A real-time, unsupervised neural network for the low-level control of a mobile robot in a nonstationary environment

Abstract This article introduces a real-time, unsupervised neural network that learns to control a two-degree-of-freedom mobile robot in a nonstationary environment. The neural controller, which is termed neural NETwork MObile Robot Controller (NETMORC), combines associative learning and Vector Associative Map (VAM) learning to generate transformations between spatial and velocity coordinates. As a result, the controller learns the wheel velocities required to reach a target at an arbitrary distance and angle. The transformations are learned in an unsupervised training phase, during which the robot moves as a result of randomly selected wheel velocities. The robot learns the relationship between these velocities and the resulting incremental movements. Aside from being able to reach stationary or moving targets, the NETMORC structure also enables the robot to perform successfully in spite of disturbances in the environment, such as wheel slippage, or changes in the robot's plant, including changes in wheel radius, changes in interwheel distance, or changes in the internal time step of the system. Finally, the controller is extended to include a module that learns an internal odometric transformation, allowing the robot to reach targets when visual input is sporadic or unreliable.

[1]  Allen M. Waxman,et al.  Visual learning, adaptive expectations, and behavioral conditioning of the mobile robot MAVIN , 1991, Neural Networks.

[2]  S. Grossberg,et al.  Neural representations for sensory-motor control, I: Head-centered 3-D target positions from opponent eye commands. , 1993, Acta psychologica.

[3]  Emmanuel Mazer,et al.  An approach to sensorimotor relevance , 1992 .

[4]  Stephen Grossberg,et al.  Neural representations for sensory-motor control, II: Learning a head-centered visuomotor representation of 3-D target position , 1993, Neural Networks.

[5]  Bernard Widrow,et al.  Adaptive Signal Processing , 1985 .

[6]  Daniel Bullock,et al.  Neural dynamics of planned arm movements: emergent invariants and speed-accuracy properties during trajectory formation , 1988 .

[7]  Dean Pomerleau,et al.  Efficient Training of Artificial Neural Networks for Autonomous Navigation , 1991, Neural Computation.

[8]  B. Widrow,et al.  Neural networks for self-learning control systems , 1990, IEEE Control Systems Magazine.

[9]  Stephen Grossberg,et al.  Neural dynamics of adaptive sensory-motor control , 1986 .

[10]  MICHAEL KUPERSTEIN,et al.  INFANT neural controller for adaptive sensory-motor coordination , 1991, Neural Networks.

[11]  Hideki Hashimoto,et al.  Visual control of robotic manipulator based on neural networks , 1992, IEEE Trans. Ind. Electron..

[12]  S. Grossberg,et al.  A Self-Organizing Neural Model of Motor Equivalent Reaching and Tool Use by a Multijoint Arm , 1993, Journal of Cognitive Neuroscience.

[13]  S. Grossberg,et al.  Some physiological and biochemical consequences of psychological postulates. , 1968, Proceedings of the National Academy of Sciences of the United States of America.

[14]  Stephen Grossberg,et al.  A self-organizing neural network model for redundant sensory-motor control, motor equivalence, and tool use , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[15]  Richard S. Sutton,et al.  Neural networks for control , 1990 .

[16]  Graham C. Goodwin,et al.  Adaptive filtering prediction and control , 1984 .

[17]  S. Grossberg,et al.  Neural dynamics of planned arm movements: emergent invariants and speed-accuracy properties during trajectory formation. , 1988, Psychological review.

[18]  P.J. Antsaklis,et al.  Parameter learning for performance adaptation , 1990, IEEE Control Systems Magazine.

[19]  S. Grossberg,et al.  Self-Organization of Spatial Representations and Arm Trajectory Controllers by Vector Associative Maps Energized by Cyclic Random Generators , 1991 .

[20]  B. Widrow,et al.  The truck backer-upper: an example of self-learning in neural networks , 1989, International 1989 Joint Conference on Neural Networks.

[21]  Anita M. Flynn,et al.  Mobile robots: inspiration to implementation , 1993 .

[22]  Panos J. Antsaklis,et al.  Neural networks for control systems , 1990, IEEE Trans. Neural Networks.

[23]  Ronald C. Arkin,et al.  Integrating behavioral, perceptual, and world knowledge in reactive navigation , 1990, Robotics Auton. Syst..

[24]  Juan López Coronado,et al.  An Unsupervised Neural Network for Real-Time Low-Level Control of a Mobile Robot: Noise Resistance, Stability, and Hardware Implementation , 1994 .

[25]  Eduardo Zalama Casanova.  Arquitectura neuronal no supervisada para el control de un robot móvil en entornos no estacionarios , 1995 .

[26]  M. Kuperstein,et al.  Implementation of an adaptive neural controller for sensory-motor coordination , 1989, International 1989 Joint Conference on Neural Networks.

[27]  Robert E. Jenkins,et al.  A simplified neural network solution through problem decomposition: the case of the truck backer-upper , 1993, IEEE Trans. Neural Networks.

[28]  L.G. Kraft,et al.  A comparison between CMAC neural network control and two traditional adaptive control systems , 1990, IEEE Control Systems Magazine.

[29]  Mitsuo Kawato,et al.  A neural network model for arm trajectory formation using forward and inverse dynamics models , 1993, Neural Networks.

[30]  S. Grossberg.  Studies of mind and brain : neural principles of learning, perception, development, cognition, and motor control , 1982 .

[31]  Kumpati S. Narendra,et al.  Neural networks in control systems , 1992, [1992] Proceedings of the 31st IEEE Conference on Decision and Control.

[32]  Stephen Grossberg,et al.  Vector associative maps: Unsupervised real-time error-based learning and control of movement trajectories , 1991, Neural Networks.

[33]  Fumio Miyazaki,et al.  A stable tracking control method for an autonomous mobile robot , 1990, Proceedings., IEEE International Conference on Robotics and Automation.

[34]  Ken Goldberg,et al.  Neural Networks in Robotics , 1993 .

[35]  F. Varela,et al.  Toward a Practice of Autonomous Systems: Proceedings of the First European Conference on Artificial Life , 1992 .

[36]  Rodney A. Brooks,et al.  Artificial Life and Real Robots , 1992 .

[37]  José L. Contreras-Vidal,et al.  Navite: A Neural Network System For Sensory-Based Robot Navigation , 1993 .

[38]  Mitsuo Kawato,et al.  Feedback-error-learning neural network for trajectory control of a robotic manipulator , 1988, Neural Networks.

[39]  Juan López Coronado,et al.  An unsupervised neural network for low-level control of a wheeled mobile robot: noise resistance, stability, and hardware implementation , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[40]  James S. Albus,et al.  New Approach to Manipulator Control: The Cerebellar Model Articulation Controller (CMAC)1 , 1975 .

[41]  W. Thomas Miller,et al.  Real-time dynamic control of an industrial manipulator using a neural network-based learning controller , 1990, IEEE Trans. Robotics Autom..

[42]  K. Asakawa,et al.  Mobile robot control by a structured hierarchical neural network , 1990, IEEE Control Systems Magazine.