Proactivity in robot assistance refers to the robot's ability to anticip...
We present IndoorSim-to-OutdoorReal (I2O), an end-to-end learned visual
...
Proactive robot assistance enables a robot to anticipate and provide for...
Robots operating in human environments must be able to rearrange objects...
Complex, multi-objective missions require the coordination of heterogene...
If we want to train robots in simulation before deploying them in realit...
Learned knowledge graph representations supporting robots contain a weal...
Creative Problem Solving (CPS) is a sub-area within Artificial Intellige...
Intelligent decision support (IDS) systems leverage artificial intellige...
Object grounding tasks aim to locate the target object in an image throu...
When interacting in unstructured human environments, occasional robot
fa...
To realize effective heterogeneous multi-robot teams, researchers must
l...
Multi-robot task allocation (MRTA) problems involve optimizing the alloc...
Smart home environments are designed to provide services that help impro...
Requiring multiple demonstrations of a task plan presents a burden to
en...
In recent years, there has been a resurgence in methods that use distrib...
With the growing capabilities of intelligent systems, the integration of...
Robotic tasks often require generation of motions that satisfy multiple
...
Deep reinforcement learning models are notoriously data hungry, yet
real...
Navigation policies are commonly learned on idealized cylinder agents in...
With the growing capabilities of intelligent systems, the integration of...
We describe a framework for research and evaluation in Embodied AI. Our
...
Robots in the real world should be able to adapt to unforeseen circumsta...
Macgyvering refers to solving problems inventively by using whatever obj...
We address the problem of adapting robot trajectories to improve safety,...
As robot autonomy improves, robots are increasingly being considered in ...
Material recognition can help inform robots about how to properly intera...
Machine learning (ML) systems across many application areas are increasi...
Robot task execution when situated in real-world environments is fragile...
Does progress in simulation translate to progress in robotics? Specifica...
This paper explores the problem of tool substitution, namely, identifyin...
In this work, we contribute a large-scale study benchmarking the perform...
Semantic grasping is the problem of selecting stable grasps that are
fun...
Active learning agents typically employ a query selection algorithm whic...
Prior work has shown that the multi-relational embedding objective can b...
The knowledge base completion problem is the problem of inferring missin...
We propose a learning framework, named Multi-Coordinate Cost Balancing
(...
Large teams of robots have the potential to solve complex multi-task pro...
Autonomous service robots require computational frameworks that allow th...
MacGyvering is defined as creating or repairing something in an inventiv...
Robot perception systems need to perform reliable image segmentation in
...
Learning from Demonstration (LfD) is a popular approach to endowing robo...
Recognizing an object's material can inform a robot on how hard it may g...
This paper explores the problem of task learning and planning, contribut...
As robots become increasingly prevalent in human environments, there wil...
Material recognition enables robots to incorporate knowledge of material...
This paper details the implementation of an algorithm for automatically
...
We present Confidence-Based Autonomy (CBA), an interactive algorithm for...