Evolution of Computer Vision Subsystems in Robot Navigation and Image Classification Tasks

Real-time decision making based on visual sensory information is a demanding task for mobile robots. Learning on high-dimensional, highly redundant image data imposes a real problem for most learning algorithms, especially those being based on neural networks. In this paper we investigate the utilization of evolutionary techniques in combination with supervised learning of feedforward nets to automatically construct and improve suitable, task-dependent preprocessing layers helping to reduce the complexity of the original learning problem. Given a number of basic, parameterized low-level computer vision algorithms, the proposed evolutionary algorithm automatically selects and appropriately sets up the parameters of exactly those operators best suited for the imposed supervised learning problem.

[1]  W. Krzanowski.  Selection of Variables to Preserve Multivariate Data Structure, Using Principal Components , 1987 .

[2]  Bruce A. Draper,et al.  Learning 3D object recognition strategies , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[3]  Stephen M. Smith,et al.  A New Class of Corner Finder , 1992, BMVC.

[4]  Lutz Priese,et al.  Traffic Sign Recognition Based On Color Image Evaluationion , 1993, Proceedings of the Intelligent Vehicles '93 Symposium.

[5]  Heinrich Braun,et al.  Evolving Neural Feedforward Networks , 1993 .

[6]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[7]  Jerzy W. Bala,et al.  Hybrid Learning Using Genetic Algorithms and Decision Trees for Pattern Classification , 1995, IJCAI.

[8]  RecognitionBruce A. DraperDept.  Learning Control Strategies for Object Recognition , 1996 .

[9]  H. Braun,et al.  Evolutionary Optimization of Neural Networks for Reinforcement Learning Algorithms , 1997, ICANNGA.

[10]  Tony Belpaeme.  Evolution of Visual Feature Detectors , 1999 .

[11]  Tony Belpaeme.  Evolving Visual Feature Detectors , 1999, ECAL.

[12]  Luc Steels,et al.  AIBO’s first words , 2000 .

[13]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[14]  Hans P. Moravec,et al.  The simulated evolution of robot perception , 2001 .

[15]  Matti Pietikäinen,et al.  Supervised Locally Linear Embedding , 2003, ICANN.

[16]  Erkki Oja,et al.  Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003 , 2003, Lecture Notes in Computer Science.