×

Discrete neural dynamic programming in wheeled mobile robot control. (English) Zbl 1221.70043

Summary: We propose a discrete algorithm for a tracking control of a two-wheeled mobile robot (WMR), using an advanced Adaptive Critic Design (ACD). We used Dual-Heuristic Programming (DHP) algorithm, that consists of two parametric structures implemented as Neural Networks (NNs): an actor and a critic, both realized in a form of Random Vector Functional Link (RVFL) NNs. In the proposed algorithm the control system consists of the DHP adaptive critic, a PD controller and a supervisory term, derived from the Lyapunov stability theorem. The supervisory term guaranties a stable realization of a tracking movement in a learning phase of the adaptive critic structure and robustness in face of disturbances. The discrete tracking control algorithm works online, uses the WMR model for a state prediction and does not require a preliminary learning. Verification has been conducted to illustrate the performance of the proposed control algorithm, by a series of experiments on the WMR Pioneer 2-DX.

MSC:

70Q05 Control of mechanical systems
90C39 Dynamic programming
93C85 Automated systems (robots, etc.) in control theory
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Giergiel, M.; Hendzel, Z.; Zylski, W., Modeling and control of wheeled mobile robots (in Polish) (2002), PWN: PWN Warsaw
[2] Ferrari, S.; Stengel, R. F., Model-based adaptive critic design, (Si, J.; Barto, A. G.; Powell, W. B.; Wunsch, D., Handbook of learning and approximate dynamic programming (2004), Willey-IEEE Press: Willey-IEEE Press New York), 65-95
[3] Hendzel, Z., An adaptive critic neural network for motion control of a wheeled mobile robot, Nonlinear Dyn, 50, 849-855 (2007) · Zbl 1170.70316
[4] Hendzel Z, Szuster M. Discrete model-based dual-heuristic programming in wheeled mobile robot control. In: Proceedings of 10th international conference on dynamical systems – theory and applications, Lodz, 2009, p. 745-752.; Hendzel Z, Szuster M. Discrete model-based dual-heuristic programming in wheeled mobile robot control. In: Proceedings of 10th international conference on dynamical systems – theory and applications, Lodz, 2009, p. 745-752.
[5] Hendzel Z, Szuster M. Heuristic dynamic programming in wheeled mobile robot control. In: Proceedings of 14th IFAC international conference on methods and models in automation and robotics, Miedzyzdroje, 2009, p. 37-41.; Hendzel Z, Szuster M. Heuristic dynamic programming in wheeled mobile robot control. In: Proceedings of 14th IFAC international conference on methods and models in automation and robotics, Miedzyzdroje, 2009, p. 37-41. · Zbl 1221.70043
[6] Powell, W. B., Approximate dynamic programming: solving the curses of dimensionality (2007), Willey-Interscience: Willey-Interscience Princeton · Zbl 1156.90021
[7] Prokhorov, D.; Wunch, D. C., Adaptive critic designs, IEEE Trans Neural Net, 8, 997-1007 (1997)
[8] Sutton, R. S.; Barto, A. G., Reinforcement learning: an introduction (1999), Cambridge MIT Press
[9] Syam, R.; Watanabe, K.; Izumi, K., Adaptive actor-critic learning for the control of mobile robots by applying predictive models, Soft Comput, 9, 835-845 (2005) · Zbl 1081.93518
[10] Koshkouei, A. J.; Zinober, A. S., Sliding mode control of discrete-time systems, J Dyn Syst Meas Control, 122, 793-802 (2000)
[11] Giergiel, J.; Zylski, W., Description of motion of a mobile robot by Maggie’s Equations, J Theory Appl Mech, 43, 511-521 (2005)
[12] Spong, M. W.; Vidyasagar, M., Robot modeling and control (in Polish) (1997), WNT: WNT Warsaw
[13] Bellman, R., Dynamic programming (1957), Princeton University Press: Princeton University Press New York · Zbl 0077.13605
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.