Using Semantic Information to Improve Generalization of Reinforcement Learning Policies for Autonomous Driving

Florence Carton, David Filliat, Jaonary Rabarisoa, Quoc Cuong Pham

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The problem of generalization of reinforcement learning policies to new environments is seldom addressed but essential in practical applications. We focus on this problem in an autonomous driving context using the CARLA simulator and first show that semantic information is the key to a good generalization for this task. We then explore and compare different ways to exploit semantic information at training time in order to improve generalization in an unseen environment without fine-tuning, showing that using semantic segmentation as an auxiliary task is the most efficient approach.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE Winter Conference on Applications of Computer Vision Workshops, WACVW 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages144-151
Number of pages8
ISBN (Electronic)9781665419673
DOIs
Publication statusPublished - 1 Jan 2021
Externally publishedYes
Event2021 IEEE Winter Conference on Applications of Computer Vision Workshops, WACVW 2021 - Virtual, Waikola, United States
Duration: 5 Jan 20219 Jan 2021

Publication series

NameProceedings - 2021 IEEE Winter Conference on Applications of Computer Vision Workshops, WACVW 2021

Conference

Conference2021 IEEE Winter Conference on Applications of Computer Vision Workshops, WACVW 2021
Country/TerritoryUnited States
CityVirtual, Waikola
Period5/01/219/01/21

Fingerprint

Dive into the research topics of 'Using Semantic Information to Improve Generalization of Reinforcement Learning Policies for Autonomous Driving'. Together they form a unique fingerprint.

Cite this