Model-Based Diffusion Optimal Control for Multi-Robot Motion Planning

2026-07-14

AI Summary

This work addresses the challenge of generating dynamically feasible and collision-free trajectories for multiple robots in continuous space, where the joint trajectory space suffers from combinatorial explosion and hard safety constraints are difficult to enforce rigorously. The authors propose a model-driven diffusion planning framework that requires no demonstration data, formulating trajectory generation as a model-based diffusion optimal control problem. By integrating known robot dynamics, control barrier function (CBF) constraint projection, and conflict-based search within the sampling process, the method simultaneously ensures dynamic feasibility, safety, and coordination. Notably, this is the first approach to combine CBFs with conflict-based search, significantly enhancing planning efficiency and scalability. Extensive simulations demonstrate superior performance over existing baselines in terms of sample efficiency, trajectory smoothness, success rate, and computation time, while strictly guaranteeing collision avoidance.

Abstract

Multi-Robot Motion Planning in continuous environments, where robots must generate dynamically feasible, collision-free trajectories, is challenging due to the combinatorial growth of the joint trajectory space and the difficulty of enforcing dynamic feasibility and hard safety constraints. Recent approaches recast trajectory planning as probabilistic inference, sampling from a posterior over trajectories using diffusion models whose score functions are learned from demonstration data. While showing promising performance, these approaches are limited: they often rely on sizable demonstration datasets and struggle to rigorously enforce dynamics and hard safety constraints during sampling. To this end, we introduce Model-Based Diffusion Optimal Control (MDOC), a model-based diffusion planner that efficiently produces dynamically feasible trajectories without relying on data. Crucially, we show that MDOC's safety mechanism -- combining known dynamics models with Control Barrier Function-constrained projections -- naturally scales to multi-robot planning settings through Conflict-Based Search. Across simulation experiments, this integrated method consistently outperforms representative baseline planners in sample efficiency, geometric smoothness, and success rate, while reducing computation time and producing collision-free trajectories.

Problem

• Multi-Robot Motion Planning
• Dynamic Feasibility
• Collision-Free Trajectories
• Safety Constraints
• Continuous Environments

Innovation

• Model-Based Diffusion
• Control Barrier Functions
• Multi-Robot Motion Planning
• Diffusion Models
• Conflict-Based Search