BodyGen: Advancing Towards Efficient Embodiment Co-Design
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916640598261760 |
|---|---|
| author | Lu, Haofei Wu, Zhe Xing, Junliang Li, Jianshu Li, Ruoyu Li, Zhe Shi, Yuanchun |
| author_facet | Lu, Haofei Wu, Zhe Xing, Junliang Li, Jianshu Li, Ruoyu Li, Zhe Shi, Yuanchun |
| contents | Embodiment co-design aims to optimize a robot's morphology and control policy simultaneously. While prior work has demonstrated its potential for generating environment-adaptive robots, this field still faces persistent challenges in optimization efficiency due to the (i) combinatorial nature of morphological search spaces and (ii) intricate dependencies between morphology and control. We prove that the ineffective morphology representation and unbalanced reward signals between the design and control stages are key obstacles to efficiency. To advance towards efficient embodiment co-design, we propose BodyGen, which utilizes (1) topology-aware self-attention for both design and control, enabling efficient morphology representation with lightweight model sizes; (2) a temporal credit assignment mechanism that ensures balanced reward signals for optimization. With our findings, Body achieves an average 60.03% performance improvement against state-of-the-art baselines. We provide codes and more results on the website: https://genesisorigin.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_00533 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BodyGen: Advancing Towards Efficient Embodiment Co-Design Lu, Haofei Wu, Zhe Xing, Junliang Li, Jianshu Li, Ruoyu Li, Zhe Shi, Yuanchun Robotics Machine Learning Systems and Control Embodiment co-design aims to optimize a robot's morphology and control policy simultaneously. While prior work has demonstrated its potential for generating environment-adaptive robots, this field still faces persistent challenges in optimization efficiency due to the (i) combinatorial nature of morphological search spaces and (ii) intricate dependencies between morphology and control. We prove that the ineffective morphology representation and unbalanced reward signals between the design and control stages are key obstacles to efficiency. To advance towards efficient embodiment co-design, we propose BodyGen, which utilizes (1) topology-aware self-attention for both design and control, enabling efficient morphology representation with lightweight model sizes; (2) a temporal credit assignment mechanism that ensures balanced reward signals for optimization. With our findings, Body achieves an average 60.03% performance improvement against state-of-the-art baselines. We provide codes and more results on the website: https://genesisorigin.github.io. |
| title | BodyGen: Advancing Towards Efficient Embodiment Co-Design |
| topic | Robotics Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2503.00533 |