GauDP: Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914130736185344 |
|---|---|
| author | Wang, Ziye Kang, Li Qin, Yiran Ma, Jiahua Peng, Zhanglin Bai, Lei Zhang, Ruimao |
| author_facet | Wang, Ziye Kang, Li Qin, Yiran Ma, Jiahua Peng, Zhanglin Bai, Lei Zhang, Ruimao |
| contents | Recently, effective coordination in embodied multi-agent systems has remained a fundamental challenge, particularly in scenarios where agents must balance individual perspectives with global environmental awareness. Existing approaches often struggle to balance fine-grained local control with comprehensive scene understanding, resulting in limited scalability and compromised collaboration quality. In this paper, we present GauDP, a novel Gaussian-image synergistic representation that facilitates scalable, perception-aware imitation learning in multi-agent collaborative systems. Specifically, GauDP constructs a globally consistent 3D Gaussian field from decentralized RGB observations, then dynamically redistributes 3D Gaussian attributes to each agent's local perspective. This enables all agents to adaptively query task-critical features from the shared scene representation while maintaining their individual viewpoints. This design facilitates both fine-grained control and globally coherent behavior without requiring additional sensing modalities (e.g., 3D point cloud). We evaluate GauDP on the RoboFactory benchmark, which includes diverse multi-arm manipulation tasks. Our method achieves superior performance over existing image-based methods and approaches the effectiveness of point-cloud-driven methods, while maintaining strong scalability as the number of agents increases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_00998 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GauDP: Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies Wang, Ziye Kang, Li Qin, Yiran Ma, Jiahua Peng, Zhanglin Bai, Lei Zhang, Ruimao Robotics Recently, effective coordination in embodied multi-agent systems has remained a fundamental challenge, particularly in scenarios where agents must balance individual perspectives with global environmental awareness. Existing approaches often struggle to balance fine-grained local control with comprehensive scene understanding, resulting in limited scalability and compromised collaboration quality. In this paper, we present GauDP, a novel Gaussian-image synergistic representation that facilitates scalable, perception-aware imitation learning in multi-agent collaborative systems. Specifically, GauDP constructs a globally consistent 3D Gaussian field from decentralized RGB observations, then dynamically redistributes 3D Gaussian attributes to each agent's local perspective. This enables all agents to adaptively query task-critical features from the shared scene representation while maintaining their individual viewpoints. This design facilitates both fine-grained control and globally coherent behavior without requiring additional sensing modalities (e.g., 3D point cloud). We evaluate GauDP on the RoboFactory benchmark, which includes diverse multi-arm manipulation tasks. Our method achieves superior performance over existing image-based methods and approaches the effectiveness of point-cloud-driven methods, while maintaining strong scalability as the number of agents increases. |
| title | GauDP: Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies |
| topic | Robotics |
| url | https://arxiv.org/abs/2511.00998 |