Repository hosted by TU Delft Library

Home · Contact · About · Disclaimer ·

Cut-in Scenario Prediction for Automated Vehicles

Publication files not online:

Author: Remmen, F. · Cara, I. · Gelder, E. de · Willemsen, D.M.C.
Publisher: Institute of Electrical and Electronics Engineers Inc.
Source:2018 IEEE International Conference on Vehicular Electronics and Safety, ICVES 2018, 12 September 2018 through 14 September 2018, 2018 IEEE International Conference on Vehicular Electronics and Safety, ICVES 2018
Identifier: 844207
Article number: 8519594
Keywords: Cut-in · Machine learning · Platooning · Predictive modelling · Adaptive boosting · Artificial intelligence · Decision trees · Forecasting · Learning systems · Safety engineering · Automated vehicles · Ensemble modeling · Logistic regressions · Platooning · Predictive modelling · Scenario predictions · Target vehicles · Traffic efficiency · Vehicles


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 . 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. © 2018 IEEE.