Journal of Advanced Computational Intelligence and Intelligent Informatics
Online ISSN : 1883-8014
Print ISSN : 1343-0130
ISSN-L : 1883-8014
Regular Papers
Imitating with Sequential Masks: Alleviating Causal Confusion in Autonomous Driving
Huanghui ZhangZhi Zheng
Author information
JOURNAL OPEN ACCESS

2024 Volume 28 Issue 4 Pages 882-892

Details
Abstract

Imitation learning which uses only expert demonstrations is suitable for safety-crucial tasks, such as autonomous driving. However, causal confusion is a problem in imitation learning where, with more features offered, an agent may perform even worse. Hence, we aim to augment agents’ imitation ability in driving scenarios under sequential setting, using a novel method we proposed: sequential masking imitation learning (SEMI). Inspired by the idea of Granger causality, we improve the imitator’s performance through a random masking operation on the encoded features in a sequential setting. With this design, the imitator is forced to focus on critical features, leading to a robust model. We demonstrated that this method can alleviate causal confusion in driving simulations by deploying it the CARLA simulator and comparing it with other methods. The experimental results showed that SEMI can effectively reduce confusion during autonomous driving.

Content from these authors

This article cannot obtain the latest cited-by information.

© 2024 Fuji Technology Press Ltd.

This article is licensed under a Creative Commons [Attribution-NoDerivatives 4.0 International] license (https://creativecommons.org/licenses/by-nd/4.0/).
The journal is fully Open Access under Creative Commons licenses and all articles are free to access at JACIII official website.
https://www.fujipress.jp/jaciii/jc-about/#https://creativecommons.org/licenses/by-nd
Previous article Next article
feedback
Top