A probabilistic maneuver prediction framework for self-learning vehicles with application to intersections

This contribution proposes a novel algorithm for predicting maneuvers at intersections. With applicability to driver assistance systems and autonomous driving, the presented methodology estimates a maneuver probability for every possible direction at an intersection. For this purpose, a generic intersection-feature, space-based representation is defined which combines static and dynamic intersection information with the dynamic properties of the observed vehicle, provided by a tracking module. A statistical behavior model is learned from previously recorded patterns by approximating the resulting feature space. Because the feature space consists of different types of features (mixed-feature space), a Bernoulli-Gaussian Mixture Model is applied as approximating function. Further, an online learning extension is proposed to adapt the model to the characteristics of different intersections.

[1]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[2]  Rüdiger Dillmann,et al.  Learning context sensitive behavior models from observations for predicting traffic situations , 2013, 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013).

[3]  Christoph Stiller,et al.  Driver intent inference at urban intersections using the intelligent driver model , 2012, 2012 IEEE Intelligent Vehicles Symposium.

[4]  Christoph Stiller,et al.  Map-based long term motion prediction for vehicles in traffic environments , 2013, 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013).

[5]  Joachim Börger.  Fahrerintentionserkennung und Kursprädiktion mit erweiterten maschinellen Lernverfahren , 2013 .

[6]  Harri Lähdesmäki,et al.  A unified probabilistic framework for clustering genes from gene expression and protein-protein interaction data , 2009 .

[7]  Klaus C. J. Dietmayer,et al.  The Labeled Multi-Bernoulli Filter , 2014, IEEE Transactions on Signal Processing.

[8]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[9]  Klaus C. J. Dietmayer,et al.  Continuous Driver Intention Recognition with Hidden Markov Models , 2008, 2008 11th International IEEE Conference on Intelligent Transportation Systems.

[10]  Ulrich Kressel,et al.  Probabilistic trajectory prediction with Gaussian mixture models , 2012, 2012 IEEE Intelligent Vehicles Symposium.

[11]  Christoph Hermes,et al.  Long-term vehicle motion prediction , 2009, 2009 IEEE Intelligent Vehicles Symposium.

[12]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[13]  Klaus C. J. Dietmayer,et al.  A sensor independent probabilistic fusion system for driver assistance systems , 2009, 2009 12th International IEEE Conference on Intelligent Transportation Systems.

[14]  Klaus C. J. Dietmayer,et al.  Driver intention inference with vehicle onboard sensors , 2009, 2009 IEEE International Conference on Vehicular Electronics and Safety (ICVES).

[15]  Klaus C. J. Dietmayer,et al.  A learning concept for behavior prediction at intersections , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[16]  Klaus C. J. Dietmayer,et al.  High-performance on-road vehicle detection in monocular images , 2013, 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013).

[17]  Christian Laugier,et al.  Exploiting map information for driver intention estimation at road intersections , 2011, 2011 IEEE Intelligent Vehicles Symposium (IV).

[18]  Stephan Reuter,et al.  Multi-object tracking using random finite sets , 2014 .

[19]  John Q. Gan,et al.  Sequential EM for Unsupervised Adaptive Gaussian Mixture Model Based Classifier , 2009, MLDM.

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

[21]  Mathias Perrollaz,et al.  Learning-based approach for online lane change intention prediction , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[22]  Klaus C. J. Dietmayer,et al.  Multi-object tracking using labeled multi-Bernoulli random finite sets , 2014, 17th International Conference on Information Fusion (FUSION).

[23]  Ronald P. S. Mahler,et al.  Statistical Multisource-Multitarget Information Fusion , 2007 .

[24]  Helge J. Ritter,et al.  Recognition of situation classes at road intersections , 2010, 2010 IEEE International Conference on Robotics and Automation.