no code implementations • 25 Jul 2021 • Haoyi Niu, Jianming Hu, Zheyu Cui, Yi Zhang
How to explore corner cases as efficiently and thoroughly as possible has long been one of the top concerns in the context of deep reinforcement learning (DeepRL) autonomous driving.
no code implementations • 9 Sep 2020 • Haoyi Niu, Jianming Hu, Zheyu Cui, Yi Zhang
The following approach reveals that DRL could complement rule-based avoiding strategy in generalization, and on the contrary, the rule-based avoiding strategy could complement DRL in stability, and their combination could lead to less response time, lower collision rate and smoother trajectory.