DocumentCode :
27326
Title :
Neural Network-Based Motion Control of an Underactuated Wheeled Inverted Pendulum Model
Author :
Chenguang Yang ; Zhijun Li ; Rongxin Cui ; Bugong Xu
Author_Institution :
Sch. of Comput. & Math., Plymouth Univ., Plymouth, UK
Volume :
25
Issue :
11
fYear :
2014
fDate :
Nov. 2014
Firstpage :
2004
Lastpage :
2016
Abstract :
In this paper, automatic motion control is investigated for wheeled inverted pendulum (WIP) models, which have been widely applied for modeling of a large range of two wheeled modern vehicles. First, the underactuated WIP model is decomposed into a fully actuated second-order subsystem Σa consisting of planar movement of vehicle forward motion and yaw angular motions, and a passive (nonactuated) first-order subsystem Σb of pendulum tilt motion. Due to the unknown dynamics of subsystem Σa and universal approximation ability of neural network (NN), an adaptive NN scheme has been employed for motion control of subsystem Σa. Model reference approach has been used, whereas the reference model is optimized by finite time linear quadratic regulation technique. Inspired by human control strategy of inverted pendulum, the tilt angular motion in the passive subsystem Σb has been indirectly controlled using the dynamic coupling with planar forward motion of subsystem Σa, such that the satisfactory tracking of set tilt angle can be guaranteed. Rigorous theoretic analysis has been established, and simulation studies have been performed to demonstrate the developed method.
Keywords :
mobile robots; model reference adaptive control systems; motion control; neurocontrollers; nonlinear control systems; pendulums; vehicles; wheels; adaptive NN scheme; automatic motion control; dynamic coupling; finite time linear quadratic regulation technique; fully actuated second-order subsystem Σa; human control strategy; model reference approach; neural network-based motion control; passive first-order subsystem Σb; pendulum tilt motion; planar forward motion; underactuated WIP model; underactuated wheeled inverted pendulum model; universal approximation ability; vehicle forward motion; wheeled modern vehicles; yaw angular motions; Artificial neural networks; Dynamics; Robots; Vectors; Vehicle dynamics; Vehicles; Wheels; Finite time linear quadratic regulator (LQR); neural network (NN); underactuated; wheeled inverted pendulum (WIP); wheeled inverted pendulum (WIP).;
fLanguage :
English
Journal_Title :
Neural Networks and Learning Systems, IEEE Transactions on
Publisher :
ieee
ISSN :
2162-237X
Type :
jour
DOI :
10.1109/TNNLS.2014.2302475
Filename :
6762995
Link To Document :
بازگشت