Related Work
Use the filters below to find what you are interested!
Add my work here!Filters
72 papersAll papers
A model that reconstructs part-level geometry and articulation model of an articulated object given observations before and after an interaction. CVPR 2022, oral.
A scalable door-pening environment in Gym. NeurIPS 2019, Deep RL workshop.
A system that can learn to articulate novel objects with no prior interaction, after training on other articulated objects. CoRL 2023.
A novel method to perceive and manipulate 3D articulated objects that generalizes to enable the robot to articulate unseen classes of objects. RSS 2022.
Learning generalizable object perception and manipulation skills via Generalizable and Actionable Parts. CVPR 2023.
A novel hand-agnostic grasping algorithm for generalizable grasping. ICRA 2023.
A novel method for multi-object grasping on a tabletop with a multi-finger dexterous hand. Preprint, under review.
NeurIPS 2021 (Dataset and Benchmark Track).
SIGGRAPH Asia 2022.
CVPR 2023; RGB-D point cloud.
ICRA 2023; RGB-D point cloud.
SAGCI-System: Towards Sample-Efficient, Generalizable, Compositional, and Incremental Robot Learning
A system for articulated object manipulation via differentiable simulation. ICRA 2022.
RSS 2023. Best System Paper Finalist.
A novel dexterous grasping policy learning pipeline. ICCV 2023.
Learning universal robotic dexterous grasping from a point cloud observation under a table-top setting. CVPR 2023.
A single image-based policy network that infers closed-loop action sequences for manipulating articulated objects. RA-L vol. 7, issue 2, 2022.
A self-supervised zero-shot visual reward and representation for downstream unseen robot tasks. ICLR 2023, spotlight.
Science Robotics 2023.
ICCV 2023; RGB-D point cloud.
ICLR 2023; RGB-D point cloud.
ICCV 2023; RGB-D point cloud.
SIGGRAPHAsia 2023.
ICLR 2022; RGB-D point cloud.