A Hybrid Collision Avoidance Algorithm for Multi-agent Traffic Coordination Under Limited Communication

This paper proposes a low complexity distributed multi-agent coordination algorithm for agents to reach their target positions under dense traffic while accounting for limited communication. The single-integrator model is used and each agent is assumed to be communicating with only one other agent at a time to approximate limited bandwidth in real systems. A unique hybrid algorithm of Voronoi Cells, repulsion fields and the velocity obstacle method is used to guarantee non-collision while enabling agents to pass between each other. We break symmetry to avoid deadlocks and livelocks by having agent pairs make mutual decisions based on comparison of the conditional priority of each agent. The effectiveness of our method is demonstrated in simulations, which show that they are able to converge to their targets in reasonable time.