Adaptive PSO-LS-wavelet H∞ control for two-wheeled self-balancing scooter

Abstract

The current study is concerned with adaptive Particle Swarm Optimization Least Square Wavelet H∞ for a two-wheel self-balancing scooter that provides a platform in order to balance itself and transport the driver in accordance to its natural lean. In order to keep the rider close to the upright position over smooth and non-smooth surfaces, providing a stable control system is the main challenge for the aforementioned vehicle. For this purpose, H∞ is combined with adaptive algorithm, Least Square Support Vector Machine (LS-SVM) and Particle Swarm Optimization (PSO) to construct the adaptive control. The most important feature of the proposed control strategy is its inherent robustness and ability to handle the nonlinear behavior of the system. Simulations results indicated that the introduced motion control architecture is capable of providing appropriate control actions to achieve both position control and trajectory tracking satisfactorily.