Personalized maneuver prediction at intersections

We investigate a new approach towards maneuver prediction that is based on personalization and incremental learning. The prediction accuracy is continuously improved by incorporating only the individual driving history. The study is based on a collection of commuting drivers who recorded their daily routes with a standard smart phone and GPS receiver. Prediction target is the expected maneuver on the next intersection with three classes: stop, turn, or go straight. We show that a personalized prediction based on at least one experience of a certain intersection already improves the prediction performance over an average prediction model trained on all test driver commute routes. This performance gain increases further with more personal training data.

[1]  Mykel J. Kochenderfer,et al.  Imitating driver behavior with generative adversarial networks , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[2]  Geoff Holmes,et al.  Leveraging Bagging for Evolving Data Streams , 2010, ECML/PKDD.

[3]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[4]  Martin Heckmann,et al.  A maximum likelihood method for driver-specific critical-gap estimation , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[5]  Horst-Michael Groß,et al.  Combining behavior and situation information for reliably estimating multiple intentions , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[6]  Ulrich Kressel,et al.  A probabilistic maneuver prediction framework for self-learning vehicles with application to intersections , 2015, 2015 IEEE Intelligent Vehicles Symposium (IV).

[7]  Horst Bischof,et al.  On-line Random Forests , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[8]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[9]  Mohan M. Trivedi,et al.  Tactical driver behavior prediction and intent inference: A review , 2011, 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[10]  Heiko Wersing,et al.  KNN Classifier with Self Adjusting Memory for Heterogeneous Concept Drift , 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

[11]  Senén Barro,et al.  Do we need hundreds of classifiers to solve real world classification problems? , 2014, J. Mach. Learn. Res..

[12]  Hermann Winner,et al.  Predicting the driver's turn intentions at urban intersections using context-based indicators , 2015, 2015 IEEE Intelligent Vehicles Symposium (IV).

[13]  Christoph Stiller,et al.  Velocity-Based Driver Intent Inference at Urban Intersections in the Presence of Preceding Vehicles , 2013, IEEE Intelligent Transportation Systems Magazine.

[14]  Roberta Di Pace,et al.  Development and testing of a fully Adaptive Cruise Control system , 2013 .

[15]  Heiko Wersing,et al.  Choosing the best algorithm for an incremental on-line learning task , 2016, ESANN.

[16]  Vamsi K. Potluru,et al.  Driver prediction to improve interaction with in-vehicle HMI , 2015 .

[17]  Gerhard Fischer,et al.  User Modeling in Human–Computer Interaction , 2001, User Modeling and User-Adapted Interaction.

[18]  Petros A. Ioannou,et al.  Personalized Driver/Vehicle Lane Change Models for ADAS , 2015, IEEE Transactions on Vehicular Technology.

[19]  Francisco Dantas Nobre Neto,et al.  A user-personalized model for real time destination and route prediction , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).