Urban Emergency Rescue Based on Multi-Agent Collaborative Learning: Coordination Between Fire Engines and Traffic Lights

TL;DR

The paper addresses efficient urban emergency rescue under heavy traffic by enabling collaborative decision-making between fire engines and traffic lights. It proposes a Unity-based smart-city simulation with a QMIX-based MARL framework and a carefully designed reward function to coordinate routing and signal control. Results indicate QMIX-based coordination yields higher cumulative rewards and faster, safer emergency responses than single-agent baselines, with scalability demonstrated by more agents. The open-source TrafficSim-MARL platform supports research in urban emergency management and policy development.

Abstract

Nowadays, traffic management in urban areas is one of the major economic problems. In particular, when faced with emergency situations like firefighting, timely and efficient traffic dispatching is crucial. Intelligent coordination between multiple departments is essential to realize efficient emergency rescue. In this demo, we present a framework that integrates techniques for collaborative learning methods into the well-known Unity Engine simulator, and thus these techniques can be evaluated in realistic settings. In particular, the framework allows flexible settings such as the number and type of collaborative agents, learning strategies, reward functions, and constraint conditions in practice. The framework is evaluated for an emergency rescue scenario, which could be used as a simulation tool for urban emergency departments.

Figures (3)

• Figure 1: System architecture.
• Figure 2: Rewards comparison between different strategies.
• Figure 3: Screenshot of the simulator in Unity Engine.