RoboMoRe: LLM-based Robot Co-design via Joint Optimization of Morphology and Reward

TL;DR

RoboMoRe introduces an LLM-driven framework for joint optimization of robot morphology and reward functions, enabling more diverse and effective robot designs without task-specific templates, outperforming existing methods.

Contribution

The paper presents RoboMoRe, a novel LLM-based approach that integrates morphology and reward shaping for co-optimization in robot design, addressing limitations of fixed reward functions.

Findings

Outperforms human-engineered designs across eight tasks.

Effectively explores diverse morphology-reward pairs.

Does not require task-specific prompts or predefined templates.

Abstract

Robot co-design, jointly optimizing morphology and control policy, remains a longstanding challenge in the robotics community, where many promising robots have been developed. However, a key limitation lies in its tendency to converge to sub-optimal designs due to the use of fixed reward functions, which fail to explore the diverse motion modes suitable for different morphologies. Here we propose RoboMoRe, a large language model (LLM)-driven framework that integrates morphology and reward shaping for co-optimization within the robot co-design loop. RoboMoRe performs a dual-stage optimization: in the coarse optimization stage, an LLM-based diversity reflection mechanism generates both diverse and high-quality morphology-reward pairs and efficiently explores their distribution. In the fine optimization stage, top candidates are iteratively refined through alternating LLM-guided reward and morphology gradient updates. RoboMoRe can optimize both efficient robot morphologies and their suited motion behaviors through reward shaping. Results demonstrate that without any task-specific prompting or predefined reward/morphology templates, RoboMoRe significantly outperforms human-engineered designs and competing methods across eight different tasks.