English

CRLLK: Constrained Reinforcement Learning for Lane Keeping in Autonomous Driving

Machine Learning 2025-03-31 v1 Robotics

Abstract

Lane keeping in autonomous driving systems requires scenario-specific weight tuning for different objectives. We formulate lane-keeping as a constrained reinforcement learning problem, where weight coefficients are automatically learned along with the policy, eliminating the need for scenario-specific tuning. Empirically, our approach outperforms traditional RL in efficiency and reliability. Additionally, real-world demonstrations validate its practical value for real-world autonomous driving.

Keywords

Cite

@article{arxiv.2503.22248,
  title  = {CRLLK: Constrained Reinforcement Learning for Lane Keeping in Autonomous Driving},
  author = {Xinwei Gao and Arambam James Singh and Gangadhar Royyuru and Michael Yuhas and Arvind Easwaran},
  journal= {arXiv preprint arXiv:2503.22248},
  year   = {2025}
}

Comments

Accepted at AAMAS 2025 (Demonstration Track), 3 pages, 2 figures, 1 table