Control of Cricket System Using LQR Controller Optimized by Particle Swarm Optimization

Abstract

The cricket system, as a strongly coupled, nonlinear and multivariable two dimensional cue system, is a typical representative of unstable and underactuated system. In this paper, the system is analyzed by modeling based on the cricket experimental platform, and while designing the LQR controller, the particle swarm algorithm is introduced to optimize the controller parameters to determine the optimal weight matrix Q in order to solve the difficult problem of controller parameter rectification. The simulation results show that the PSO-LQR can restore the balance of the system in a shorter period of time with enhanced stability compared to a single LQR controller, which exhibits good control performance.

Visual Information Features and Machine Learning for Wushu Arts Tracking

“…Therefore, in GPR, the selection of parameters is a crucial problem. The parameters of different features need further cross-validation to avoid overfitting and underfitting [ 16 – 20 ].…”