High-Level Sensor Models for the Reinforcement Learning Driving Policy Training
Performance limitations of automotive sensors and the resulting perception errors are one of the most critical limitations in the design of Advanced Driver Assistance Systems and Autonomous Driving Systems. Ability to efficiently recreate realistic error patterns in a traffic simulation setup not on...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-12-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/12/1/71 |
_version_ | 1797625943963992064 |
---|---|
author | Wojciech Turlej |
author_facet | Wojciech Turlej |
author_sort | Wojciech Turlej |
collection | DOAJ |
description | Performance limitations of automotive sensors and the resulting perception errors are one of the most critical limitations in the design of Advanced Driver Assistance Systems and Autonomous Driving Systems. Ability to efficiently recreate realistic error patterns in a traffic simulation setup not only helps to ensure that such systems operate correctly in presence of perception errors, but also fulfills a key role in the training of Machine-Learning-based algorithms often utilized in them. This paper proposes a set of efficient sensor models for detecting road users and static road features. Applicability of the models is presented on an example of Reinforcement-Learning-based driving policy training. Experimental results demonstrate a significant increase in the policy’s robustness to perception errors, alleviating issues caused by the differences between the virtual traffic environment used in the policy’s training and the realistic conditions. |
first_indexed | 2024-03-11T10:03:39Z |
format | Article |
id | doaj.art-1fb56764a8a343c59e927969114d2949 |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-11T10:03:39Z |
publishDate | 2022-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-1fb56764a8a343c59e927969114d29492023-11-16T15:10:43ZengMDPI AGElectronics2079-92922022-12-011217110.3390/electronics12010071High-Level Sensor Models for the Reinforcement Learning Driving Policy TrainingWojciech Turlej0Aptiv Services Poland S.A., Ul. Podgórki Tynieckie 2, 30-399 Cracow, PolandPerformance limitations of automotive sensors and the resulting perception errors are one of the most critical limitations in the design of Advanced Driver Assistance Systems and Autonomous Driving Systems. Ability to efficiently recreate realistic error patterns in a traffic simulation setup not only helps to ensure that such systems operate correctly in presence of perception errors, but also fulfills a key role in the training of Machine-Learning-based algorithms often utilized in them. This paper proposes a set of efficient sensor models for detecting road users and static road features. Applicability of the models is presented on an example of Reinforcement-Learning-based driving policy training. Experimental results demonstrate a significant increase in the policy’s robustness to perception errors, alleviating issues caused by the differences between the virtual traffic environment used in the policy’s training and the realistic conditions.https://www.mdpi.com/2079-9292/12/1/71sensor modelingtraffic simulationreinforcement learningautonomous driving |
spellingShingle | Wojciech Turlej High-Level Sensor Models for the Reinforcement Learning Driving Policy Training Electronics sensor modeling traffic simulation reinforcement learning autonomous driving |
title | High-Level Sensor Models for the Reinforcement Learning Driving Policy Training |
title_full | High-Level Sensor Models for the Reinforcement Learning Driving Policy Training |
title_fullStr | High-Level Sensor Models for the Reinforcement Learning Driving Policy Training |
title_full_unstemmed | High-Level Sensor Models for the Reinforcement Learning Driving Policy Training |
title_short | High-Level Sensor Models for the Reinforcement Learning Driving Policy Training |
title_sort | high level sensor models for the reinforcement learning driving policy training |
topic | sensor modeling traffic simulation reinforcement learning autonomous driving |
url | https://www.mdpi.com/2079-9292/12/1/71 |
work_keys_str_mv | AT wojciechturlej highlevelsensormodelsforthereinforcementlearningdrivingpolicytraining |