3D object-level mapping is a fundamental problem in robotics, which is
e...
6D pose estimation of textureless shiny objects has become an essential
...
Simultaneous localization and mapping (SLAM) in slowly varying scenes is...
3D object reconstruction is important for semantic scene understanding. ...
Accurate 3D object detection in all weather conditions remains a key
cha...
Current LiDAR-based 3D object detectors for autonomous driving are almos...
In this work, we present a novel target-based lidar-camera extrinsic
cal...
Robotic eye-in-hand calibration is the task of determining the rigid 6-D...
An effective framework for learning 3D representations for perception ta...
Estimating the uncertainty in deep neural network predictions is crucial...
6D pose estimation of textureless objects is a valuable but challenging ...
3D multi-object tracking (MOT) is a key problem for autonomous vehicles,...
Maintaining an up-to-date map to reflect recent changes in the scene is ...
LiDAR has become one of the primary 3D object detection sensors in auton...
Camera and LiDAR sensor modalities provide complementary appearance and
...
Depth acquisition with the active stereo camera is a challenging task fo...
Autonomous driving datasets are often skewed and in particular, lack tra...
Model-based control methods for robotic systems such as quadrotors,
auto...
In robotic bin-picking applications, the perception of texture-less, hig...
The reliable fusion of depth maps from multiple viewpoints has become an...
Monocular 3D object detection is a key problem for autonomous vehicles, ...
Successful visual navigation depends upon capturing images that contain
...
Predictive uncertainty estimation is an essential next step for the reli...
Most mobile robots follow a modular sense-planact system architecture th...
Accurate and reliable 3D object detection is vital to safe autonomous
dr...
We define a new problem called the Vehicle Scheduling Problem (VSP). The...
Unmanned aerial vehicles (UAVs) have increasingly been adopted for safet...
Safe autonomous driving requires reliable 3D object detection-determinin...
In this work, we introduce a microscopic traffic flow model called Scala...
Accurately estimating the orientation of pedestrians is an important and...
The University of Toronto is one of eight teams competing in the SAE
Aut...
We present MonoPSR, a monocular 3D object detection method that leverage...
One of the challenging aspects of incorporating deep neural networks int...
In order to facilitate long-term localization using a visual simultaneou...
Automatic mapping of buildings from remote sensing imagery is currently
...
Dynamic Camera Clusters (DCCs) are multi-camera systems where one or mor...
Training 3D object detectors for autonomous driving has been limited to ...
Traffic light and sign detectors on autonomous cars are integral for roa...
Recurrent Neural Networks (RNNs) can encode rich dynamics which makes th...
Computer vision and robotics problems often require representation and
e...
With the rise of data driven deep neural networks as a realization of
un...
An analysis of the relative motion and point feature model configuration...