Discrete model-based adaptive critic designs in wheeled mobile robot control

Authors:
Zenon Hendzel;Marcin Szuster
Affiliations:
Rzeszów University of Technology, Department of Applied Mechanics and Robotics, Rzeszów, Poland;Rzeszów University of Technology, Department of Applied Mechanics and Robotics, Rzeszów, Poland
Venue:
ICAISC'10 Proceedings of the 10th international conference on Artifical intelligence and soft computing: Part II
Year:
2010

Citing 5
Cited 1

Adaptive critic designs: a case study for neurocontrol

Neural Networks
A course in fuzzy systems and control

A course in fuzzy systems and control
Handbook of Learning and Approximate Dynamic Programming (IEEE Press Series on Computational Intelligence)

Handbook of Learning and Approximate Dynamic Programming (IEEE Press Series on Computational Intelligence)
Adaptive actor-critic learning for the control of mobile robots by applying predictive models

Soft Computing - A Fusion of Foundations, Methodologies and Applications
Approximate Dynamic Programming: Solving the Curses of Dimensionality (Wiley Series in Probability and Statistics)

Approximate Dynamic Programming: Solving the Curses of Dimensionality (Wiley Series in Probability and Statistics)

Neural dynamic programming in reactive navigation of wheeled mobile robot

ICAISC'12 Proceedings of the 11th international conference on Artificial Intelligence and Soft Computing - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper a discrete tracking control algorithm for a nonholonomic two-wheeled mobile robot (WMR) is presented. The basis of the control algorithm is an Adaptive Critic Design (ACD) in two model-based configurations: Heuristic Dynamic Programming (HDP) and Dual Heuristic Programming (DHP). In proposed control algorithm Actor-- Critic structure, composed of two neural networks (NN), is supplied by a PD controller and a supervisory term derived from the Lyapunov stability theorem. The control algorithm works on-line and does not require preliminary learning. Verification of the proposed control algorithm was realized on a WMR Pioneer-2DX.