Neural network-based motion control of an underactuated wheeled inverted pendulum model

Yang, Chenguang; Li, Zhijun; Cui, Rongxin; Xu, Bugong

Abstract

In this paper, automatic motion control is investigated for one of 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 ?a consisting of planar movement of vehicle forward and yaw angular motions, and a nonactuated first order subsystem ?b of pendulum motion. Due to the unknown dynamics of subsystem ?a and the universal approximation ability of neural network (NN), an adaptive NN scheme has been employed for motion control of subsystem ?a. The model reference approach has been used whereas the reference model is optimized by the finite time linear quadratic regulation technique. The pendulum motion in the passive subsystem ?b is indirectly controlled using the dynamic coupling with planar forward motion of subsystem ?a , such that satisfactory tracking of a set pendulum tilt angle can be guaranteed. Rigours theoretic analysis has been established, and simulation studies have been performed to demonstrate the developed method.

Citation

Yang, C., Li, Z., Cui, R., & Xu, B. (2014). Neural network-based motion control of an underactuated wheeled inverted pendulum model. IEEE Transactions on Neural Networks and Learning Systems, 25(11), 2004-2016. https://doi.org/10.1109/TNNLS.2014.2302475

• Journal Article Type: Article
• Acceptance Date: Jan 12, 2014
• Online Publication Date: Mar 11, 2014
• Publication Date: Nov 1, 2014
• Deposit Date: Oct 8, 2019
• Journal: IEEE Transactions on Neural Networks and Learning Systems
• Print ISSN: 2162-237X
• Electronic ISSN: 2162-2388
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 25
• Issue: 11
• Pages: 2004-2016
• DOI: https://doi.org/10.1109/TNNLS.2014.2302475
• Keywords: Vehicle dynamics , Vehicles , Dynamics , Artificial neural networks , Vectors , Wheels , Robots
• Public URL: https://uwe-repository.worktribe.com/output/3596879
• Publisher URL: https://ieeexplore.ieee.org/document/6762995