DSIP: A Dynamic Coordination Planner for Signal-Free Intersections using Diffusion-Model-Based Multi-Agent Motion Planning

2026-06-28

AI Summary

This study addresses the inefficiencies of conventional traffic signal control, which often causes frequent vehicle stops and increased intersection delays under high traffic volumes. To overcome these limitations, the authors propose the DSIP framework—the first approach to integrate diffusion generative models into multi-agent cooperative trajectory planning for unsignalized intersections. By transcending the constraints of discrete signal phases, DSIP enables software-defined collaborative optimization in continuous spatiotemporal dimensions. Evaluated through diffusion-driven multi-vehicle trajectory generation and validated via SUMO simulations, the method significantly outperforms both fixed-time signal control and state-of-the-art reinforcement learning approaches under moderate-to-high traffic densities, effectively reducing average vehicle delay and enhancing traffic throughput.

Abstract

Traffic signal control at urban intersections inherently introduces stop-and-go behavior, resulting in increased delays and reduced traffic efficiency, especially under high traffic demand. With the emergence of connected and automated vehicles (CAVs), trajectory-level coordination has emerged as a high-potential strategy to augment or transcend conventional phase-based management. This paper proposes DSIP (Diffusion-model-based Signal-free Intersection Planner), a multi-agent motion planning framework driven by a generative diffusion process. DSIP shifts the intersection management paradigm from discrete temporal phasing to continuous multi-vehicle trajectory optimization. This work evaluates the theoretical upper-bound performance of this coordination strategy under idealized communication and execution conditions to isolate the core benefits of the diffusion-driven approach. Using the SUMO platform, we evaluate DSIP across diverse four-leg intersection configurations. Experimental results demonstrate that DSIP significantly reduces average delay and maintains higher average speed compared to both fixed-time signal control and state-of-the-art reinforcement-learning-based controllers, particularly in medium- to high-density traffic. These findings suggest that diffusion-based trajectory planning provides a scalable and robust foundation for future autonomous intersection management. By unlocking latent intersection capacity through software-defined coordination, this approach offers a cost-effective pathway to improve urban traffic flow efficiency without requiring physical infrastructure expansion.

Problem

• signal-free intersection
• traffic efficiency
• trajectory coordination
• connected and automated vehicles
• intersection management

Innovation

• diffusion model
• signal-free intersection
• multi-agent motion planning
• trajectory optimization
• connected and automated vehicles