A Risk-Based Decision-Making Process for Autonomous Trains Using POMDP: Case of the Anti-Collision Function
As the railway domain progresses towards autonomy, maintaining safety at levels comparable to human-operated systems is a crucial challenge. Autonomous trains require advanced systems capable of real-time risk assessment and decision-making, a task traditionally managed by human situational awarenes...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10374132/ |
| _version_ | 1797357089204469760 |
|---|---|
| author | Mohammed Chelouati Abderraouf Boussif Julie Beugin El-Miloudi El-Koursi |
| author_facet | Mohammed Chelouati Abderraouf Boussif Julie Beugin El-Miloudi El-Koursi |
| author_sort | Mohammed Chelouati |
| collection | DOAJ |
| description | As the railway domain progresses towards autonomy, maintaining safety at levels comparable to human-operated systems is a crucial challenge. Autonomous trains require advanced systems capable of real-time risk assessment and decision-making, a task traditionally managed by human situational awareness. This paper introduces a novel risk-based decision-making approach for autonomous trains, using Partially Observable Markov Decision Processes (POMDPs) for continuous monitoring and evaluation of environmental collision risks. By consistently maintaining an acceptable risk level through ongoing risk estimation (in terms of occurrence probability and severity degree), the approach supports the decision-making capabilities of the autonomous driving system in autonomous trains, enabling safe and informed decisions despite the uncertainties in the train’s operational state and environmental conditions. The approach’s relevance and effectiveness are illustrated through its application in an anti-collision function for autonomous trains. |
| first_indexed | 2024-03-08T14:38:24Z |
| format | Article |
| id | doaj.art-72775c56bce74e13b6395f9c256bf3f2 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T14:38:24Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-72775c56bce74e13b6395f9c256bf3f22024-01-12T00:02:15ZengIEEEIEEE Access2169-35362024-01-01125630564710.1109/ACCESS.2023.334750010374132A Risk-Based Decision-Making Process for Autonomous Trains Using POMDP: Case of the Anti-Collision FunctionMohammed Chelouati0https://orcid.org/0000-0003-2098-8100Abderraouf Boussif1Julie Beugin2https://orcid.org/0000-0003-1981-1906El-Miloudi El-Koursi3https://orcid.org/0000-0002-1153-1929Technological Research Institute Railenium, Valenciennes, FranceCOSYS-ESTAS, Gustave Eiffel University, Villeneuve d’Ascq, FranceCOSYS-ESTAS, Gustave Eiffel University, Villeneuve d’Ascq, FranceCOSYS-ESTAS, Gustave Eiffel University, Villeneuve d’Ascq, FranceAs the railway domain progresses towards autonomy, maintaining safety at levels comparable to human-operated systems is a crucial challenge. Autonomous trains require advanced systems capable of real-time risk assessment and decision-making, a task traditionally managed by human situational awareness. This paper introduces a novel risk-based decision-making approach for autonomous trains, using Partially Observable Markov Decision Processes (POMDPs) for continuous monitoring and evaluation of environmental collision risks. By consistently maintaining an acceptable risk level through ongoing risk estimation (in terms of occurrence probability and severity degree), the approach supports the decision-making capabilities of the autonomous driving system in autonomous trains, enabling safe and informed decisions despite the uncertainties in the train’s operational state and environmental conditions. The approach’s relevance and effectiveness are illustrated through its application in an anti-collision function for autonomous trains.https://ieeexplore.ieee.org/document/10374132/Autonomous traindynamic risk assessmentMarkov decision processsafety assurance |
| spellingShingle | Mohammed Chelouati Abderraouf Boussif Julie Beugin El-Miloudi El-Koursi A Risk-Based Decision-Making Process for Autonomous Trains Using POMDP: Case of the Anti-Collision Function IEEE Access Autonomous train dynamic risk assessment Markov decision process safety assurance |
| title | A Risk-Based Decision-Making Process for Autonomous Trains Using POMDP: Case of the Anti-Collision Function |
| title_full | A Risk-Based Decision-Making Process for Autonomous Trains Using POMDP: Case of the Anti-Collision Function |
| title_fullStr | A Risk-Based Decision-Making Process for Autonomous Trains Using POMDP: Case of the Anti-Collision Function |
| title_full_unstemmed | A Risk-Based Decision-Making Process for Autonomous Trains Using POMDP: Case of the Anti-Collision Function |
| title_short | A Risk-Based Decision-Making Process for Autonomous Trains Using POMDP: Case of the Anti-Collision Function |
| title_sort | risk based decision making process for autonomous trains using pomdp case of the anti collision function |
| topic | Autonomous train dynamic risk assessment Markov decision process safety assurance |
| url | https://ieeexplore.ieee.org/document/10374132/ |
| work_keys_str_mv | AT mohammedchelouati ariskbaseddecisionmakingprocessforautonomoustrainsusingpomdpcaseoftheanticollisionfunction AT abderraoufboussif ariskbaseddecisionmakingprocessforautonomoustrainsusingpomdpcaseoftheanticollisionfunction AT juliebeugin ariskbaseddecisionmakingprocessforautonomoustrainsusingpomdpcaseoftheanticollisionfunction AT elmiloudielkoursi ariskbaseddecisionmakingprocessforautonomoustrainsusingpomdpcaseoftheanticollisionfunction AT mohammedchelouati riskbaseddecisionmakingprocessforautonomoustrainsusingpomdpcaseoftheanticollisionfunction AT abderraoufboussif riskbaseddecisionmakingprocessforautonomoustrainsusingpomdpcaseoftheanticollisionfunction AT juliebeugin riskbaseddecisionmakingprocessforautonomoustrainsusingpomdpcaseoftheanticollisionfunction AT elmiloudielkoursi riskbaseddecisionmakingprocessforautonomoustrainsusingpomdpcaseoftheanticollisionfunction |