Cut-in scenario prediction for automated vehicles

F. Remmen, Irene Cara, Erwin de Gelder, Dehlia Willemsen

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)
2 Downloads (Pure)

Abstract

Truck platooning is gaining more and more interest thanks to the benefits on improved traffic efficiency, reduced fuel consumption and emissions. To gain these benefits, it typically involves small following distances (0.8 s - 0.3 s). Due to the small following distances, the cut-in manoeuvre of target vehicles becomes safety critical and requires the platooning system to take action as soon as possible. This work shows how machine learning can be used for the prediction of a cut-in manoeuvre of a vehicle, which we refer to as target vehicle, from a host vehicle perspective. A real-life driving experiment was performed to measure several cut-ins that were manually annotated. Measurements are gathered with a lidar installed on the host vehicle and consequently used to train several well-known machine learning algorithms such as Logistic Regression, Random Forest, Support Vector Machine, Adaboost and an Ensemble of the previous models. The Ensemble model achieves the best results. This method is capable of predicting cut-ins prior to their occurrence, with an f 1 score of 62.28 % on the test set. Moreover, over 60% of the cut-ins are correctly predicted more than one second before the corresponding vehicle crosses the lane marker.
Original languageEnglish
Title of host publication2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Pages249-255
Number of pages7
ISBN (Print)978-1-5386-3543-8
DOIs
Publication statusPublished - 12 Sep 2018
Event2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES 2018) - Universidad Carlos III de Madrid - Puerta de Toledo Campus, Madrid, Spain
Duration: 12 Sep 201814 Sep 2018
https://www.icves2018.org/

Conference

Conference2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES 2018)
Abbreviated titleICVES2018
CountrySpain
CityMadrid
Period12/09/1814/09/18
Internet address

Fingerprint

Learning systems
Adaptive boosting
Optical radar
Fuel consumption
Learning algorithms
Trucks
Support vector machines
Logistics
Experiments

Keywords

  • platooning
  • cut-in
  • machine learning
  • predictive modelling

Cite this

Remmen, F., Cara, I., de Gelder, E., & Willemsen, D. (2018). Cut-in scenario prediction for automated vehicles. In 2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES) (pp. 249-255). Piscataway: Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICVES.2018.8519594
Remmen, F. ; Cara, Irene ; de Gelder, Erwin ; Willemsen, Dehlia. / Cut-in scenario prediction for automated vehicles. 2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES) . Piscataway : Institute of Electrical and Electronics Engineers, 2018. pp. 249-255
@inproceedings{05bda2ce4e904b5780d1f075b857fdf7,
title = "Cut-in scenario prediction for automated vehicles",
abstract = "Truck platooning is gaining more and more interest thanks to the benefits on improved traffic efficiency, reduced fuel consumption and emissions. To gain these benefits, it typically involves small following distances (0.8 s - 0.3 s). Due to the small following distances, the cut-in manoeuvre of target vehicles becomes safety critical and requires the platooning system to take action as soon as possible. This work shows how machine learning can be used for the prediction of a cut-in manoeuvre of a vehicle, which we refer to as target vehicle, from a host vehicle perspective. A real-life driving experiment was performed to measure several cut-ins that were manually annotated. Measurements are gathered with a lidar installed on the host vehicle and consequently used to train several well-known machine learning algorithms such as Logistic Regression, Random Forest, Support Vector Machine, Adaboost and an Ensemble of the previous models. The Ensemble model achieves the best results. This method is capable of predicting cut-ins prior to their occurrence, with an f 1 score of 62.28 {\%} on the test set. Moreover, over 60{\%} of the cut-ins are correctly predicted more than one second before the corresponding vehicle crosses the lane marker.",
keywords = "platooning, cut-in, machine learning, predictive modelling",
author = "F. Remmen and Irene Cara and {de Gelder}, Erwin and Dehlia Willemsen",
year = "2018",
month = "9",
day = "12",
doi = "10.1109/ICVES.2018.8519594",
language = "English",
isbn = "978-1-5386-3543-8",
pages = "249--255",
booktitle = "2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)",
publisher = "Institute of Electrical and Electronics Engineers",
address = "United States",

}

Remmen, F, Cara, I, de Gelder, E & Willemsen, D 2018, Cut-in scenario prediction for automated vehicles. in 2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES) . Institute of Electrical and Electronics Engineers, Piscataway, pp. 249-255, 2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES 2018), Madrid, Spain, 12/09/18. https://doi.org/10.1109/ICVES.2018.8519594

Cut-in scenario prediction for automated vehicles. / Remmen, F.; Cara, Irene; de Gelder, Erwin ; Willemsen, Dehlia.

2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES) . Piscataway : Institute of Electrical and Electronics Engineers, 2018. p. 249-255.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Cut-in scenario prediction for automated vehicles

AU - Remmen, F.

AU - Cara, Irene

AU - de Gelder, Erwin

AU - Willemsen, Dehlia

PY - 2018/9/12

Y1 - 2018/9/12

N2 - Truck platooning is gaining more and more interest thanks to the benefits on improved traffic efficiency, reduced fuel consumption and emissions. To gain these benefits, it typically involves small following distances (0.8 s - 0.3 s). Due to the small following distances, the cut-in manoeuvre of target vehicles becomes safety critical and requires the platooning system to take action as soon as possible. This work shows how machine learning can be used for the prediction of a cut-in manoeuvre of a vehicle, which we refer to as target vehicle, from a host vehicle perspective. A real-life driving experiment was performed to measure several cut-ins that were manually annotated. Measurements are gathered with a lidar installed on the host vehicle and consequently used to train several well-known machine learning algorithms such as Logistic Regression, Random Forest, Support Vector Machine, Adaboost and an Ensemble of the previous models. The Ensemble model achieves the best results. This method is capable of predicting cut-ins prior to their occurrence, with an f 1 score of 62.28 % on the test set. Moreover, over 60% of the cut-ins are correctly predicted more than one second before the corresponding vehicle crosses the lane marker.

AB - Truck platooning is gaining more and more interest thanks to the benefits on improved traffic efficiency, reduced fuel consumption and emissions. To gain these benefits, it typically involves small following distances (0.8 s - 0.3 s). Due to the small following distances, the cut-in manoeuvre of target vehicles becomes safety critical and requires the platooning system to take action as soon as possible. This work shows how machine learning can be used for the prediction of a cut-in manoeuvre of a vehicle, which we refer to as target vehicle, from a host vehicle perspective. A real-life driving experiment was performed to measure several cut-ins that were manually annotated. Measurements are gathered with a lidar installed on the host vehicle and consequently used to train several well-known machine learning algorithms such as Logistic Regression, Random Forest, Support Vector Machine, Adaboost and an Ensemble of the previous models. The Ensemble model achieves the best results. This method is capable of predicting cut-ins prior to their occurrence, with an f 1 score of 62.28 % on the test set. Moreover, over 60% of the cut-ins are correctly predicted more than one second before the corresponding vehicle crosses the lane marker.

KW - platooning

KW - cut-in

KW - machine learning

KW - predictive modelling

U2 - 10.1109/ICVES.2018.8519594

DO - 10.1109/ICVES.2018.8519594

M3 - Conference contribution

SN - 978-1-5386-3543-8

SP - 249

EP - 255

BT - 2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

ER -

Remmen F, Cara I, de Gelder E, Willemsen D. Cut-in scenario prediction for automated vehicles. In 2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES) . Piscataway: Institute of Electrical and Electronics Engineers. 2018. p. 249-255 https://doi.org/10.1109/ICVES.2018.8519594