Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning
Preprint
Abstract
This paper introduces a method, based on deep reinforcement learning, for automatically generating a general purpose decision making function. A Deep Q-Network agent was trained in a simulated environment to handle speed and lane change decisions for a truck-trailer combination. In a highway driving case, it is shown that the method produced an agent that matched or surpassed the performance of a commonly used reference model. To demonstrate the generality of the method, the exact same algorithm was also tested by training it for an overtaking case on a road with oncoming traffic. Furthermore, a novel way of applying a convolutional neural network to high level input that represents interchangeable objects is also introduced.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Mastering the game of Go without human knowledgeNature, 2017
- Deep Reinforcement Learning framework for Autonomous DrivingElectronic Imaging, 2017
- If, When, and How to Perform Lane Change Maneuvers on HighwaysIEEE Intelligent Transportation Systems Magazine, 2016
- Truck Automation: Testing and Trusting the Virtual Driver2016
- A review of inverse reinforcement learning theory and recent advances2012
- General Lane-Changing Model MOBIL for Car-Following ModelsTransportation Research Record: Journal of the Transportation Research Board, 2007
- A Two-Point Visual Control Model of SteeringPerception, 2004
- Congested traffic states in empirical observations and microscopic simulationsPhysical Review E, 2000
- Planning and acting in partially observable stochastic domainsArtificial Intelligence, 1998
- A model for the structure of lane-changing decisionsTransportation Research Part B: Methodological, 1986