Driver Maneuvers Inference Through Machine Learning

Inferring driver maneuvers is a fundamental issue in Advanced Driver Assistance Systems (ADAS), which can significantly increase security and reduce the risk of road accidents. This is not an easy task due to a number of factors such as driver distraction, unpredictable events on the road, and irregularity of the maneuvers. In this complex setting, Machine Learning techniques can play a fundamental and leading role to improve driving security. In this paper, we present preliminary results obtained within the Development Platform for Safe and Efficient Drive (DESERVE) European project. We trained a number of classifiers over a preliminary dataset to infer driver maneuvers of Lane Keeping and Lane Change. These preliminary results are very satisfactory and motivate us to proceed with the application of Machine Learning techniques over the whole dataset.

[1]  Song Gao,et al.  Optimal paths in dynamic networks with dependent random link travel times , 2012 .

[2]  Michael E. Tipping.  Sparse Bayesian Learning and the Relevance Vector Machine , 2001, J. Mach. Learn. Res..

[3]  Mohan M. Trivedi,et al.  Driver classification and driving style recognition using inertial sensors , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[4]  Mohan M. Trivedi,et al.  Predicting driver maneuvers by learning holistic features , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[5]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[6]  Elisa Landini,et al.  Development of cost efficient ADAS tool platform for automotive industry , 2015 .

[7]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[8]  Masayoshi Tomizuka,et al.  An Overview on Study of Identification of Driver Behavior Characteristics for Automotive Control , 2014 .

[9]  Guido Perboli,et al.  A subjective field test on lane departure warning function - euroFOT , 2010 .

[10]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[11]  Hema Swetha Koppula,et al.  Car that Knows Before You Do: Anticipating Maneuvers via Learning Temporal Driving Models , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[12]  Koji Oguri,et al.  Prediction of stopping maneuver considering driver's state , 2006, 2006 IEEE Intelligent Transportation Systems Conference.

[13]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[14]  Oskar von Stryk,et al.  Optimal Control Based Modeling of Vehicle Driver Properties , 2005 .

[15]  Hiren M. Mandalia,et al.  Using Support Vector Machines for Lane-Change Detection , 2005 .

[16]  Mauro Dell'Amico,et al.  A subjective field test on lane departure warning function in the framework of the euroFOT project , 2009, 2009 2nd Conference on Human System Interactions.

[17]  Tomohiro Yamamura,et al.  Lane-Change Detection Using a Computational Driver Model , 2007, Hum. Factors.

[18]  Ioannis Iossifidis,et al.  Towards a Driver Model: Preliminary Study of Lane Change Behavior , 2008, 2008 11th International IEEE Conference on Intelligent Transportation Systems.

[19]  Weifeng Liu,et al.  Multiview Hessian Regularization for Image Annotation , 2013, IEEE Transactions on Image Processing.

[20]  L. Rabiner,et al.  An introduction to hidden Markov models , 1986, IEEE ASSP Magazine.

[21]  Weiping Deng,et al.  A Study on Lane-Change Recognition Using Support Vector Machine , 2013 .