Kinematic and dynamic adaptive control of a nonholonomic mobile robot using a RNN

In this paper, an adaptive neurocontrol system with two levels is proposed for the motion control of a nonholonomic mobile robot. In the first level, a recurrent network improves the robustness of a kinematic controller and generates linear and angular velocities, necessary to track a reference trajectory. In the second level, another network converts the desired velocities, provided by the first level, into a torque control. The advantage of the control approach is that, no knowledge about the dynamic model is required, and no synaptic weight changing is needed in presence of robot's parameters variation. This capability is acquired through prior 'meta-learning'. Simulation results are demonstrated to validate the robustness of the proposed approach.

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

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

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

[4]  A. D. Back.  Multiple and time-varying dynamic modelling capabilities of recurrent neural networks , 1997, Neural Networks for Signal Processing VII. Proceedings of the 1997 IEEE Signal Processing Society Workshop.

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

[6]  Qiuju Zhang,et al.  Robust backstepping and neural network control of a low-quality nonholonomic mobile robot , 1999 .

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

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

[9]  J. Lo,et al.  Adaptive vs. accommodative neural networks for adaptive system identification , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[10]  Andrew D. Back,et al.  Universal Approximation of Multiple Nonlinear Operators by Neural Networks , 2002, Neural Computation.

[11]  Ju-Jang Lee,et al.  Designing a robust adaptive dynamic controller for nonholonomic mobile robots under modeling uncertainty and disturbances , 2003 .

[12]  James Ting-Ho Lo,et al.  Adaptive vs. accommodative neural networks for adaptive system identification: part II , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[13]  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..

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