Coupled neural networks for real-time road and obstacle recognition by intelligent road vehicles

Individual neural networks have been developed for specific recognition tasks within a system to be used by an intelligent road vehicle for recognizing traffic situations in real time. A set of networks, designed to cooperate in recognizing the own lane and obstacles on the lane is described. A video camera is used as a sensor. Separate neural networks are employed for different levels of processing and knowledge representation. The algorithms have been implemented on a PC. Results of real-time tests are reported.

[1]  Volker Graefe,et al.  Vision For Intelligent Road Vehicles , 1993, Proceedings of the Intelligent Vehicles '93 Symposium.

[2]  Anthony C. C. Coolen,et al.  A learning mechanism for invariant pattern recognition in neural networks , 1989, Neural Networks.

[3]  A. Guyton,et al.  Human Physiology and Mechanisms of Disease , 1982 .

[4]  Volker Graefe,et al.  An approach to obstacle recognition for autonomous mobile robots , 1990, EEE International Workshop on Intelligent Robots and Systems, Towards a New Frontier of Applications.

[5]  Dean A. Pomerleau.  Neural network-based vision processing for autonomous robot guidance , 1991 .

[6]  Dean A. Pomerleau,et al.  Progress in neural network-based vision for autonomous robot driving , 1992, Proceedings of the Intelligent Vehicles `92 Symposium.

[7]  L. Tsinas,et al.  Object Recognition in Traffic Scenes by Neural Networks , 1992 .

[8]  B. Morcego,et al.  A neural network texture segmentation system for open road vehicle guidance , 1992, Proceedings of the Intelligent Vehicles `92 Symposium.

[9]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[10]  Volker Graefe,et al.  Visual Recognition of Traffic Situations by a Robot Car Driver , 1992, Singapore International Conference on Intelligent Control and Instrumentation [Proceedings 1992].

[11]  Klaus-Dieter Kuhnert,et al.  Real Time Suited Road Border Recognition Utilizing a Neural Network Technique , 1989, Proceedings. IEEE/RSJ International Workshop on Intelligent Robots and Systems '. (IROS '89) 'The Autonomous Mobile Robots and Its Applications.

[12]  Volker Graefe,et al.  Dynamic Vision Systems for Autonomous Mobile Robots , 1989, Proceedings. IEEE/RSJ International Workshop on Intelligent Robots and Systems '. (IROS '89) 'The Autonomous Mobile Robots and Its Applications.