Score: 0

Multi-Group Equivariant Augmentation for Reinforcement Learning in Robot Manipulation

Published: August 15, 2025 | arXiv ID: 2508.11204v1

By: Hongbin Lin, Juan Rojas, Kwok Wai Samuel Au

Potential Business Impact:

Teaches robots to learn tasks faster.

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.

Page Count
16 pages

Category
Computer Science:
Robotics