Reinforcement Learning-Based Collision Avoidance of a Connected and Automated Vehicle at Merging Roads

Although autonomous driving technology has made significant advancements, autonomous vehicles tend to be defensive in complex environments such as merging roads, intersections, and roundabouts. Connected autonomous vehicles (CAVs) are expected to behave more naturally even in such complex environmen...

Full description

Saved in:
Bibliographic Details
Published in2023 International Workshop on Intelligent Systems (IWIS) pp. 1 - 5
Main Authors Seo, Minseok, Shin, Seongjae, Kim, Kyungjoong, Choi, Kyunghwan
Format Conference Proceeding
LanguageEnglish
Published IEEE 09.08.2023
Subjects
Collision avoidance
Conferences
Connected automated vehicle (CAV)
Current measurement
Merging
merging roads
reinforcement learning
Roads
Training
Weight measurement
Online AccessGet full text

Cover

More Information
Summary:Although autonomous driving technology has made significant advancements, autonomous vehicles tend to be defensive in complex environments such as merging roads, intersections, and roundabouts. Connected autonomous vehicles (CAVs) are expected to behave more naturally even in such complex environments leveraging information obtained through vehicle connectivity, such as neighboring vehicles' position and velocity. This study presents a reinforcement learning-based framework for collision avoidance of a CAV at merging roads. The key idea is to redesign the reward function of previous relevant work so that collision avoidance is realized more in a human-like and predictive manner.
DOI:10.1109/IWIS58789.2023.10284616