发表机构
Robotics Department, University of Michigan（密歇根大学机器人系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对多机器人轨迹优化难题，提出分布式基于模型的扩散算法（DMBD），将反向扩散过程分解为局部条件反向扩散过程，使机器人能独立去噪，模拟显示其可扩展性强，能快速解决协调任务且优于现有基线。
AI 中文摘要
多机器人系统的轨迹优化仍然是一个关键挑战，尤其是在高度非凸、非线性和不可微的环境中导航时。虽然基于模型的扩散（MBD）最近已成为一种有前途的基于采样的单机器人轨迹生成优化范式，但将其扩展到多机器人系统会导致一个集中式、高维推理问题，即（i）由于维度诅咒而样本效率低下，（ii）需要全局访问所有机器人的动力学、约束和目标。为了解决这个问题，我们提出了分布式基于模型的扩散（DMBD），这是一种分布式服务器-机器人框架，它将反向扩散过程分解为局部条件反向扩散过程。这种分解使每个机器人能够在其自己的控制子空间内迭代地独立执行去噪，同时以服务器聚合和广播的其他机器人的当前轨迹估计为条件。在目标交换、多层覆盖、停车和高峰时段场景中的广泛模拟表明，DMBD实现了强大的可扩展性，能在亚秒级内解决许多具有挑战性的协调任务，并且显著优于现有基线。
英文摘要
Trajectory optimization for multi-robot systems remains a critical challenge, particularly when navigating highly non-convex, non-linear, and non-differentiable environments. While Model-Based Diffusion (MBD) has recently emerged as a promising sampling-based optimization paradigm for single-robot trajectory generation, extending it to multi-robot systems results in a centralized, high-dimensional inference problem that (i) suffers from poor sample efficiency due to the curse of dimensionality and (ii) requires global access to all robots' dynamics, constraints, and objectives. To address this, we propose Distributed Model-Based Diffusion (DMBD), a distributed server-robot method that decomposes the reverse diffusion process into local conditional reverse diffusion processes. This decomposition enables each robot to iteratively perform denoising independently within its own control subspace while conditioning on the current trajectory estimates of the other robots that are aggregated and broadcast by the server. Extensive simulations in goal swapping, multi-floor coverage, parking, and rush-hour scenarios demonstrate that DMBD achieves strong scalability, solving many challenging coordination tasks with sub-second computation time and outperforming existing baselines.
CommentsSubmitted to 2027 IEEE ICRA, 9 pages, 4 figures
