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

TL;DR

PALCAS is a federated reinforcement learning system that improves autonomous vehicle lane changes by prioritizing vehicle urgency, enhancing safety and traffic efficiency.

Contribution

It introduces a novel priority-aware reward function and uses PDQN for cooperative multi-agent lane change decisions in autonomous vehicles.

Findings

PALCAS significantly improves traffic efficiency and safety in simulations.

The system increases destination arrival and merging success rates.

Extensive SUMO simulations validate the effectiveness of PALCAS.

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.