Controlling an Autonomous Vehicle with Deep Reinforcement Learning

2019/09/30 by Andreas Folkers, Matthias Rick, Christof Büskens · 1 citation
Computer Science · #cs.RO #cs.AI #cs.LG

paper · pdf · doi:10.1109/ivs.2019.8814124

Award as Best Student Paper at IEEE Intelligent Vehicles Symposium (IV), 2019

arxiv created 2020/03/13 · arxiv updated 2020/03/16

Abstract

We present a control approach for autonomous vehicles based on deep reinforcement learning. A neural network agent is trained to map its estimated state to acceleration and steering commands given the objective of reaching a specific target state while considering detected obstacles. Learning is performed using state-of-the-art proximal policy optimization in combination with a simulated environment. Training from scratch takes five to nine hours. The resulting agent is evaluated within simulation and subsequently applied to control a full-size research vehicle. For this, the autonomous exploration of a parking lot is considered, including turning maneuvers and obstacle avoidance. Altogether, this work is among the first examples to successfully apply deep reinforcement learning to a real vehicle.

Cited by

• Exposing the Copycat Problem of Imitation-based Planner: A Novel Closed-Loop Simulator, Causal Benchmark and Joint IL-RL Baseline