Abstract
In the article a new approach to a reactive navigation of a wheeled mobile robot (WMR), using a neural dynamic programming algorithm (NPD), is presented. A proposed discrete hierarchical control system consists of a trajectory generator and a tracking control system. In the trajectory generator we used a sensor-based approach to path design for the WMR in an unknown 2-D environment with static obstacles. The main part of the navigator is an action dependant heuristic dynamic programming algorithm (ADHDP), that generates control signals used to design a collision-free trajectory, that makes reaching a goal possible. ADHDP is the discrete algorithm of actor-critic architecture, that works on-line and does not require a preliminary learning or a controlled system knowledge. The tracking control system realises the generated trajectory, it consists of dual-heuristic dynamic programming (DHP) structure, PD controller and the supervisory term derived from the Lyapunov stability theorem. Computer simulations have been conducted to illustrate the performance of the algorithm.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Arkin, R.C.: Behavior-Based Robotics. MIT Press, Cambridge (1998)
Bellman, R.: Dynamic Programming. Princeton University Press, New York (1957)
Burghardt, A.: Behavioural Control of Wheeled Minirobot. PAK 11, 26–29 (2004) (in polish)
Giergiel, J., Hendzel, Z., Zylski, W.: Modeling and Control of Wheeled Mobile Robots, WNT, Warsaw (2002) (in polish)
Giergiel, J., Zylski, W.: Description of Motion of a Mobile Robot by Maggie’s Equations. J. of Theoretical and Applied Mechanics 43, 511–521 (2005)
Hendzel, Z., Szuster, M.: Discrete Action Dependant Heuristic Dynamic Programming in Wheeled Mobile Robot Control. Solid State Phenomena 164, 419–424 (2010)
Hendzel, Z., Szuster, M.: Discrete Model-Based Adaptive Critic Designs in Wheeled Mobile Robot Control. In: Rutkowski, L., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2010. LNCS, vol. 6114, pp. 264–271. Springer, Heidelberg (2010)
Hendzel, Z., Szuster, M.: Neural Dynamic Programming in Behavioural Control of Wheeled Mobile Robot. Acta Mechanica et Automatica 5, 28–36 (2011) (in polish)
Maaref, H., Barret, C.: Sensor-based Navigation of a Mobile Robot in an Indoor Environment. Robotics and Autonomous Systems 38, 1–18 (2002)
Millan, J.: Reinforcement Learning of Goal-Directed Obstacle-Avoiding Reaction Strategies in an Autonomous Mobile Robot. Robotics and Autonomous Systems 15, 275–299 (1995)
Powell, W.B.: Approximate Dynamic Programming: Solving the Curses of Dimensionality. Willey-Interscience, Princeton (2007)
Prokhorov, D., Wunch, D.: Adaptive Critic Designs. IEEE Transactions on Neural Networks 8, 997–1007 (1997)
Si, J., Barto, A.G., Powell, W.B., Wunsch, D.: Handbook of Learning and Approximate Dynamic Programming. IEEE Press, Wiley-Interscience (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hendzel, Z., Szuster, M. (2012). Neural Dynamic Programming in Reactive Navigation of Wheeled Mobile Robot. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds) Artificial Intelligence and Soft Computing. ICAISC 2012. Lecture Notes in Computer Science(), vol 7268. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-29350-4_54
Download citation
DOI: https://doi.org/10.1007/978-3-642-29350-4_54
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-29349-8
Online ISBN: 978-3-642-29350-4
eBook Packages: Computer ScienceComputer Science (R0)