Sensor system for development of perception systems for ATO
Abstract Developing AI systems for automatic train operation (ATO) requires developers to have a deep understanding of the human tasks they are trying to replace. This paper fills this gap and translates the regulatory requirements from the context of German railways for the AI developer community....
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Springer
2023-06-01
|
Series: | Discover Artificial Intelligence |
Subjects: | |
Online Access: | https://doi.org/10.1007/s44163-023-00066-4 |
_version_ | 1797806611235864576 |
---|---|
author | Rustam Tagiew Dirk Leinhos Henrik von der Haar Christian Klotz Dennis Sprute Jens Ziehn Andreas Schmelter Stefan Witte Pavel Klasek |
author_facet | Rustam Tagiew Dirk Leinhos Henrik von der Haar Christian Klotz Dennis Sprute Jens Ziehn Andreas Schmelter Stefan Witte Pavel Klasek |
author_sort | Rustam Tagiew |
collection | DOAJ |
description | Abstract Developing AI systems for automatic train operation (ATO) requires developers to have a deep understanding of the human tasks they are trying to replace. This paper fills this gap and translates the regulatory requirements from the context of German railways for the AI developer community. As a result, tasks such as train’s path monitoring for collision prediction, signal detection, door operation, etc. are identified. Based on this analysis, a functionally justified sensor setup with detailed configuration requirements is presented. This setup was also evaluated by a survey within the railway industry. The evaluated sensors include RGB/IR cameras, LIDARs, radars and ultrasonic sensors. Calculations and estimates for the evaluated sensors are presented graphically and included in this paper. However, the ultimate sensor setup is still a subject of research. The results of this paper also address the lack of training and test datasets for railway AI systems. It is proposed to acquire research datasets that will allow the training of domain adaptation algorithms to transform other datasets, thus increasing the number of available datasets. The sensor setup is also recommended for such research datasets. |
first_indexed | 2024-03-13T06:09:53Z |
format | Article |
id | doaj.art-e69afdb32696430384db33a905f8f0c0 |
institution | Directory Open Access Journal |
issn | 2731-0809 |
language | English |
last_indexed | 2024-03-13T06:09:53Z |
publishDate | 2023-06-01 |
publisher | Springer |
record_format | Article |
series | Discover Artificial Intelligence |
spelling | doaj.art-e69afdb32696430384db33a905f8f0c02023-06-11T11:20:15ZengSpringerDiscover Artificial Intelligence2731-08092023-06-013112410.1007/s44163-023-00066-4Sensor system for development of perception systems for ATORustam Tagiew0Dirk Leinhos1Henrik von der Haar2Christian Klotz3Dennis Sprute4Jens Ziehn5Andreas Schmelter6Stefan Witte7Pavel Klasek8German Centre for Rail Traffic Research at Federal Railway AuthorityDB Systemtechnik GmbHDB Systemtechnik GmbHGerman Centre for Rail Traffic Research at Federal Railway AuthorityFraunhofer IOSBFraunhofer IOSBTechnische Hochschule OWLTechnische Hochschule OWLGerman Centre for Rail Traffic Research at Federal Railway AuthorityAbstract Developing AI systems for automatic train operation (ATO) requires developers to have a deep understanding of the human tasks they are trying to replace. This paper fills this gap and translates the regulatory requirements from the context of German railways for the AI developer community. As a result, tasks such as train’s path monitoring for collision prediction, signal detection, door operation, etc. are identified. Based on this analysis, a functionally justified sensor setup with detailed configuration requirements is presented. This setup was also evaluated by a survey within the railway industry. The evaluated sensors include RGB/IR cameras, LIDARs, radars and ultrasonic sensors. Calculations and estimates for the evaluated sensors are presented graphically and included in this paper. However, the ultimate sensor setup is still a subject of research. The results of this paper also address the lack of training and test datasets for railway AI systems. It is proposed to acquire research datasets that will allow the training of domain adaptation algorithms to transform other datasets, thus increasing the number of available datasets. The sensor setup is also recommended for such research datasets.https://doi.org/10.1007/s44163-023-00066-4Automatic train operationATOGoA3GoA4PerceptionAI |
spellingShingle | Rustam Tagiew Dirk Leinhos Henrik von der Haar Christian Klotz Dennis Sprute Jens Ziehn Andreas Schmelter Stefan Witte Pavel Klasek Sensor system for development of perception systems for ATO Discover Artificial Intelligence Automatic train operation ATO GoA3 GoA4 Perception AI |
title | Sensor system for development of perception systems for ATO |
title_full | Sensor system for development of perception systems for ATO |
title_fullStr | Sensor system for development of perception systems for ATO |
title_full_unstemmed | Sensor system for development of perception systems for ATO |
title_short | Sensor system for development of perception systems for ATO |
title_sort | sensor system for development of perception systems for ato |
topic | Automatic train operation ATO GoA3 GoA4 Perception AI |
url | https://doi.org/10.1007/s44163-023-00066-4 |
work_keys_str_mv | AT rustamtagiew sensorsystemfordevelopmentofperceptionsystemsforato AT dirkleinhos sensorsystemfordevelopmentofperceptionsystemsforato AT henrikvonderhaar sensorsystemfordevelopmentofperceptionsystemsforato AT christianklotz sensorsystemfordevelopmentofperceptionsystemsforato AT dennissprute sensorsystemfordevelopmentofperceptionsystemsforato AT jensziehn sensorsystemfordevelopmentofperceptionsystemsforato AT andreasschmelter sensorsystemfordevelopmentofperceptionsystemsforato AT stefanwitte sensorsystemfordevelopmentofperceptionsystemsforato AT pavelklasek sensorsystemfordevelopmentofperceptionsystemsforato |