English

Multi-Group Equivariant Augmentation for Reinforcement Learning in Robot Manipulation

Robotics 2025-08-18 v1 Artificial Intelligence

Abstract

Sampling efficiency is critical for deploying visuomotor learning in real-world robotic manipulation. While task symmetry has emerged as a promising inductive bias to improve efficiency, most prior work is limited to isometric symmetries -- applying the same group transformation to all task objects across all timesteps. In this work, we explore non-isometric symmetries, applying multiple independent group transformations across spatial and temporal dimensions to relax these constraints. We introduce a novel formulation of the partially observable Markov decision process (POMDP) that incorporates the non-isometric symmetry structures, and propose a simple yet effective data augmentation method, Multi-Group Equivariance Augmentation (MEA). We integrate MEA with offline reinforcement learning to enhance sampling efficiency, and introduce a voxel-based visual representation that preserves translational equivariance. Extensive simulation and real-robot experiments across two manipulation domains demonstrate the effectiveness of our approach.

Keywords

Cite

@article{arxiv.2508.11204,
  title  = {Multi-Group Equivariant Augmentation for Reinforcement Learning in Robot Manipulation},
  author = {Hongbin Lin and Juan Rojas and Kwok Wai Samuel Au},
  journal= {arXiv preprint arXiv:2508.11204},
  year   = {2025}
}
R2 v1 2026-07-01T04:51:04.861Z