English

Adversarial Imitation Learning via Random Search in Lane Change Decision-Making

Robotics 2021-09-14 v1

Abstract

As the advanced driver assistance system (ADAS) functions become more sophisticated, the strategies that properly coordinate interaction and communication among the ADAS functions are required for autonomous driving. This paper proposes a derivative-free optimization based imitation learning method for the decision maker that coordinates the proper ADAS functions. The proposed method is able to make decisions in multi-lane highways timely with the LIDAR data. The simulation-based evaluation verifies that the proposed method presents desired performance.

Keywords

Cite

@article{arxiv.2109.05197,
  title  = {Adversarial Imitation Learning via Random Search in Lane Change Decision-Making},
  author = {Myungjae Shin and Joongheon Kim},
  journal= {arXiv preprint arXiv:2109.05197},
  year   = {2021}
}

Comments

Note that this framework is accepted to be published in proceedings of IJCNN 2019 and IJCAI 2019