Hybrid Deep Reinforcement Learning and Planning for Safe and Comfortable Automated Driving
It addresses safe and comfortable automated driving for self-driving cars, but appears incremental as it combines existing techniques like planning and reinforcement learning.
The paper tackles collision-free navigation for self-driving cars in POMDPs by proposing HyLEAR, a hybrid learning method that embeds planner knowledge into deep reinforcement learning, resulting in significant outperformance in safety and ride comfort on the CARLA-CTS1 benchmark.
We present a novel hybrid learning method, HyLEAR, for solving the collision-free navigation problem for self-driving cars in POMDPs. HyLEAR leverages interposed learning to embed knowledge of a hybrid planner into a deep reinforcement learner to faster determine safe and comfortable driving policies. In particular, the hybrid planner combines pedestrian path prediction and risk-aware path planning with driving-behavior rule-based reasoning such that the driving policies also take into account, whenever possible, the ride comfort and a given set of driving-behavior rules. Our experimental performance analysis over the CARLA-CTS1 benchmark of critical traffic scenarios revealed that HyLEAR can significantly outperform the selected baselines in terms of safety and ride comfort.