A Conflicts-free, Speed-lossless KAN-based Reinforcement Learning Decision System for Interactive Driving in Roundabouts

TL;DR

This paper introduces a novel reinforcement learning system for autonomous vehicles in roundabouts that ensures safety, efficiency, and stability by combining deep Q-learning, KAN, action inspection, route planning, and model predictive control.

Contribution

It presents a conflicts-free, speed-lossless decision system integrating multiple advanced techniques for safe and efficient autonomous driving in complex roundabout scenarios.

Findings

Fewer collisions compared to existing methods

Reduced travel time in simulated environments

Stable training with smooth reward convergence

Abstract

Safety and efficiency are crucial for autonomous driving in roundabouts, especially mixed traffic with both autonomous vehicles (AVs) and human-driven vehicles. This paper presents a learning-based algorithm that promotes safe and efficient driving across varying roundabout traffic conditions. A deep Q-learning network is used to learn optimal strategies in complex multi-vehicle roundabout scenarios, while a Kolmogorov-Arnold Network (KAN) improves the AVs' environmental understanding. To further enhance safety, an action inspector filters unsafe actions, and a route planner optimizes driving efficiency. Moreover, model predictive control ensures stability and precision in execution. Experimental results demonstrate that the proposed system consistently outperforms state-of-the-art methods, achieving fewer collisions, reduced travel time, and stable training with smooth reward convergence.