Adaptive hierarchical sliding mode control using an artificial neural network for a ballbot system with uncertainties

Hai Le Xuan, Quoc Dong Hoang, Soon Geul Lee, Dat Pham Xuan, Hoang Tran Viet, Minh Pham Van, Hung Pham Van, Hung Pham Viet, Pham Duc Tuan, Duc Anh Nguyen

Research output: Contribution to journalArticlepeer-review

Abstract

Ballbots, which have been studied for over ten years, are under-actuated mobile robots that operate using the inverted pendulum paradigm. Controlling a ballbot poses a number of challenges, including maintaining the stable upright posture from the ground in all directions and making sure it follows the desired trajectory. External factors such as a minor change in contact surface properties or fabrication errors can affect the system’s stabilization and transfer capabilities. In this study, an adaptive hierarchical sliding mode control algorithm based on an artificial neural network is developed to make the ballbot robust to external factors. The use of the proposed controller ensures system stability despite uncertainties including friction, accidental centrifugal forces and gravity that occur when the ballbot follows the reference trajectory. The system stability is guaranteed on the basis of Lyapunov theory. Control efficiency and robot stability under system uncertainties are demonstrated by numerical simulation.

Original languageEnglish
Pages (from-to)947-958
Number of pages12
JournalJournal of Mechanical Science and Technology
Volume36
Issue number2
DOIs
Publication statusPublished - Feb 2022

Keywords

  • Adaptive hierarchial sliding mode control
  • Artificial neural network
  • Ballbot
  • Under-actuated system

Fingerprint

Dive into the research topics of 'Adaptive hierarchical sliding mode control using an artificial neural network for a ballbot system with uncertainties'. Together they form a unique fingerprint.

Cite this