AUTHOR=Lan Xiangyu , Jin Jie , Liu Haiyan 

TITLE=Towards non-linearly activated ZNN model for constrained manipulator trajectory tracking

JOURNAL=Frontiers in Physics

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/physics/articles/10.3389/fphy.2023.1159212

DOI=10.3389/fphy.2023.1159212

ISSN=2296-424X

ABSTRACT=As a powerful method for time-varying problems solving, the zeroing neural network (ZNN) are widely applied in many practical applications that can be modeled as time-varying linear matrix equations (TVLME). Generally, existing ZNN models solve these TVLME problems in the ideal no noise situation without inequality constraints, and the TVLME with noises and inequality constraints are rarely considered. Therefore, in this paper, a nonlinear activation function (NAF) is designed and a nonlinearly activated ZNN (NAZNN) model is established based on the NAF. Besides, the NAZNN model is also applied to find the exact solutions of constrained TVLME (CTVLME) and completes the constrained robot manipulator trajectory tracking (CRMTT) problems. The convergence and robustness of the proposed NAZNN model is verified theoretically, and simulation results further demonstrate the effectiveness and superiority of the NAZNN  model in dealing with CTVLME and CRMTT problems. In addition, the wheeled robots trajectory tracking fault problem with physical constraints is also analyzed theoretically, and the NAZNN model is applied to the manipulator trajectory tracking fault problem, and the experimental results prove that the NAZNN model also deals with the  manipulator trajectory tracking fault problem effectively. Finally, considering the theoretical practicality, simulation experiments of the proposed NAZNN for the trajectory tracking fault problem of ABB robots with physical constraints are provided, which further verifies the NAZNN model can successfully solve the physically limited robot trajectory tracking fault problems.