A Path Prediction Model based on Multiple Time Series Analysis Tools used to Detect Unintended Lane Departures

In this paper, a path prediction model is presented and used to detect unintended lane departures caused by erroneous driving behaviors. The prediction model is inspired by the concept of a linear vector autoregressive model that is commonly used for multiple time series analysis. The original concept is extended to allow sparse historic sampling, which is shown to reduce the computational complexity while maintaining the predictive performance. A real world data set is used to derive and validate the proposed model, for which the performance is benchmarked against a kinematic model. The results show that the proposed model can improve the true positive rate by 18% and reduce the false-positive rate by 34%, with respect to a constant velocity model and for a prediction horizon of 1.75 s.

[1]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[2]  John Dahl,et al.  Collision Avoidance: A Literature Review on Threat-Assessment Techniques , 2019, IEEE Transactions on Intelligent Vehicles.

[3]  Jing Gao,et al.  Multistep-Ahead Time Series Prediction , 2006, PAKDD.

[4]  Dragan Kukolj,et al.  Predicting Positions and Velocities of Surrounding Vehicles using Deep Neural Networks , 2019, 2019 Zooming Innovation in Consumer Technologies Conference (ZINC).

[5]  Dimitar Filev,et al.  A neural network for predicting unintentional lane departures , 2017, 2017 IEEE International Conference on Industrial Technology (ICIT).

[6]  Dizan Vasquez,et al.  A survey on motion prediction and risk assessment for intelligent vehicles , 2014, ROBOMECH Journal.

[7]  Junqiang Xi,et al.  A Learning-Based Approach for Lane Departure Warning Systems With a Personalized Driver Model , 2017, IEEE Transactions on Vehicular Technology.

[8]  Gerd Wanielik,et al.  Comparison and evaluation of advanced motion models for vehicle tracking , 2008, 2008 11th International Conference on Information Fusion.

[10]  Dimitar Filev,et al.  A support vector machine approach to unintentional vehicle lane departure prediction , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[11]  Helmut Ltkepohl,et al.  New Introduction to Multiple Time Series Analysis , 2007 .

[12]  Amir F. Atiya,et al.  A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition , 2011, Expert Syst. Appl..

[13]  Véronique Berge-Cherfaoui,et al.  Vehicle trajectory prediction based on motion model and maneuver recognition , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[14]  John Dahl,et al.  Automotive Safety: a Neural Network Approach for Lane Departure Detection using Real World Driving Data , 2019, 2019 IEEE Intelligent Transportation Systems Conference (ITSC).

[15]  Mehrdad Dianati,et al.  Implicit Personalization in Driving Assistance: State-of-the-Art and Open Issues , 2020, IEEE Transactions on Intelligent Vehicles.

[16]  Kunsoo Huh,et al.  RNN-Based Path Prediction of Obstacle Vehicles With Deep Ensemble , 2019, IEEE Transactions on Vehicular Technology.