Learning how to drive in a real world simulation with deep Q-Networks
- 1 June 2017
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 244-250
- https://doi.org/10.1109/ivs.2017.7995727
Abstract
We present a reinforcement learning approach using Deep Q-Networks to steer a vehicle in a 3D physics simulation. Relying solely on camera image input the approach directly learns steering the vehicle in an end-to-end manner. The system is able to learn human driving behavior without the need of any labeled training data. An action-based reward function is proposed, which is motivated by a potential use in real world reinforcement learning scenarios. Compared to a naive distance-based reward function, it improves the overall driving behavior of the vehicle agent. The agent is even able to reach comparable to human driving performance on a previously unseen track in our simulation environment.This publication has 22 references indexed in Scilit:
- On circular traffic sign detection and recognitionExpert Systems with Applications, 2016
- Pedestrian Detection with Spatially Pooled Features and Structured Ensemble LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Autonomous driving at Ulm University: A modular, robust, and sensor-independent fusion approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Human-level control through deep reinforcement learningNature, 2015
- Evolving deep unsupervised convolutional networks for vision-based reinforcement learningPublished by Association for Computing Machinery (ACM) ,2014
- Car detection in sequences of images of urban environments using mixture of deformable part modelsPattern Recognition Letters, 2014
- Robust lane marking detection under different road conditionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Detection of traffic signs in real-world images: The German traffic sign detection benchmarkPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Traffic light mapping and detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Self-improving reactive agents based on reinforcement learning, planning and teachingMachine Learning, 1992