Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning
Paper in proceeding, 2018

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.
https://arxiv.org/abs/1803.10056

Artificial Intelligence (cs.AI)

Robotics (cs.RO)

Machine Learning (cs.LG)

Author

Carl-Johan E Hoel

Chalmers, Mechanics and Maritime Sciences (M2), Vehicle Engineering and Autonomous Systems

Volvo Group

Krister Wolff

Chalmers, Mechanics and Maritime Sciences (M2), Vehicle Engineering and Autonomous Systems

Leo Laine

Chalmers, Mechanics and Maritime Sciences (M2)

Volvo Group

IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC

Vol. 2018-November 2148-2155 8569568
978-172810323-5 (ISBN)

21st IEEE International Conference on Intelligent Transportation Systems (ITSC)
Maui, Hawaii, USA,

Areas of Advance

Information and Communication Technology

Transport

Driving Forces

Sustainable development

Innovation and entrepreneurship

Subject Categories

Computer and Information Science

Computer Science

Roots

Basic sciences

DOI

10.1109/ITSC.2018.8569568

More information

Latest update

7/17/2024