A Deep Reinforcement Learning Driving Policy for Autonomous Road Vehicles

TL;DR

This paper proposes a reinforcement learning-based driving policy for autonomous vehicles on freeways, demonstrating its effectiveness through comparison with optimal and manual driving policies in simulation.

Contribution

It introduces a reinforcement learning approach for freeway path planning that requires no prior knowledge of system dynamics.

Findings

Reinforcement learning policy performs comparably to optimal dynamic programming policy.

The RL policy outperforms manual driving in simulation.

Minimal assumptions about environment dynamics are sufficient for effective path planning.

Abstract

This work regards our preliminary investigation on the problem of path planning for autonomous vehicles that move on a freeway. We approach this problem by proposing a driving policy based on Reinforcement Learning. The proposed policy makes minimal or no assumptions about the environment, since no a priori knowledge about the system dynamics is required. We compare the performance of the proposed policy against an optimal policy derived via Dynamic Programming and against manual driving simulated by SUMO traffic simulator.