Neural-Adaptive Output Feedback Control of a Class of Transportation Vehicles Based on Wheeled Inverted Pendulum Models

• Published in: IEEE transactions on control systems technology Vol. 20; no. 6; pp. 1583 - 1591
• Main Authors: Li, Zhijun, Yang, Chenguang
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.11.2012; Institute of Electrical and Electronics Engineers
• Subjects: Adaptative systems; Adaptive control; Applied sciences; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Control system synthesis; Control theory. Systems; Exact sciences and technology; Fundamental areas of phenomenology (including applications); neural network (NN); Neural networks; Output feedback; output feedback NN control; Physics; Robot control; Software; Solid dynamics (ballistics, collision, multibody system, stabilization...); Solid mechanics; Vehicle dynamics; wheeled inverted pendulum (WIP); Wheels; Inversed pendulum; Wheel; Human operator; dynamic control; Non linear control; Solid dynamic; Feedback regulation; Control synthesis; output feedback NN control; Neural network; Adaptive control; Linear control; Vehicle dynamics; Modeling; Closed feedback; Neurocontrollers; Uncertain system; Optimal trajectory; wheeled inverted pendulum (WIP); Distributed control; neural network (NN); Output feedback
• ISSN: 1063-6536; 1558-0865
• DOI: 10.1109/TCST.2011.2168224

The wheeled inverted pendulum (WIP) models have been widely applied in the transportation vehicles formed by a mobile wheeled inverted pendulum system with an operator (demonstrated in Fig. 1 ). In this paper, we focus on the study of nonlinear control design for the WIP model-based vehicles, for which accurate dynamics could not be obtained beforehand due to the presence of uncertainties caused by the human operator as well as the vehicle. We develop an output feedback adaptive neural network (NN) control incorporating a linear dynamic compensator to achieve stable dynamic balance and tracking of the desired given trajectories. Comparison simulation studies demonstrate guaranteed tracking performance and stable dynamics balance in the presence of uncertainties and thus verify the efficiency of the developed nonlinear controller.