activity
20172026
most citedEfficient Hierarchical Graph-Based Segmentation of RGBD Videos

52 citations · 163 across the 20 of their papers we have counts for

collaborators
Showing 2020Show all

10 papers · 1 filter

cs.RO202013 cited

Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs

Yifeng Zhu, Jonathan Tremblay, Stan Birchfield +1

We present a visually grounded hierarchical planning algorithm for long-horizon manipulation tasks. Our algorithm offers a joint framework of neuro-symbolic task planning and low-l…

cs.CV20207 cited

Displacement-Invariant Cost Computation for Efficient Stereo Matching

Yiran Zhong, Charles Loop, Wonmin Byeon +7

Although deep learning-based methods have dominated stereo matching leaderboards by yielding unprecedented disparity accuracy, their inference time is typically slow, on the order…

cs.CV2020

Self-Supervised Real-to-Sim Scene Generation

Aayush Prakash, Shoubhik Debnath, Jean-Francois Lafleche +4

Synthetic data is emerging as a promising solution to the scalability issue of supervised deep learning, especially when real data are difficult to acquire or hard to annotate. Syn…

cs.RO20202 cited

Fast Uncertainty Quantification for Deep Object Pose Estimation

Guanya Shi, Yifeng Zhu, Jonathan Tremblay +4

Deep learning-based object pose estimators are often unreliable and overconfident especially when the input image is outside the training domain, for instance, with sim2real transf…

cs.RO2020

Joint Space Control via Deep Reinforcement Learning

Visak Kumar, David Hoeller, Balakumar Sundaralingam +2

The dominant way to control a robot manipulator uses hand-crafted differential equations leveraging some form of inverse kinematics / dynamics. We propose a simple, versatile joint…

cs.RO2020

Indirect Object-to-Robot Pose Estimation from an External Monocular RGB Camera

Jonathan Tremblay, Stephen Tyree, Terry Mosier +1

We present a robotic grasping system that uses a single external monocular RGB camera as input. The object-to-robot pose is computed indirectly by combining the output of two neura…