Multilayer perceptron dual adaptive control for mobile robots

Marvin K. Bugeja, Simon G. Fabri
2007 2007 Mediterranean Conference on Control & Automation  
This paper presents a novel dual adaptive dynamic controller for trajectory tracking of nonholonomic wheeled mobile robots. The controller is developed in discrete-time and the robot's nonlinear dynamic functions are assumed to be unknown. A sigmoidal multilayer perceptron neural network is employed for function approximation, and its weights are estimated stochastically in real-time. In contrast to adaptive certainty equivalence controllers hitherto published for mobile robots, the proposed
more » ... trol law takes into consideration the estimates' uncertainty, thereby leading to improved tracking performance. The proposed method is verified by realistic simulations and Monte Carlo analysis.
doi:10.1109/med.2007.4433902 fatcat:2g57keq5a5asjkqzke4xpph24y