Self-supervised and language-supervised image models contain rich knowledge of the
world that is important for generalization. Many robotic tasks, however, require a detailed …

Legged robots have the potential to expand the reach of autonomy beyond paved roads. In
this work, we consider the difficult problem of locomotion on challenging terrains using a …

Building 3D perception systems for autonomous vehicles that do not rely on high-density
LiDAR is a critical research problem because of the expense of LiDAR systems compared to …

A major bottleneck in training robust Human-Activity Recognition models (HAR) is the need
for large-scale labeled sensor datasets. Because labeling large amounts of sensor data is …

3D perceptual representations are well suited for robot manipulation as they easily encode
occlusions and simplify spatial reasoning. Many manipulation tasks require high spatial …

Taking advantage of multi-view aggregation presents a promising solution to tackle
challenges such as occlusion and missed detection in multi-object tracking and detection …

3D scene representation for robot manipulation should capture three key object properties:
permanency--objects that become occluded over time continue to exist; amodal …

Abstract We present Video Autoencoder for learning disentangled representations of 3D
structure and camera pose from videos in a self-supervised manner. Relying on temporal …

Multi-camera perception tasks have gained significant attention in the field of autonomous
driving. However, existing frameworks based on Lift-Splat-Shoot (LSS) in the multi-camera …

We present a novel Relightable Neural Renderer (RNR) for simultaneous view synthesis
and relighting using multi-view image inputs. Existing neural rendering (NR) does not …