Embodied Robot Manipulation in the Era of Foundation Models: Planning and Learning Perspectives
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918265172787200 |
|---|---|
| author | Bai, Shuanghao Song, Wenxuan Chen, Jiayi Ji, Yuheng Zhong, Zhide Yang, Jin Zhao, Han Zhou, Wanqi Li, Zhe Ding, Pengxiang Chi, Cheng Xu, Chang Zheng, Xiaolong Wang, Donglin Li, Haoang Zhang, Shanghang Chen, Badong |
| author_facet | Bai, Shuanghao Song, Wenxuan Chen, Jiayi Ji, Yuheng Zhong, Zhide Yang, Jin Zhao, Han Zhou, Wanqi Li, Zhe Ding, Pengxiang Chi, Cheng Xu, Chang Zheng, Xiaolong Wang, Donglin Li, Haoang Zhang, Shanghang Chen, Badong |
| contents | Recent advances in vision, language, and multimodal learning have substantially accelerated progress in robotic foundation models, with robot manipulation remaining a central and challenging problem. This survey examines robot manipulation from an algorithmic perspective and organizes recent learning-based approaches within a unified abstraction of high-level planning and low-level control. At the high level, we extend the classical notion of task planning to include reasoning over language, code, motion, affordances, and 3D representations, emphasizing their role in structured and long-horizon decision making. At the low level, we propose a training-paradigm-oriented taxonomy for learning-based control, organizing existing methods along input modeling, latent representation learning, and policy learning. Finally, we identify open challenges and prospective research directions related to scalability, data efficiency, multimodal physical interaction, and safety. Together, these analyses aim to clarify the design space of modern foundation models for robotic manipulation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_22983 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Embodied Robot Manipulation in the Era of Foundation Models: Planning and Learning Perspectives Bai, Shuanghao Song, Wenxuan Chen, Jiayi Ji, Yuheng Zhong, Zhide Yang, Jin Zhao, Han Zhou, Wanqi Li, Zhe Ding, Pengxiang Chi, Cheng Xu, Chang Zheng, Xiaolong Wang, Donglin Li, Haoang Zhang, Shanghang Chen, Badong Robotics Recent advances in vision, language, and multimodal learning have substantially accelerated progress in robotic foundation models, with robot manipulation remaining a central and challenging problem. This survey examines robot manipulation from an algorithmic perspective and organizes recent learning-based approaches within a unified abstraction of high-level planning and low-level control. At the high level, we extend the classical notion of task planning to include reasoning over language, code, motion, affordances, and 3D representations, emphasizing their role in structured and long-horizon decision making. At the low level, we propose a training-paradigm-oriented taxonomy for learning-based control, organizing existing methods along input modeling, latent representation learning, and policy learning. Finally, we identify open challenges and prospective research directions related to scalability, data efficiency, multimodal physical interaction, and safety. Together, these analyses aim to clarify the design space of modern foundation models for robotic manipulation. |
| title | Embodied Robot Manipulation in the Era of Foundation Models: Planning and Learning Perspectives |
| topic | Robotics |
| url | https://arxiv.org/abs/2512.22983 |