Automatic driving system using identification of switched systems with unknown switch points

In this paper, we propose a modeling method for evaluating drivers' driving skill, with which automatic driving of a vehicle is realized. The method is to formulate the automatic driving system of a vehicle as a switched system with unknown switch points by using the hinging hyperplane auto regressive eXternal (HHARX) model, which can extract driving operation modes and their switch conditions simultaneously. To verify the effectiveness, we apply the proposed method to an automatic driving system of a small remote-controlled vehicle, instead of a real vehicle. Simulation results illustrate that the obtained models can achieve functions such as start acceleration, normal traveling, stop deceleration and auto steering in the automatic driving system. © 2006 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

[1]  B. Wayne Bequette,et al.  Nonlinear system identification and model reduction using artificial neural networks , 2003, Comput. Chem. Eng..

[2]  Lennart Ljung,et al.  Linear approximations of nonlinear FIR systems for separable input processes , 2005, Autom..

[3]  W. Steven Gray.  Nonlinear system identification - input-output modeling approach, Volumes 1 and 2: R. Haber and L. Keviczky, Kluwer Academic Publishers, Dordrecht, 1999, ISBN: 0-7923-5856-2, 0-7923-5857-0 , 2004, Autom..

[4]  Vedran Bilas,et al.  A system identification approach to the modelling of pulsed eddy-current systems , 2005 .

[5]  Alberto Bemporad,et al.  Identification of piecewise affine systems via mixed-integer programming , 2004, Autom..

[6]  Andy H. Lee,et al.  Using a driving simulator to identify older drivers at inflated risk of motor vehicle crashes. , 2003, Journal of safety research.

[7]  Chong-Ho Choi,et al.  Constructive neural networks with piecewise interpolation capabilities for function approximations , 1994, IEEE Trans. Neural Networks.

[8]  Cristian Ghiaus.  Fault diagnosis of air conditioning systems based on qualitative bond graph , 1999 .

[9]  J. H. Schuppen.  System theory for system identification , 2004 .

[10]  Marian Cichy,et al.  Bond graph model of the IC engine as an element of energetic systems , 2001 .

[11]  Mark Bakker,et al.  Modeling groundwater flow to elliptical lakes and through multi-aquifer elliptical inhomogeneities , 2004 .

[12]  Chang-Soo Han,et al.  Proposition of a modeling method for constrained mechanical systems based on the vector bond graph , 1998 .

[13]  Michel Verhaegen,et al.  Bilinear State Space Systems for Nonlinear Dynamical Modelling , 2000 .

[14]  Hamish A Deery,et al.  Hazard and Risk Perception among Young Novice Drivers , 1999 .

[15]  Ali Keyhani,et al.  System identification approach for modeling and parameter estimation of power system elements , 1995 .

[16]  Manfred Morari,et al.  A clustering technique for the identification of piecewise affine systems , 2001, Autom..

[17]  Otto D Strack,et al.  Principles of the analytic element method , 1999 .