Deep Reinforcement-Learning-based Driving Policy for Autonomous Road Vehicles.

What is it about?

In this work, the problem of path planning for an autonomous vehicle that moves on a freeway is considered. The most common approaches that are used to address this problem are based on optimal control methods, which make assumptions about the model of the environment and the system dynamics. On the contrary, this work proposes the development of a driving policy based on reinforcement learning. In this way, the proposed driving policy makes minimal or no assumptions about the environment, since a priori knowledge about the system dynamics is not required. Driving scenarios where the road is occupied both by autonomous and manual driving vehicles are considered. To the best of the authors' knowledge, this is one of the first approaches that propose a reinforcement learning driving policy for mixed driving environments. The derived reinforcement learning policy, firstly, is compared against an optimal policy derived via dynamic programming, and, secondly, its efficiency is evaluated under realistic scenarios generated by the established SUMO microscopic traffic flow simulator. Finally, some initial results regarding the effect of autonomous vehicles' behaviour on the overall traffic flow are presented.

Featured Image

Photo by Ildar Garifullin on Unsplash

Photo by Ildar Garifullin on Unsplash

Why is it important?

We combine reinforcement learning and ad-hoc safety rules to derive collision-free driving policies for autonomous road vehicles in mixed driving scenarios. To the best of our knowledge, this is one of the first approaches towards this direction. Moreover, we conducted an initial investigation regarding the effect of the derived driving policies on the overall traffic flow.