EMVLight: a Multi-agent Reinforcement Learning Framework for an Emergency Vehicle Decentralized Routing and Traffic Signal Control System

Abstract

Emergency vehicles (EMVs) play a crucial role in responding to time-critical calls such as medical emergencies and fire outbreaks in urban areas. Existing methods for EMV dispatch typically optimize routes based on historical traffic-flow data and design traffic signal pre-emption accordingly; however, we still lack a systematic methodology to address the coupling between EMV routing and traffic signal control. In this paper, we propose EMVLight, a decentralized reinforcement learning (RL) framework for joint dynamic EMV routing and traffic signal pre-emption. We adopt the multi-agent advantage actor-critic method with policy sharing and spatial discounted factor. This framework addresses the coupling between EMV navigation and traffic signal control via an innovative design of multi-class RL agents and a novel pressure-based reward function. The proposed methodology enables EMVLight to learn network-level cooperative traffic signal phasing strategies that not only reduce EMV travel time but also shortens the travel time of non-EMVs. Simulation-based experiments indicate that EMVLight enables up to a $42.6\%$ reduction in EMV travel time as well as an $23.5\%$ shorter average travel time compared with existing approaches.

19 figures, 10 tables. Manuscript extended on previous work arXiv:2109.05429, arXiv:2111.00278

References in corpus (9)

• Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation
• Towards Data Distillation for End-to-end Spoken Conversational Question Answering
• Undistillable: Making A Nasty Teacher That CANNOT teach students
• SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentation
• Contextualized Attention-based Knowledge Transfer for Spoken Conversational Question Answering
• Dynamic Queue-Jump Lane for Emergency Vehicles under Partially Connected Settings: A Multi-Agent Deep Reinforcement Learning Approach
• EMVLight: A Decentralized Reinforcement Learning Framework for Efficient Passage of Emergency Vehicles
• MEGAN: Memory Enhanced Graph Attention Network for Space-Time Video Super-Resolution
• Graph-in-Graph Network for Automatic Gene Ontology Description Generation

Cited by in corpus (1)

• UniTSA: A Universal Reinforcement Learning Framework for V2X Traffic Signal Control