AI Recommendation Systems for Lane-Changing Using Adherence-Aware Reinforcement Learning

In this paper, we present an adherence-aware reinforcement learning (RL) approach aimed at seeking optimal lane-changing recommendations within a semi-autonomous driving environment to enhance a single vehicle's travel efficiency. The problem is framed within a Markov decision process setting and is addressed through an adherence-aware deep Q network, which takes into account the partial compliance of human drivers with the recommended actions. This approach is evaluated within CARLA's driving environment under realistic scenarios.

@article{sun2025_2504.20187,
  title={ AI Recommendation Systems for Lane-Changing Using Adherence-Aware Reinforcement Learning },
  author={ Weihao Sun and Heeseung Bang and Andreas A. Malikopoulos },
  journal={arXiv preprint arXiv:2504.20187},
  year={ 2025 }
}