Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning

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...

Full description

Saved in:

Bibliographic Details
Published in:	Proceedings (IEEE Conference on Intelligent Transportation Systems) Vol. 2018-November; pp. 2148 - 2155
Main Authors:	Hoel, Carl-Johan, Wolff, Krister, Laine, Leo
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.11.2018
Subjects:	Accelerated aging Artificial Intelligence (cs.AI) Decision making Machine Learning (cs.LG) Markov processes Neurons Roads Robotics (cs.RO)
ISBN:	9781728103211, 1728103215
ISSN:	2153-0009, 2153-0017, 2153-0017
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	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.
ISBN:	9781728103211 1728103215
ISSN:	2153-0009 2153-0017 2153-0017
DOI:	10.1109/ITSC.2018.8569568