collaborators

7 papers

cs.RO2025

Residual Rotation Correction using Tactile Equivariance

Yizhe Zhu, Zhang Ye, Boce Hu +4

Visuotactile policy learning augments vision-only policies with tactile input, facilitating contact-rich manipulation. However, the high cost of tactile data collection makes sampl…

cs.RO2025

Generalizable Hierarchical Skill Learning via Object-Centric Representation

Haibo Zhao, Yu Qi, Boce Hu +9

We present Generalizable Hierarchical Skill Learning (GSL), a novel framework for hierarchical policy learning that significantly improves policy generalization and sample efficien…

cs.RO2025

Robot Tactile Gesture Recognition Based on Full-body Modular E-skin

Shuo Jiang, Boce Hu, Linfeng Zhao +1

With the development of robot electronic skin technology, various tactile sensors, enhanced by AI, are unlocking a new dimension of perception for robots. In this work, we explore…

cs.RO2025

3D Equivariant Visuomotor Policy Learning via Spherical Projection

Boce Hu, Dian Wang, David Klee +5

Equivariant models have recently been shown to improve the data efficiency of diffusion policy by a significant margin. However, prior work that explored this direction focused pri…

cs.RO2025

A Practical Guide for Incorporating Symmetry in Diffusion Policy

Dian Wang, Boce Hu, Shuran Song +2

Recently, equivariant neural networks for policy learning have shown promising improvements in sample efficiency and generalization, however, their wide adoption faces substantial…

cs.RO2025

Push-Grasp Policy Learning Using Equivariant Models and Grasp Score Optimization

Boce Hu, Heng Tian, Dian Wang +4

Goal-conditioned robotic grasping in cluttered environments remains a challenging problem due to occlusions caused by surrounding objects, which prevent direct access to the target…