Detection and Risk Analysis with Lane-Changing Decision Algorithms for Autonomous Vehicles
Despite the great technological advances in ADAS, autonomous driving still faces many challenges. Among them is improving decision-making algorithms so that vehicles can make the right decision inspired by human driving. Not only must these decisions ensure the safety of the car occupants and the ot...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-10-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/21/8148 |
_version_ | 1797466554898579456 |
---|---|
author | Amin Mechernene Vincent Judalet Ahmed Chaibet Moussa Boukhnifer |
author_facet | Amin Mechernene Vincent Judalet Ahmed Chaibet Moussa Boukhnifer |
author_sort | Amin Mechernene |
collection | DOAJ |
description | Despite the great technological advances in ADAS, autonomous driving still faces many challenges. Among them is improving decision-making algorithms so that vehicles can make the right decision inspired by human driving. Not only must these decisions ensure the safety of the car occupants and the other road users, but they have to be understandable by them. This article focuses on decision-making algorithms for autonomous vehicles, specifically for lane changing on highways and sub-urban roads. The challenge to overcome is to develop a decision-making algorithm that combines fidelity to human behavior and that is based on machine learning, with a global structure that allows understanding the behavior of the algorithm and that is not opaque such as black box algorithms. To this end, a three-step decision-making method was developed: trajectory prediction of the surrounding vehicles, risk and gain computation associated with the maneuver and based on the predicted trajectories, and finally decision making. For the decision making, three algorithms: decision tree, random forest, and artificial neural network are proposed and compared based on a naturalistic driving database and a driving simulator. |
first_indexed | 2024-03-09T18:41:27Z |
format | Article |
id | doaj.art-cf8fdd29432d4d6a99f988a9ba4554dd |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T18:41:27Z |
publishDate | 2022-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-cf8fdd29432d4d6a99f988a9ba4554dd2023-11-24T06:43:28ZengMDPI AGSensors1424-82202022-10-012221814810.3390/s22218148Detection and Risk Analysis with Lane-Changing Decision Algorithms for Autonomous VehiclesAmin Mechernene0Vincent Judalet1Ahmed Chaibet2Moussa Boukhnifer3ESTACA Engineering School, 12 Rue Paul Delouvrier, 78180 Montigny-le-Bretonneux, FranceESTACA Engineering School, 12 Rue Paul Delouvrier, 78180 Montigny-le-Bretonneux, FranceDRIVE, Université de Bourgogne, 49 rue Mademoiselle Bourgeois, BP 31, CEDEX, 58027 Nevers, FranceUniversité de Lorraine, LCOMS, F-57000 Metz, FranceDespite the great technological advances in ADAS, autonomous driving still faces many challenges. Among them is improving decision-making algorithms so that vehicles can make the right decision inspired by human driving. Not only must these decisions ensure the safety of the car occupants and the other road users, but they have to be understandable by them. This article focuses on decision-making algorithms for autonomous vehicles, specifically for lane changing on highways and sub-urban roads. The challenge to overcome is to develop a decision-making algorithm that combines fidelity to human behavior and that is based on machine learning, with a global structure that allows understanding the behavior of the algorithm and that is not opaque such as black box algorithms. To this end, a three-step decision-making method was developed: trajectory prediction of the surrounding vehicles, risk and gain computation associated with the maneuver and based on the predicted trajectories, and finally decision making. For the decision making, three algorithms: decision tree, random forest, and artificial neural network are proposed and compared based on a naturalistic driving database and a driving simulator.https://www.mdpi.com/1424-8220/22/21/8148risk assessmentdecision makingautonomous drivinglane-changing maneuverdecision treerandom forest |
spellingShingle | Amin Mechernene Vincent Judalet Ahmed Chaibet Moussa Boukhnifer Detection and Risk Analysis with Lane-Changing Decision Algorithms for Autonomous Vehicles Sensors risk assessment decision making autonomous driving lane-changing maneuver decision tree random forest |
title | Detection and Risk Analysis with Lane-Changing Decision Algorithms for Autonomous Vehicles |
title_full | Detection and Risk Analysis with Lane-Changing Decision Algorithms for Autonomous Vehicles |
title_fullStr | Detection and Risk Analysis with Lane-Changing Decision Algorithms for Autonomous Vehicles |
title_full_unstemmed | Detection and Risk Analysis with Lane-Changing Decision Algorithms for Autonomous Vehicles |
title_short | Detection and Risk Analysis with Lane-Changing Decision Algorithms for Autonomous Vehicles |
title_sort | detection and risk analysis with lane changing decision algorithms for autonomous vehicles |
topic | risk assessment decision making autonomous driving lane-changing maneuver decision tree random forest |
url | https://www.mdpi.com/1424-8220/22/21/8148 |
work_keys_str_mv | AT aminmechernene detectionandriskanalysiswithlanechangingdecisionalgorithmsforautonomousvehicles AT vincentjudalet detectionandriskanalysiswithlanechangingdecisionalgorithmsforautonomousvehicles AT ahmedchaibet detectionandriskanalysiswithlanechangingdecisionalgorithmsforautonomousvehicles AT moussaboukhnifer detectionandriskanalysiswithlanechangingdecisionalgorithmsforautonomousvehicles |