CoEnv: Driving Embodied Multi-Agent Collaboration via Compositional Environment
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918430806900736 |
|---|---|
| author | Kang, Li Fan, Yutao Li, Rui Zhou, Heng Qin, Yiran Zhang, Zhemeng Huang, Songtao Song, Xiufeng Zhang, Zaibin Chen, Bruno N. Y. Yin, Zhenfei Zhou, Dongzhan Zuo, Wangmeng Bai, Lei |
| author_facet | Kang, Li Fan, Yutao Li, Rui Zhou, Heng Qin, Yiran Zhang, Zhemeng Huang, Songtao Song, Xiufeng Zhang, Zaibin Chen, Bruno N. Y. Yin, Zhenfei Zhou, Dongzhan Zuo, Wangmeng Bai, Lei |
| contents | Multi-agent embodied systems hold promise for complex collaborative manipulation, yet face critical challenges in spatial coordination, temporal reasoning, and shared workspace awareness. Inspired by human collaboration where cognitive planning occurs separately from physical execution, we introduce the concept of compositional environment -- a synergistic integration of real-world and simulation components that enables multiple robotic agents to perceive intentions and operate within a unified decision-making space. Building on this concept, we present CoEnv, a framework that leverages simulation for safe strategy exploration while ensuring reliable real-world deployment. CoEnv operates through three stages: real-to-sim scene reconstruction that digitizes physical workspaces, VLM-driven action synthesis supporting both real-time planning with high-level interfaces and iterative planning with code-based trajectory generation, and validated sim-to-real transfer with collision detection for safe deployment. Extensive experiments on challenging multi-arm manipulation benchmarks demonstrate CoEnv's effectiveness in achieving high task success rates and execution efficiency, establishing a new paradigm for multi-agent embodied AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_05484 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CoEnv: Driving Embodied Multi-Agent Collaboration via Compositional Environment Kang, Li Fan, Yutao Li, Rui Zhou, Heng Qin, Yiran Zhang, Zhemeng Huang, Songtao Song, Xiufeng Zhang, Zaibin Chen, Bruno N. Y. Yin, Zhenfei Zhou, Dongzhan Zuo, Wangmeng Bai, Lei Robotics Computer Vision and Pattern Recognition I.2.9; I.2.10 Multi-agent embodied systems hold promise for complex collaborative manipulation, yet face critical challenges in spatial coordination, temporal reasoning, and shared workspace awareness. Inspired by human collaboration where cognitive planning occurs separately from physical execution, we introduce the concept of compositional environment -- a synergistic integration of real-world and simulation components that enables multiple robotic agents to perceive intentions and operate within a unified decision-making space. Building on this concept, we present CoEnv, a framework that leverages simulation for safe strategy exploration while ensuring reliable real-world deployment. CoEnv operates through three stages: real-to-sim scene reconstruction that digitizes physical workspaces, VLM-driven action synthesis supporting both real-time planning with high-level interfaces and iterative planning with code-based trajectory generation, and validated sim-to-real transfer with collision detection for safe deployment. Extensive experiments on challenging multi-arm manipulation benchmarks demonstrate CoEnv's effectiveness in achieving high task success rates and execution efficiency, establishing a new paradigm for multi-agent embodied AI. |
| title | CoEnv: Driving Embodied Multi-Agent Collaboration via Compositional Environment |
| topic | Robotics Computer Vision and Pattern Recognition I.2.9; I.2.10 |
| url | https://arxiv.org/abs/2604.05484 |