A Conflicts-free, Speed-lossless KAN-based Reinforcement Learning Decision System for Interactive Driving in Roundabouts
This work addresses safety and efficiency challenges for autonomous vehicles in roundabouts, representing an incremental improvement over existing methods.
The paper tackles the problem of safe and efficient autonomous driving in roundabouts with mixed traffic by proposing a learning-based algorithm that integrates deep Q-learning, Kolmogorov-Arnold Networks, and safety mechanisms, resulting in fewer collisions and reduced travel time compared to state-of-the-art methods.
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.