S. and Lee, K. M. (2009). Multi-robot SLAM using ceiling vision. In 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 912–917.
  • [Lee et al., 2020] Lee, S., Kim, H., and Lee, B. (2020). An Efficient Rescue System with Online Multi-Agent SLAM Framework. Sensors, 20(1):235.
  • [Leung et al., 2011a] Leung, K. Y., Halpern, Y., Barfoot, T. D., and Liu, H. H. (2011a). The UTIAS multi-robot cooperative localization and mapping dataset. The International Journal of Robotics Research, 30(8):969–974.
  • [Leung, 2012] Leung, K. Y. K. (2012). Cooperative Localization and Mapping in Sparsely-Communicating Robot Networks. Ph.D. dissertation, University of Toronto, Toronto, Ontario, Canada.
  • [Leung et al., 2011b] Leung, K. Y. K., Barfoot, T. D., and Liu, H. H. T. (2011b). Distributed and decentralized cooperative simultaneous localization and mapping for dynamic and sparse robot networks. In 2011 IEEE International Conference on Robotics and Automation, pages 3841–3847.
  • [Leung et al., 2012] Leung, K. Y. K., Barfoot, T. D., and Liu, H. H. T. (2012). Decentralized Cooperative SLAM for Sparsely-Communicating Robot Networks: A Centralized-Equivalent Approach. Journal of Intelligent & Robotic Systems, 66(3):321–342.
  • [Li et al., 2018] Li, F., Yang, S., Yi, X., and Yang, X. (2018). CORB-SLAM: A Collaborative Visual SLAM System for Multiple Robots. In Romdhani, I., Shu, L., Takahiro, H., Zhou, Z., Gordon, T., and Zeng, D., editors, Collaborative Computing: Networking, Applications and Worksharing, Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, pages 480–490, Cham. Springer International Publishing.
  • [Liu et al., 2020] Liu, R., Marakkalage, S. H., Padmal, M., Shaganan, T., Yuen, C., Guan, Y. L., and Tan, U. (2020). Collaborative SLAM Based on WiFi Fingerprint Similarity and Motion Information. IEEE Internet of Things Journal, 7(3):1826–1840.
  • [Loianno et al., 2015] Loianno, G., Thomas, J., and Kumar, V. (2015). Cooperative localization and mapping of MAVs using RGB-D sensors. In 2015 IEEE International Conference on Robotics and Automation (ICRA), pages 4021–4028.
  • [Lowry et al., 2016] Lowry, S., Sünderhauf, N., Newman, P., Leonard, J. J., Cox, D., Corke, P., and Milford, M. J. (2016). Visual Place Recognition: A Survey. IEEE Transactions on Robotics, 32(1):1–19.
  • [Luft et al., 2016] Luft, L., Schubert, T., I. Roumeliotis, S., and Burgard, W. (2016). Recursive Decentralized Collaborative Localization for Sparsely Communicating Robots. In Robotics: Science and Systems XII. Robotics: Science and Systems Foundation.
  • [Madhavan et al., 2004] Madhavan, R., Fregene, K., and Parker, L. E. (2004). Distributed Cooperative Outdoor Multirobot Localization and Mapping. Autonomous Robots, 17(1):23–39.
  • [Mahdoui et al., 2020] Mahdoui, N., Frémont, V., and Natalizio, E. (2020). Communicating Multi-UAV System for Cooperative SLAM-based Exploration. Journal of Intelligent & Robotic Systems, 98(2):325–343.
  • [Mangelson et al., 2018] Mangelson, J. G., Dominic, D., Eustice, R. M., and Vasudevan, R. (2018). Pairwise Consistent Measurement Set Maximization for Robust Multi-Robot Map Merging. In 2018 IEEE International Conference on Robotics and Automation (ICRA), pages 2916–2923.
  • [Martin and Emami, 2010] Martin, A. and Emami, M. R. (2010). Just-in-time cooperative simultaneous localization and mapping. In 2010 11th International Conference on Control Automation Robotics Vision, pages 479–484.
  • [Martinez et al., 2020] Martinez, J., Doubov, S., Fan, J., and Bã, I. A. (2020). Pit30M: A Benchmark for Global Localization in the Age of Self-Driving Cars. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), page 8.
  • [Mohamed et al., 2019] Mohamed, S. A. S., Haghbayan, M., Westerlund, T., Heikkonen, J., Tenhunen, H., and Plosila, J. (2019). A Survey on Odometry for Autonomous Navigation Systems. IEEE Access, 7:97466–97486.
  • [Montijano et al., 2013] Montijano, E., Aragues, R., and Sagüés, C. (2013). Distributed Data Association in Robotic Networks With Cameras and Limited Communications. IEEE Transactions on Robotics, 29(6):1408–1423.
  • [Morales and Kassas, 2018] Morales, J. and Kassas, Z. M. (2018). Information fusion strategies for collaborative radio SLAM. In 2018 IEEE/ION Position, Location and Navigation Symposium (PLANS), pages 1445–1454.
  • [Moratuwage et al., 2013] Moratuwage, D., Vo, B., and Wang, D. (2013). Collaborative Multi-vehicle SLAM with moving object tracking. In 2013 IEEE International Conference on Robotics and Automation, pages 5702–5708.
  • [Moratuwage et al., 2014] Moratuwage, D., Wang, D., Rao, A., Senarathne, N., and Wang, H. (2014). RFS Collaborative Multivehicle SLAM: SLAM in Dynamic High-Clutter Environments. IEEE Robotics Automation Magazine, 21(2):53–59.
  • [Morrison et al., 2016] Morrison, J. G., Gálvez-López, D., and Sibley, G. (2016). MOARSLAM: Multiple Operator Augmented RSLAM. Distributed Autonomous Robotic Systems, pages 119–132.
  • [Mur-Artal and Tardós, 2017] Mur-Artal, R. and Tardós, J. D. (2017).

    ORB-SLAM2: an open-source SLAM system for monocular, stereo and RGB-D cameras.

    IEEE Transactions on Robotics, 33(5):1255–1262.
  • [Nerurkar et al., 2009] Nerurkar, E. D., Roumeliotis, S. I., and Martinelli, A. (2009).

    Distributed maximum a posteriori estimation for multi-robot cooperative localization.

    In 2009 IEEE International Conference on Robotics and Automation, pages 1402–1409.
  • [Nettleton et al., 2006] Nettleton, E., Thrun, S., Durrant-Whyte, H., and Sukkarieh, S. (2006). Decentralised SLAM with Low-Bandwidth Communication for Teams of Vehicles. In Yuta, S., Asama, H., Prassler, E., Tsubouchi, T., and Thrun, S., editors, Field and Service Robotics: Recent Advances in Reserch and Applications, Springer Tracts in Advanced Robotics, pages 179–188. Springer, Berlin, Heidelberg.
  • [Opdenbosch and Steinbach, 2019] Opdenbosch, D. V. and Steinbach, E. (2019). Collaborative Visual SLAM Using Compressed Feature Exchange. IEEE Robotics and Automation Letters, 4(1):57–64.
  • [Özyeşil et al., 2017] Özyeşil, O., Voroninski, V., Basri, R., and Singer, A. (2017). A survey of structure from motion. Acta Numerica, 26:305–364.
  • [Paull et al., 2015] Paull, L., Huang, G., Seto, M., and Leonard, J. J. (2015). Communication-constrained multi-AUV cooperative SLAM. In 2015 IEEE International Conference on Robotics and Automation (ICRA), pages 509–516.
  • [Paull et al., 2014] Paull, L., Seto, M., and Leonard, J. J. (2014). Decentralized cooperative trajectory estimation for autonomous underwater vehicles. In 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 184–191.
  • [Pei et al., 2020] Pei, Z., Piao, S., Quan, M., Qadir, M. Z., and Li, G. (2020). Active collaboration in relative observation for multi-agent visual simultaneous localization and mapping based on Deep Q Network. International Journal of Advanced Robotic Systems, 17(2):1729881420920216.
  • [Pfingsthorn et al., 2008] Pfingsthorn, M., Slamet, B., and Visser, A. (2008). A Scalable Hybrid Multi-robot SLAM Method for Highly Detailed Maps. In Visser, U., Ribeiro, F., Ohashi, T., and Dellaert, F., editors, RoboCup 2007: Robot Soccer World Cup XI, Lecture Notes in Computer Science, pages 457–464, Berlin, Heidelberg. Springer.
  • [Queralta et al., 2020] Queralta, J. P., Taipalmaa, J., Pullinen, B. C., Sarker, V. K., Gia, T. N., Tenhunen, H., Gabbouj, M., Raitoharju, J., and Westerlund, T. (2020). Collaborative Multi-Robot Search and Rescue: Planning, Coordination, Perception, and Active Vision. IEEE Access, 8:191617–191643.
  • [Quraishi et al., 2016] Quraishi, A., Cieslewski, T., Lynen, S., and Siegwart, R. (2016). Robustness to connectivity loss for collaborative mapping. In 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 4580–4585.
  • [Ramtoula et al., 2020] Ramtoula, B., de Azambuja, R., and Beltrame, G. (2020). CAPRICORN: Communication Aware Place Recognition using Interpretable Constellations of Objects in Robot Networks. In 2020 IEEE International Conference on Robotics and Automation (ICRA), pages 8761–8768.
  • [Rekleitis et al., 2003] Rekleitis, I., Dudek, G., and Milios, E. (2003). Probabilistic cooperative localization and mapping in practice. In 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422), volume 2, pages 1907–1912 vol.2.
  • [Riazuelo et al., 2014] Riazuelo, L., Civera, J., and Montiel, J. M. M. (2014). C2TAM: A Cloud framework for cooperative tracking and mapping. Robotics and Autonomous Systems, 62(4):401–413.
  • [Rioux et al., 2015] Rioux, A., Esteves, C., Hayet, J., and Suleiman, W. (2015). Cooperative SLAM-based object transportation by two humanoid robots in a cluttered environment. In 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids), pages 331–337.
  • [Rone and Ben-Tzvi, 2013] Rone, W. and Ben-Tzvi, P. (2013). Mapping, localization and motion planning in mobile multi-robotic systems. Robotica, 31(1):1–23.
  • [Rosen et al., 2019] Rosen, D. M., Carlone, L., Bandeira, A. S., and Leonard, J. J. (2019). SE-Sync: A certifiably correct algorithm for synchronization over the special Euclidean group. The International Journal of Robotics Research, 38(2-3):95–125.
  • [Rosen et al., 2021] Rosen, D. M., Doherty, K. J., Espinoza, A. T., and Leonard, J. J. (2021). Advances in Inference and Representation for Simultaneous Localization and Mapping. arXiv:2103.05041 [cs].
  • [Saeedi et al., 2011a] Saeedi, S., Paull, L., Trentini, M., and Li, H. (2011a). Multiple robot simultaneous localization and mapping. In 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 853–858.
  • [Saeedi et al., 2011b] Saeedi, S., Paull, L., Trentini, M., and Li, H. (2011b). Neural Network-Based Multiple Robot Simultaneous Localization and Mapping. IEEE Transactions on Neural Networks, 22(12):2376–2387.
  • [Saeedi et al., 2015] Saeedi, S., Paull, L., Trentini, M., and Li, H. (2015). Occupancy grid map merging for multiple robot simultaneous localization and mapping. International Journal of Robotics and Automation 2015, 30(6).
  • [Saeedi et al., 2014] Saeedi, S., Paull, L., Trentini, M., Seto, M., and Li, H. (2014). Group Mapping: A Topological Approach to Map Merging for Multiple Robots. IEEE Robotics Automation Magazine, 21(2):60–72.
  • [Saeedi et al., 2016] Saeedi, S., Trentini, M., Seto, M., and Li, H. (2016). Multiple-Robot Simultaneous Localization and Mapping: A Review. Journal of Field Robotics, 33(1):3–46.
  • [Sartipi et al., 2019] Sartipi, K., DuToit, R. C., Cobar, C. B., and Roumeliotis, S. I. (2019). Decentralized Visual-Inertial Localization and Mapping on Mobile Devices for Augmented Reality. In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 2145–2152.
  • [Sasaoka et al., 2016] Sasaoka, T., Kimoto, I., Kishimoto, Y., Takaba, K., and Nakashima, H. (2016). Multi-robot SLAM via Information Fusion Extended Kalman Filters. IFAC-PapersOnLine, 49(22):303–308.
  • [Satyanarayanan, 2017] Satyanarayanan, M. (2017). The Emergence of Edge Computing. Computer, 50(1):30–39.
  • [Schmuck and Chli, 2017] Schmuck, P. and Chli, M. (2017). Multi-UAV collaborative monocular SLAM. In 2017 IEEE International Conference on Robotics and Automation (ICRA), pages 3863–3870.
  • [Schmuck and Chli, 2019] Schmuck, P. and Chli, M. (2019). CCM-SLAM: Robust and efficient centralized collaborative monocular simultaneous localization and mapping for robotic teams. Journal of Field Robotics, 36(4):763–781.
  • [Schulz et al., 2019] Schulz, C., Hanten, R., Reisenauer, M., and Zell, A. (2019). Simultaneous Collaborative Mapping Based on Low-Bandwidth Communication. In 2019 Third IEEE International Conference on Robotic Computing (IRC), pages 413–414.
  • [Schuster et al., 2015] Schuster, M. J., Brand, C., Hirschmüller, H., Suppa, M., and Beetz, M. (2015). Multi-robot 6D graph SLAM connecting decoupled local reference filters. In 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 5093–5100.
  • [Schuster et al., 2019] Schuster, M. J., Schmid, K., Brand, C., and Beetz, M. (2019). Distributed stereo vision-based 6D localization and mapping for multi-robot teams. Journal of Field Robotics, 36(2):305–332.
  • [Sidaoui et al., 2019] Sidaoui, A., Elhajj, I. H., and Asmar, D. (2019). Collaborative Human Augmented SLAM. In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 2131–2138.
  • [Simmons et al., 2000] Simmons, R. G., Apfelbaum, D., Burgard, W., Fox, D., Moors, M., Thrun, S., and Younes, H. L. S. (2000). Coordination for Multi-Robot Exploration and Mapping. In Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence, pages 852–858. AAAI Press.
  • [Strasdat et al., 2012] Strasdat, H., Montiel, J. M. M., and Davison, A. (2012). Visual SLAM: Why filter? Image Vis. Comput.
  • [Sünderhauf and Protzel, 2012] Sünderhauf, N. and Protzel, P. (2012). Switchable constraints for robust pose graph SLAM. In 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 1879–1884.
  • [Tardioli et al., 2015] Tardioli, D., Montijano, E., and Mosteo, A. R. (2015). Visual data association in narrow-bandwidth networks. In 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 2572–2577.
  • [Tchuiev and Indelman, 2020] Tchuiev, V. and Indelman, V. (2020). Distributed Consistent Multi-Robot Semantic Localization and Mapping. IEEE Robotics and Automation Letters, 5(3):4649–4656.
  • [Thrun, 2001] Thrun, S. (2001). A Probabilistic On-Line Mapping Algorithm for Teams of Mobile Robots. The International Journal of Robotics Research, 20(5):335–363.
  • [Thrun et al., 2005] Thrun, S., Burgard, W., and Fox, D. (2005). Probabilistic Robotic — The MIT Press. The MIT Press.
  • [Thrun and Liu, 2005] Thrun, S. and Liu, Y. (2005). Multi-robot SLAM with Sparse Extended Information Filers. In Dario, P. and Chatila, R., editors, Robotics Research. The Eleventh International Symposium, Springer Tracts in Advanced Robotics, pages 254–266, Berlin, Heidelberg. Springer.
  • [Tian et al., 2018a] Tian, Y., Khosoussi, K., Giamou, M., How, J., and Kelly, J. (2018a). Near-Optimal Budgeted Data Exchange for Distributed Loop Closure Detection. In Robotics: Science and Systems XIV. Robotics: Science and Systems Foundation.
  • [Tian et al., 2018b] Tian, Y., Khosoussi, K., and How, J. P. (2018b). Resource-Aware Algorithms for Distributed Loop Closure Detection with Provable Performance Guarantees. In Algorithmic Foundations of Robotics XIII, pages 422–438. Springer, Cham.
  • [Tian et al., 2020a] Tian, Y., Khosoussi, K., and How, J. P. (2020a). A resource-aware approach to collaborative loop-closure detection with provable performance guarantees. The International Journal of Robotics Research, page 0278364920948594.
  • [Tian et al., 2021] Tian, Y., Khosoussi, K., Rosen, D. M., and How, J. P. (2021). Distributed Certifiably Correct Pose-Graph Optimization. IEEE Transactions on Robotics, pages 1–20.
  • [Tian et al., 2020b] Tian, Y., Koppel, A., Bedi, A. S., and How, J. P. (2020b). Asynchronous and Parallel Distributed Pose Graph Optimization. IEEE Robotics and Automation Letters, 5(4):5819–5826.
  • [Tian et al., 2020c] Tian, Y., Liu, K., Ok, K., Tran, L., Allen, D., Roy, N., and How, J. P. (2020c). Search and rescue under the forest canopy using multiple UAVs. The International Journal of Robotics Research, 39(10-11):1201–1221.
  • [Tron et al., 2016] Tron, R., Thomas, J., Loianno, G., Daniilidis, K., and Kumar, V. (2016). A Distributed Optimization Framework for Localization and Formation Control: Applications to Vision-Based Measurements. IEEE Control Systems Magazine, 36(4):22–44.
  • [Tron and Vidal, 2009] Tron, R. and Vidal, R. (2009). Distributed image-based 3-D localization of camera sensor networks. In Proceedings of the 48h IEEE Conference on Decision and Control (CDC) Held Jointly with 2009 28th Chinese Control Conference, pages 901–908.
  • [Tron and Vidal, 2014] Tron, R. and Vidal, R. (2014). Distributed 3-D Localization of Camera Sensor Networks From 2-D Image Measurements. IEEE Transactions on Automatic Control, 59(12):3325–3340.
  • [Trujillo et al., 2018] Trujillo, J.-C., Munguia, R., Guerra, E., and Grau, A. (2018). Cooperative Monocular-Based SLAM for Multi-UAV Systems in GPS-Denied Environments. Sensors (Basel, Switzerland), 18(5).
  • [Tuna et al., 2015] Tuna, G., Güngör, V. Ç., and Potirakis, S. M. (2015). Wireless sensor network-based communication for cooperative simultaneous localization and mapping. Computers & Electrical Engineering, 41:407–425.
  • [Uy and Lee, 2018] Uy, M. A. and Lee, G. H. (2018). Pointnetvlad: Deep point cloud based retrieval for large-scale place recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4470–4479.
  • [Vitug, 2021] Vitug, E. (2021). Cooperative Autonomous Distributed Robotic Exploration (CADRE). http://www.nasa.gov/directorates/spacetech/game_changing_development/projects/CADRE.
  • [Wang et al., 2019] Wang, W., Jadhav, N., Vohs, P., Hughes, N., Mazumder, M., and Gil, S. (2019). Active Rendezvous for Multi-Robot Pose Graph Optimization using Sensing over Wi-Fi. In International Symposium on Robotics Research (ISRR), Hanoi.
  • [Waniek et al., 2015] Waniek, N., Biedermann, J., and Conradt, J. (2015). Cooperative SLAM on small mobile robots. In 2015 IEEE International Conference on Robotics and Biomimetics (ROBIO), pages 1810–1815.
  • [Williams et al., 2002] Williams, S. B., Dissanayake, G., and Durrant-Whyte, H. (2002). Towards multi-vehicle simultaneous localisation and mapping. In Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292), volume 3, pages 2743–2748 vol.3.
  • [Wu et al., 2009] Wu, M., Huang, F., Wang, L., and Sun, J. (2009). Cooperative Multi-Robot Monocular-SLAM Using Salient Landmarks. In 2009 International Asia Conference on Informatics in Control, Automation and Robotics, pages 151–155.
  • [Xie et al., 2016] Xie, J., Kiefel, M., Sun, M., and Geiger, A. (2016). Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 3688–3697.
  • [Yu et al., 2020] Yu, K., Ahn, J., Lee, J., Kim, M., and Han, J. (2020). Collaborative SLAM and AR-guided navigation for floor layout inspection. The Visual Computer, 36(10):2051–2063.
  • [Yun et al., 2017] Yun, P., Jiao, J., and Liu, M. (2017). Towards a Cloud Robotics Platform for Distributed Visual SLAM. In Liu, M., Chen, H., and Vincze, M., editors, Computer Vision Systems, Lecture Notes in Computer Science, pages 3–15, Cham. Springer International Publishing.
  • [Zhang et al., 2018a] Zhang, H., Chen, X., Lu, H., and Xiao, J. (2018a). Distributed and collaborative monocular simultaneous localization and mapping for multi-robot systems in large-scale environments. International Journal of Advanced Robotic Systems, 15(3):1729881418780178.
  • [Zhang et al., 2018b] Zhang, P., Wang, H., Ding, B., and Shang, S. (2018b). Cloud-Based Framework for Scalable and Real-Time Multi-Robot SLAM. In 2018 IEEE International Conference on Web Services (ICWS), pages 147–154.
  • [Zhou and Roumeliotis, 2006] Zhou, X. S. and Roumeliotis, S. I. (2006). Multi-robot SLAM with Unknown Initial Correspondence: The Robot Rendezvous Case. In 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 1785–1792.
  • [Zou and Tan, 2013] Zou, D. and Tan, P. (2013). CoSLAM: Collaborative Visual SLAM in Dynamic Environments. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(2):354–366.
  • [Zou et al., 2019] Zou, D., Tan, P., and Yu, W. (2019). Collaborative visual SLAM for multiple agents: A brief survey. Virtual Real. Intell. Hardw.