DeFIX: Detecting and Fixing Failure Scenarios with Reinforcement Learning in Imitation Learning Based Autonomous Driving

Resul Dagdanov, Feyza Eksen, Halil Durmus, Ferhat Yurdakul, Nazim Kemal Ure

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

3 Citations (Scopus)

Abstract

Safely navigating through an urban environment without violating any traffic rules is a crucial performance target for reliable autonomous driving. In this paper, we present a Reinforcement Learning (RL) based methodology to DEtect and FIX (DeFIX) failures of an Imitation Learning (IL) agent by extracting infraction spots and re-constructing mini -scenarios on these infraction areas to train an RL agent for fixing the shortcomings of the IL approach. DeFIX is a continuous learning framework, where extraction of failure scenarios and training of RL agents are executed in an infinite loop. After each new policy is trained and added to the library of policies, a policy classifier method effectively decides on which policy to activate at each step during the evaluation. It is demonstrated that even with only one RL agent trained on failure scenario of an IL agent, DeFIX method is either competitive or does out-perform state-of-the-art IL and RL based autonomous urban driving benchmarks. We trained and validated our approach on the most challenging map (Town05) of CARLA simulator which involves complex, realistic, and adversarial driving scenarios. The source code is publicly available at https://github.com/data-and-decision-lab/DeFIX

Original languageEnglish
Title of host publication2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4215-4220
Number of pages6
ISBN (Electronic)9781665468800
DOIs
Publication statusPublished - 2022
Event25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022 - Macau, China
Duration: 8 Oct 202212 Oct 2022

Publication series

NameIEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
Volume2022-October

Conference

Conference25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022
Country/TerritoryChina
CityMacau
Period8/10/2212/10/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Funding

ACKNOWLEDGMENT This work is supported by Istanbul Technical University BAP Grant NO: MOA-2019-42321. We gratefully thank Eatron Technologies for their technical support. Feyza Eksen thanks the DeepMind scholarship program for their support.

FundersFunder number
Istanbul Teknik ÜniversitesiMOA-2019-42321

    Keywords

    • Autonomous Driving
    • Imitation Learning
    • Reinforcement Learning

    Fingerprint

    Dive into the research topics of 'DeFIX: Detecting and Fixing Failure Scenarios with Reinforcement Learning in Imitation Learning Based Autonomous Driving'. Together they form a unique fingerprint.

    Cite this