Distributed Model-Based Diffusion For Scalable Multi-Robot Trajectory Optimization

2026-07-23

AI Summary

This work addresses the challenges of multi-robot trajectory optimization in highly non-convex, nonlinear, and non-differentiable environments, where scalability is often hindered by the curse of dimensionality and global coupling. The authors propose a Distributed Model-Based Diffusion (DMBD) framework that decentralizes diffusion models for the first time: each robot independently performs conditional reverse diffusion within its local control subspace to denoise trajectories, while a central server aggregates and broadcasts trajectory estimates to enable coordination. This approach substantially improves scalability and sample efficiency, achieving sub-second real-time solutions across diverse complex scenarios. Experimental results demonstrate clear performance advantages over existing baselines, validating the method’s strong coordination capability and robust scalability.

Abstract

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 framework 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 in sub-seconds and significantly outperforming existing baselines.

Problem

• multi-robot trajectory optimization
• non-convex environments
• curse of dimensionality
• centralized inference
• scalability

Innovation

• Distributed Model-Based Diffusion
• multi-robot trajectory optimization
• conditional reverse diffusion
• scalable coordination
• sampling-based optimization