A neural framework for adaptive robot control

This paper investigates how dynamics in recurrent neural networks can be used to solve some specific mobile robot problems such as motion control and behavior generation. We have designed an adaptive motion control approach based on a novel recurrent neural network, called Echo state networks. The advantage is that no knowledge about the dynamic model is required, and no synaptic weight changing is needed in presence of time varying parameters in the robot. To generate the robot behavior over time, we adopted a biologically inspired approach called neural fields. Due to its dynamical properties, a neural field produces only one localized peak that indicates the optimum movement direction, which navigates a mobile robot to its goal in an unknown environment without any collisions with static or moving obstacles.

[1]  Robert Kozma,et al.  Chaotic neurodynamics for autonomous agents , 2005, IEEE Transactions on Neural Networks.

[2]  Mohamed Oubbati,et al.  Kinematic and dynamic adaptive control of a nonholonomic mobile robot using a RNN , 2005, 2005 International Symposium on Computational Intelligence in Robotics and Automation.

[3]  Gregor Schöner,et al.  Self-calibration based on invariant view recognition: Dynamic approach to navigation , 1997, Robotics Auton. Syst..

[4]  Raffaello D'Andrea,et al.  Near-optimal dynamic trajectory generation and control of an omnidirectional vehicle , 2004, Robotics Auton. Syst..

[5]  Michael Schanz,et al.  Velocity Control of an Omnidirectional RoboCup Player with Recurrent Neural Networks , 2005, RoboCup.

[6]  Herbert Jaeger,et al.  A tutorial on training recurrent neural networks , covering BPPT , RTRL , EKF and the " echo state network " approach - Semantic Scholar , 2005 .

[7]  Kwang Y. Lee,et al.  Diagonal recurrent neural networks for dynamic systems control , 1995, IEEE Trans. Neural Networks.

[8]  Ilya Kolmanovsky,et al.  Developments in nonholonomic control problems , 1995 .

[9]  Les E. Atlas,et al.  Recurrent neural networks and robust time series prediction , 1994, IEEE Trans. Neural Networks.

[10]  P. Levi,et al.  Meta-Learning for Adaptive Identification of Non-Linear Dynamical Systems , 2005, Proceedings of the 2005 IEEE International Symposium on, Mediterrean Conference on Control and Automation Intelligent Control, 2005..

[11]  S. Amari,et al.  Existence and stability of local excitations in homogeneous neural fields , 1979, Journal of mathematical biology.

[12]  S. Amari.  Dynamics of pattern formation in lateral-inhibition type neural fields , 1977, Biological Cybernetics.

[13]  Yoram Koren,et al.  Potential field methods and their inherent limitations for mobile robot navigation , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[14]  Elias S. Manolakos,et al.  Using recurrent neural networks for adaptive communication channel equalization , 1994, IEEE Trans. Neural Networks.

[15]  O. Khatib,et al.  Real-Time Obstacle Avoidance for Manipulators and Mobile Robots , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[16]  Gregor Schöner,et al.  Dynamics of behavior: Theory and applications for autonomous robot architectures , 1995, Robotics Auton. Syst..

[17]  Lee A. Feldkamp,et al.  Adaptation from fixed weight dynamic networks , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[18]  Quanmin Zhu,et al.  Stable adaptive neurocontrol for nonlinear discrete-time systems , 2004, IEEE Trans. Neural Networks.

[19]  Norihiko Adachi,et al.  Adaptive tracking control of a nonholonomic mobile robot , 2000, IEEE Trans. Robotics Autom..

[20]  P J Webros.  BACKPROPAGATION THROUGH TIME: WHAT IT DOES AND HOW TO DO IT , 1990 .

[21]  S. Goldenstein.  Nonlinear Dynamic Systems for Autonomous Agents Navigation , 2002 .

[22]  W. von Seelen,et al.  Application and optimization of neural field dynamics for driver assistance , 2001, ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585).

[23]  Lee A. Feldkamp,et al.  Fixed-weight controller for multiple systems , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[24]  Martin A. Giese.  Neural field model for the recognition of biological motion patterns , 2000 .

[25]  Brian Yamauchi.  Dynamical Neural Networks for Mobile Robot Control , 1993 .

[26]  Frank L. Lewis,et al.  Control of a nonholonomic mobile robot using neural networks , 1998, IEEE Trans. Neural Networks.

[27]  Jürgen Schmidhuber,et al.  A Fixed Size Storage O(n3) Time Complexity Learning Algorithm for Fully Recurrent Continually Running Networks , 1992, Neural Computation.

[28]  Günther Palm,et al.  Neural Fields for Controlling Formation of Multiple Robots , 2007, 2007 International Symposium on Computational Intelligence in Robotics and Automation.

[29]  Jürgen Schmidhuber,et al.  Kalman filters improve LSTM network performance in problems unsolvable by traditional recurrent nets , 2003, Neural Networks.

[30]  A. Steinhage,et al.  The dynamic approach to autonomous robot navigation , 1997, ISIE '97 Proceeding of the IEEE International Symposium on Industrial Electronics.

[31]  Michael Schanz,et al.  NEURAL FIELDS FOR BEHAVIOR-BASED CONTROL OF MOBILE ROBOTS , 2006 .

[32]  Peter R. Conwell,et al.  Fixed-weight networks can learn , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[33]  Ricardo Vilalta,et al.  A Perspective View and Survey of Meta-Learning , 2002, Artificial Intelligence Review.

[34]  A. Steven Younger,et al.  Fixed-weight on-line learning , 1999, IEEE Trans. Neural Networks.

[35]  Frank Joublin,et al.  A Neural Field Approach to Robot Motion , 1998 .

[36]  Weiliang Xu,et al.  Tracking control of uncertain dynamic nonholonomic system and its application to wheeled mobile robots , 2000, IEEE Trans. Robotics Autom..

[37]  Sergio Monteiro,et al.  A dynamical systems approach to behavior-based formation control , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[38]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[39]  Werner von Seelen,et al.  Complex behavior by means of dynamical systems for an anthropomorphic robot , 1999, Neural Networks.

[40]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[41]  Estela Bicho,et al.  The dynamic neural field approach to cognitive robotics , 2006, Journal of neural engineering.