Header

UZH-Logo

Maintenance Infos

Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learning


Fuchs, Florian; Song, Yunlong; Kaufmann, Elia; Scaramuzza, Davide; Durr, Peter (2022). Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learning. IEEE Robotics and Automation Letters, 6(3):4257-4264.

Abstract

Autonomous car racing is a major challenge in robotics. It raises fundamental problems for classical approaches such as planning minimum-time trajectories under uncertain dynamics and controlling the car at the limits of its handling. Besides, the requirement of minimizing the lap time, which is a sparse objective, and the difficulty of collecting training data from human experts have also hindered researchers from directly applying learning-based approaches to solve the problem. In the present work, we propose a learning-based system for autonomous car racing by leveraging a high-fidelity physical car simulation, a course-progress proxy reward, and deep reinforcement learning. We deploy our system in Gran Turismo Sport, a world-leading car simulator known for its realistic physics simulation of different race cars and tracks, which is even used to recruit human race car drivers. Our trained policy achieves autonomous racing performance that goes beyond what had been achieved so far by the built-in AI, and at the same time, outperforms the fastest driver in a dataset of over 50,000 human players.

Abstract

Autonomous car racing is a major challenge in robotics. It raises fundamental problems for classical approaches such as planning minimum-time trajectories under uncertain dynamics and controlling the car at the limits of its handling. Besides, the requirement of minimizing the lap time, which is a sparse objective, and the difficulty of collecting training data from human experts have also hindered researchers from directly applying learning-based approaches to solve the problem. In the present work, we propose a learning-based system for autonomous car racing by leveraging a high-fidelity physical car simulation, a course-progress proxy reward, and deep reinforcement learning. We deploy our system in Gran Turismo Sport, a world-leading car simulator known for its realistic physics simulation of different race cars and tracks, which is even used to recruit human race car drivers. Our trained policy achieves autonomous racing performance that goes beyond what had been achieved so far by the built-in AI, and at the same time, outperforms the fastest driver in a dataset of over 50,000 human players.

Statistics

Citations

Dimensions.ai Metrics
31 citations in Web of Science®
38 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

108 downloads since deposited on 17 Feb 2022
12 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Scopus Subject Areas:Physical Sciences > Control and Systems Engineering
Physical Sciences > Biomedical Engineering
Physical Sciences > Human-Computer Interaction
Physical Sciences > Mechanical Engineering
Physical Sciences > Computer Vision and Pattern Recognition
Physical Sciences > Computer Science Applications
Physical Sciences > Control and Optimization
Physical Sciences > Artificial Intelligence
Scope:Discipline-based scholarship (basic research)
Language:English
Date:2022
Deposited On:17 Feb 2022 09:44
Last Modified:27 Apr 2024 01:35
Publisher:Institute of Electrical and Electronics Engineers
ISSN:2377-3766
OA Status:Green
Publisher DOI:https://doi.org/10.1109/LRA.2021.3064284
Other Identification Number:merlin-id:22159
  • Content: Accepted Version