DOI

Autonomous driving systems include modules of several levels. Thanks to deep learning architectures at the moment technologies in most of the levels have high accuracy. It is important to notice that currently in autonomous driving systems for many tasks classical methods of supervised learning are no longer applicable. In this paper we are interested in a specific problem, that is to control a car to move along a given reference trajectory using reinforcement learning algorithms. In control theory, this problem is called an optimal control problem for moving along the reference trajectory. Airsim environment is used to simulate a moving car for a fixed period of time without obstacles. The purpose of our research is to determine the best reinforcement learning algorithm for a formulated problem among state-of-the-art algorithms such as DDPG, PPO, SAC, DQN and others. As a result of the conducted training and testing, it was revealed that the best algorithm for this problem is A2C.

Язык оригиналаанглийский
Название основной публикацииMathematical Optimization Theory and Operations Research
Подзаголовок основной публикацииRecent Trends - 21st International Conference, MOTOR 2022, Revised Selected Papers
РедакторыYury Kochetov, Anton Eremeev, Oleg Khamisov, Anna Rettieva
ИздательSpringer Nature
Страницы338-349
Число страниц12
ISBN (печатное издание)9783031162237
DOI
СостояниеОпубликовано - 2022
Событие21st International Conference on Mathematical Optimization Theory and Operations Research , MOTOR 2022 - Petrozavodsk, Российская Федерация
Продолжительность: 2 июл 20226 июл 2022
http://motor2022.krc.karelia.ru/en/section/1

Серия публикаций

НазваниеCommunications in Computer and Information Science
Том1661 CCIS
ISSN (печатное издание)1865-0929
ISSN (электронное издание)1865-0937

конференция

конференция21st International Conference on Mathematical Optimization Theory and Operations Research , MOTOR 2022
Сокращенное названиеMOTOR 2022
Страна/TерриторияРоссийская Федерация
ГородPetrozavodsk
Период2/07/226/07/22
Сайт в сети Internet

    Предметные области Scopus

  • Компьютерные науки (все)
  • Математика (все)

ID: 101415278