State Dropout-Based Curriculum Reinforcement Learning for Self-Driving at Unsignalized Intersections
This addresses the challenge of self-driving at unsignalized intersections, which is critical for autonomous vehicle safety and efficiency, but the approach is incremental as it builds on existing deep reinforcement learning methods with a curriculum enhancement.
The paper tackled the problem of autonomous vehicles traversing unsignalized intersections by proposing a novel curriculum for deep reinforcement learning, resulting in faster training and better performance compared to non-curriculum methods, as tested in the CommonRoad simulator on T-intersections and four-way intersections.
Traversing intersections is a challenging problem for autonomous vehicles, especially when the intersections do not have traffic control. Recently deep reinforcement learning has received massive attention due to its success in dealing with autonomous driving tasks. In this work, we address the problem of traversing unsignalized intersections using a novel curriculum for deep reinforcement learning. The proposed curriculum leads to: 1) A faster training process for the reinforcement learning agent, and 2) Better performance compared to an agent trained without curriculum. Our main contribution is two-fold: 1) Presenting a unique curriculum for training deep reinforcement learning agents, and 2) showing the application of the proposed curriculum for the unsignalized intersection traversal task. The framework expects processed observations of the surroundings from the perception system of the autonomous vehicle. We test our method in the CommonRoad motion planning simulator on T-intersections and four-way intersections.