AnyBody: A Benchmark Suite for Cross-Embodiment Manipulation

TL;DR

This paper introduces a standardized benchmark suite for evaluating the ability of reinforcement learning policies to generalize manipulation skills across different robot morphologies, addressing a key challenge in scalable robotics learning.

Contribution

It provides a systematic benchmark for cross-embodiment manipulation tasks, enabling consistent evaluation of policy generalization across diverse robot morphologies.

Findings

Morphology-aware training can outperform single-embodiment baselines.

Zero-shot generalization to unseen morphologies is challenging but possible.

Architectural and training choices significantly impact generalization performance.

Abstract

Generalizing control policies to novel embodiments remains a fundamental challenge in enabling scalable and transferable learning in robotics. While prior works have explored this in locomotion, a systematic study in the context of manipulation tasks remains limited, partly due to the lack of standardized benchmarks. In this paper, we introduce a benchmark for learning cross-embodiment manipulation, focusing on two foundational tasks-reach and push-across a diverse range of morphologies. The benchmark is designed to test generalization along three axes: interpolation (testing performance within a robot category that shares the same link structure), extrapolation (testing on a robot with a different link structure), and composition (testing on combinations of link structures). On the benchmark, we evaluate the ability of different RL policies to learn from multiple morphologies and to generalize to novel ones. Our study aims to answer whether morphology-aware training can outperform single-embodiment baselines, whether zero-shot generalization to unseen morphologies is feasible, and how consistently these patterns hold across different generalization regimes. The results highlight the current limitations of multi-embodiment learning and provide insights into how architectural and training design choices influence policy generalization.