动态调整多机器人协作任务，实时应对突发干扰。
Graph-of-Constraints Model Predictive Control for Reactive Multi-agent Task and Motion Planning
- 构建约束图模型，支持任务部分排序与动态分配。
- 无需训练数据，仅靠视觉观测在线调整路径，成功率更高。
- 适合真实场景下需快速响应的多机器人协同操作。
多智能体任务与运动规划（TAMP）中的几何约束序列至关重要。现有方法在处理任务部分排序和动态代理分配时表现不佳，通常假设静态分配，无法应对扰动导致的任务重分配。为此，我们提出图约束模型预测控制（GoC-MPC），一种集成于模型预测控制（MPC）的广义约束序列框架。该方法天然支持部分有序任务、动态代理协调与扰动恢复。通过在追踪的3D关键点上定义约束，本方法可鲁棒地解决多种多智能体操作任务——在仅依赖视觉观测的情况下在线协调多个代理，无需训练数据或环境模型。实验表明，相较于近期基线方法，GoC-MPC实现了更高的成功率、显著更快的TAMP计算速度以及更短的整体路径，验证了其在真实扰动下的高效性与鲁棒性。补充视频与代码见：https://sites.google.com/view/goc-mpc/home。
原文摘要 · Abstract (English)
Sequences of interdependent geometric constraints are central to many multi-agent Task and Motion Planning (TAMP) problems. However, existing methods for handling such constraint sequences struggle with partially ordered tasks and dynamic agent assignments. They typically assume static assignments and cannot adapt when disturbances alter task allocations. To overcome these limitations, we introduce Graph-of-Constraints Model Predictive Control (GoC-MPC), a generalized sequence-of-constraints framework integrated with MPC. GoC-MPC naturally supports partially ordered tasks, dynamic agent coordination, and disturbance recovery. By defining constraints over tracked 3D keypoints, our method robustly solves diverse multi-agent manipulation tasks-coordinating agents and adapting online from visual observations alone, without relying on training data or environment models. Experiments demonstrate that GoC-MPC achieves higher success rates, significantly faster TAMP computation, and shorter overall paths compared to recent baselines, establishing it as an efficient and robust solution for multi-agent manipulation under real-world disturbances. Our supplementary video and code can be found at https://sites.google.com/view/goc-mpc/home .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。