A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data

Adrian Remonda*, Nicklas Hansen, Ayoub Raji, Nicola Musiu, Marko Bertogna, Eduardo Enrique Veas, Xiaolong Wang

*Korrespondierende/r Autor/-in für diese Arbeit

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandBegutachtung

Abstract

Despite the availability of international prize-money competitions, scaled vehicles, and simulation environments, research on autonomous racing and the control of sports cars operating close to the limit of handling has been limited by the high costs of vehicle acquisition and management, as well as the limited physics accuracy of open-source simulators. In this paper, we propose a racing simulation platform based on the simulator Assetto Corsa to test, validate, and benchmark autonomous driving algorithms, including reinforcement learning (RL) and classical Model Predictive Control (MPC), in realistic and challenging scenarios. Our contributions include the development of this simulation platform, several state-of-the-art algorithms tailored to the racing environment, and a comprehensive dataset collected from human drivers. Additionally, we evaluate algorithms in the offline RL setting. All the necessary code (including environment and benchmarks), working examples, and datasets are publicly released and can be found https://github.com/dasGringuen/assetto_corsa_gym.
Originalspracheenglisch
Titel38th International Conference On Neural Information Processing Systems NIPS 2024
DOIs
PublikationsstatusAngenommen/In Druck - 12 Dez. 2024
Veranstaltung38th Annual Conference on Neural Information Processing Systems, NeurIPS 2024 - Vancouver Convention Center , Vancouver, Kanada
Dauer: 10 Dez. 202415 Dez. 2024
Konferenznummer: 38

Konferenz

Konferenz38th Annual Conference on Neural Information Processing Systems, NeurIPS 2024
KurztitelThe Thirty-Eighth NeurIPS
Land/GebietKanada
OrtVancouver
Zeitraum10/12/2415/12/24

ASJC Scopus subject areas

  • Artificial intelligence

Fingerprint

Untersuchen Sie die Forschungsthemen von „A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren