Diffusion for Long-Horizon Multi-Robot Path Planning in Human-Shared Environments

2026-07-10

AI Summary

In human-robot shared environments, multi-robot systems struggle to simultaneously satisfy long-horizon planning, real-time responsiveness, social compliance, and large-scale coordination. This work proposes the Multi-Robot Rolling Diffusion (MRRD) framework, which, for the first time, applies diffusion models to variable-duration multi-robot navigation. MRRD integrates receding-horizon planning, parallel diffusion-based inference, and conflict-based search, enhanced by urgency-aware temporal conditioning and a differentiated guidance mechanism to jointly promote social awareness and inter-robot coordination. Experiments demonstrate that MRRD enables real-time operation of up to 15 robots in dense crowds, significantly outperforming existing methods in both safety and task success rate.

Abstract

Multi-robot path planning in human-shared environments requires a delicate balance between robust inter-robot coordination and socially aware behavior. While diffusion models excel at generating predictable, human-like paths, existing generative planners are often restricted to paths of fixed duration and high computational latency, limiting their adaptability to varying goal distances and hindering real-time deployment. We present Multi-Robot Rolling Diffusion (MRRD), a novel framework that enables real-time, long-horizon navigation for large robot teams through dense crowds. MRRD combines a rolling-horizon scheme to accommodate the limited prediction horizon of human motion, parallelized diffusion inference for scalable generation of human-like paths, and a conflict-based-search mechanism for resolving inter-robot collisions. It further incorporates urgency-based temporal conditioning to generate paths with varying speeds and employs differentiated guidance terms to maximize both social awareness around humans and efficient coordination between robots. Experimental results in crowded environments demonstrate that MRRD successfully scales to 15 robots in real-time, significantly outperforming existing baselines in both safety and mission success rates.

Problem

• multi-robot path planning
• human-shared environments
• diffusion models
• real-time navigation
• long-horizon planning

Innovation

• rolling-horizon diffusion
• multi-robot path planning
• socially aware navigation
• parallelized diffusion inference
• conflict-based search