Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.07892 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914387433881600 |
|---|---|
| author | Chen, Yiteng Cao, Zhe Ren, Hongjia Yang, Chenjie Li, Wenbo Wang, Shiyi Wang, Yemin Zhang, Li Shao, Yanming Zhao, Zhenjun Zhuang, Huiping Wu, Qingyao |
| author_facet | Chen, Yiteng Cao, Zhe Ren, Hongjia Yang, Chenjie Li, Wenbo Wang, Shiyi Wang, Yemin Zhang, Li Shao, Yanming Zhao, Zhenjun Zhuang, Huiping Wu, Qingyao |
| contents | Research on robotic manipulation has developed a diverse set of policy paradigms, including vision-language-action (VLA) models, vision-action (VA) policies, and code-based compositional approaches. Concrete policies typically attain high success rates on specific task distributions but lim-ited generalization beyond it. Rather than proposing an other monolithic policy, we propose to leverage the complementary strengths of existing approaches through intelligent policy routing. We introduce RoboRouter, a training-free framework that maintains a pool of heterogeneous policies and learns to select the best-performing policy for each task through accumulated execution experience. Given a new task, RoboRouter constructs a semantic task representation, retrieves historical records of similar tasks, predicts the optimal policy choice without requiring trial-and-error, and incorporates structured feedback to refine subsequent routing decisions. Integrating a new policy into the system requires only lightweight evaluation and incurs no training overhead. Across simulation benchmark and real-world evaluations, RoboRouter consistently outperforms than in-dividual policies, improving average success rate by more than 3% in simulation and over 13% in real-world settings, while preserving execution efficiency. Our results demonstrate that intelligent routing across heterogeneous, off-the-shelf policies provides a practical and scalable pathway toward building more capable robotic systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07892 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RoboRouter: Training-Free Policy Routing for Robotic Manipulation Chen, Yiteng Cao, Zhe Ren, Hongjia Yang, Chenjie Li, Wenbo Wang, Shiyi Wang, Yemin Zhang, Li Shao, Yanming Zhao, Zhenjun Zhuang, Huiping Wu, Qingyao Robotics Research on robotic manipulation has developed a diverse set of policy paradigms, including vision-language-action (VLA) models, vision-action (VA) policies, and code-based compositional approaches. Concrete policies typically attain high success rates on specific task distributions but lim-ited generalization beyond it. Rather than proposing an other monolithic policy, we propose to leverage the complementary strengths of existing approaches through intelligent policy routing. We introduce RoboRouter, a training-free framework that maintains a pool of heterogeneous policies and learns to select the best-performing policy for each task through accumulated execution experience. Given a new task, RoboRouter constructs a semantic task representation, retrieves historical records of similar tasks, predicts the optimal policy choice without requiring trial-and-error, and incorporates structured feedback to refine subsequent routing decisions. Integrating a new policy into the system requires only lightweight evaluation and incurs no training overhead. Across simulation benchmark and real-world evaluations, RoboRouter consistently outperforms than in-dividual policies, improving average success rate by more than 3% in simulation and over 13% in real-world settings, while preserving execution efficiency. Our results demonstrate that intelligent routing across heterogeneous, off-the-shelf policies provides a practical and scalable pathway toward building more capable robotic systems. |
| title | RoboRouter: Training-Free Policy Routing for Robotic Manipulation |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.07892 |