JSAI2018

Presentation information

Oral presentation

General Session » [General Session] 13. AI Application

[3Z2] [General Session] 13. AI Application

Thu. Jun 7, 2018 3:50 PM - 5:30 PM Room Z (3F Matsu Take)

座長:井上 中順(東京工業大学)

4:50 PM - 5:10 PM

[3Z2-04] Efficiency of Traffic Flow with Mutual Concessions of Autonomous Cars Using Deep Q-Network

〇Ichitaro Ogawa1, Soichiro Yokoyama1, Toyohasha Yanashita1, Hidenori Kawamura1, Akira Sakatoku2, Tadashi Yanagihara2, Tomohiko Ogishi2, Hideaki Tanaka2 (1. Hokkaido University, 2. KDDI Research Inc.)

Keywords:Deep Q-Network, Multi agent, autonomous driving

In recent years, the development of autonomous operation technology has been actively carried out in a various research institutions and companies. Many experiments are conducted in public road to confirm whether one autonomous car can drive safely. However, autonomous operation with inter-vehicle communication has not been much researched.
In this paper, we implement mutual concessions of autonomous cars with Deep Q-Network (DQN), which is a deep neural network structure used for estimation of Q-value of the Q-learning method.
To verify the effectiveness of mutual concessions, we develop an experiment environment for verification of autonomous operation with radio control (RC) cars.
We implement mutual concessions of autonomous cars at the confluence in the roundabout. DQN is applied for the decision-making mechanism to decide velocity in the roundabout based on the position of others and the status of congestion. As a result of our experiment, we confirmed that the autonomous cars with DQN can realize high transfer efficiency in the roundabout.