PALCAS: A Priority-Aware Intelligent Lane Change Advisory System for Autonomous Vehicles using Federated Reinforcement Learning

2026-04-29

AI Summary

This work addresses the challenge of insufficient priority awareness and suboptimal safety-efficiency trade-offs in autonomous lane-changing within multi-vehicle cooperative scenarios. To this end, the authors propose a priority-aware collaborative lane-changing method based on multi-agent federated reinforcement learning. The approach dynamically ranks vehicles’ lane-change requests according to destination urgency and introduces a novel safety-oriented reward function that integrates both lateral and longitudinal control. Notably, it is the first to apply federated reinforcement learning to decentralized multi-vehicle systems with explicit support for priority-based decision-making. Experimental results, leveraging the PDQN algorithm, SUMO traffic simulator, and Mosaic V2X communication framework, demonstrate significant improvements over existing baselines in traffic efficiency, safety, ride comfort, destination arrival rate, and merging success rate.

Abstract

We present a priority-aware intelligent lane change advisory system based on multi-agent federated reinforcement learning, namely PALCAS, for autonomous vehicles (AVs). While existing lane-change approaches typically focus on single-agent systems or centralized multi-agent systems, we introduce a federated reinforcement learning-based multi-agent lane change system prioritizing lane changing based on vehicle destination urgency. PALCAS incorporates a novel priority-aware safe lane-change reward function to enable judicious lane-change decisions in both mandatory and discretionary scenarios. PALCAS leverages the parameterized deep Q-network (PDQN) algorithm to facilitate effective cooperation among agents, enabling both lateral and longitudinal motion controls of AVs. Extensive simulations conducted using the SUMO traffic simulator and Mosaic V2X communication framework demonstrate that PALCAS significantly improves traffic efficiency, driving safety, comfort, destination arrival rates, and merging success rates compared to baseline methods.

Problem

• lane change
• autonomous vehicles
• priority-aware
• multi-agent systems
• traffic efficiency

Innovation

• Federated Reinforcement Learning
• Priority-aware Lane Change
• Multi-agent Autonomous Driving
• Parameterized Deep Q-Network (PDQN)
• Intelligent Transportation Systems