Predicting car states through learned models of vehicle dynamics and user behaviours

The ability to predict forthcoming car states is crucial for the development of smart assistance systems. Forthcoming car states do not only depend on vehicle dynamics but also on user behaviour. In this paper, we describe a novel prediction methodology by combining information from both sources - vehicle and user - using Gaussian Processes. We then apply this method in the context of high speed car racing. Results show that the forthcoming position and speed of the car can be predicted with low Root Mean Square Error through the trained model.

[1]  Erwin R. Boer,et al.  Toward an Integrated Model of Driver Behavior in Cognitive Architecture , 2001 .

[2]  Amine Bermak,et al.  Gaussian process for nonstationary time series prediction , 2004, Comput. Stat. Data Anal..

[3]  Michael Brost,et al.  Action Recognition and Prediction for Driver Assistance Systems Using Dynamic Belief Networks , 2002, Agent Technologies, Infrastructures, Tools, and Applications for E-Services.

[4]  T A Ranney,et al.  Models of driving behavior: a review of their evolution. , 1994, Accident; analysis and prevention.

[5]  Evangelos Bekiaris,et al.  ADAS module in driving simulation for training young drivers , 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

[6]  Fumitada Itakura,et al.  Driver identification using driving behavior signals , 2005 .

[7]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[8]  A. Rakotonirainy,et al.  The Need of Intelligent Driver Training Systems for Road Safety , 2008, 2008 19th International Conference on Systems Engineering.

[9]  Carl E. Rasmussen,et al.  Gaussian Processes for Machine Learning (GPML) Toolbox , 2010, J. Mach. Learn. Res..

[10]  Visakan Kadirkamanathan,et al.  Time Series Forecasting Using Multiple Gaussian Process Prior Model , 2007, 2007 IEEE Symposium on Computational Intelligence and Data Mining.

[11]  Dieter Fox,et al.  Gaussian Processes and Reinforcement Learning for Identification and Control of an Autonomous Blimp , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[12]  Y. M. Wang,et al.  Improve driver performance by experience of driver cognitive behavior model's practice , 2009, 2009 IEEE Intelligent Vehicles Symposium.

[13]  A. Murat Tekalp,et al.  Multimodal person recognition for human-vehicle interaction , 2006, IEEE Multimedia.

[14]  Ronald R. Mourant,et al.  A framework for modeling human-like driving behaviors for autonomous vehicles in driving simulators , 2001, AGENTS '01.

[15]  Y. Kishimoto,et al.  A modeling method for predicting driving behavior concerning with driver’s past movements , 2008, 2008 IEEE International Conference on Vehicular Electronics and Safety.

[16]  Weizhong Yan,et al.  Gaussian process for long-term time-series forecasting , 2009, 2009 International Joint Conference on Neural Networks.

[17]  Kazuya Takeda,et al.  Driver identification using driving behavior signals , 2005, Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005..

[18]  Alex Pentland,et al.  Modeling and Prediction of Human Behavior , 1999, Neural Computation.

[19]  Dejan Mitrovic,et al.  Reliable method for driving events recognition , 2005, IEEE Transactions on Intelligent Transportation Systems.

[20]  Alex Pentland,et al.  Driver behavior recognition and prediction in a SmartCar , 2000, Defense, Security, and Sensing.

[21]  Kazuya Takeda,et al.  Driver Modeling Based on Driving Behavior and Its Evaluation in Driver Identification , 2007, Proceedings of the IEEE.