activity
20242026
collaborators

5 papers

cs.RO2026

Geometry-Aware Motion Latents for Learning Robust Manipulation Policies

Yunchao Zhang, Yijia Weng, Ruizhe Liu +3

Learning motion latents for robotic manipulation heavily relies on extracting motion patterns from visual sequences, yet effective action abstractions require understanding three-d…

cs.RO2025

Robot Learning from Any Images

Siheng Zhao, Jiageng Mao, Wei Chow +11

We introduce RoLA, a framework that transforms any in-the-wild image into an interactive, physics-enabled robotic environment. Unlike previous methods, RoLA operates directly on a…

cs.RO2025

AO-Grasp: Articulated Object Grasp Generation

Carlota Parés Morlans, Claire Chen, Yijia Weng +6

We introduce AO-Grasp, a grasp proposal method that generates 6 DoF grasps that enable robots to interact with articulated objects, such as opening and closing cabinets and applian…

cs.CV2024

Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objects

Yijia Weng, Bowen Wen, Jonathan Tremblay +4

We address the problem of building digital twins of unknown articulated objects from two RGBD scans of the object at different articulation states. We decompose the problem into tw…

cs.RO2024

EquivAct: SIM(3)-Equivariant Visuomotor Policies beyond Rigid Object Manipulation

Jingyun Yang, Congyue Deng, Jimmy Wu +3

If a robot masters folding a kitchen towel, we would expect it to master folding a large beach towel. However, existing policy learning methods that rely on data augmentation still…