Recurrent neural network based optimal integral sliding mode tracking control for four‐wheel independently driven robots

Abstract

This paper investigates robust path tracking issue of the four-wheel independent driven robot (FWIDR) under time-varying system uncertainties and unavoidable external disturbances. A robust optimal integral sliding mode tracking control (OISMTC) scheme based on double feedback recurrent neural network (DFRNN) is proposed for the FWIDR system. Firstly, the presented OISMTC scheme modifies nominal optimal control part by exploiting an additional integral term to improve the tracking accuracy. Then, the designed DFRNN utilizes a double feedback loops structure to enhance the robustness against large system uncertainties by learning to approximate nonlinear systems. The adaptive law of the DFRNN is presented based on the Lyapunov theory to obtain favourable approximation performance in the presence of the time-varying operating conditions. Moreover, the asymptotic stability of the resultant FWIDR system is guaranteed by mathematical analysis. Finally, practical experiments are conducted to demonstrate the advantages of the proposed DFRNN-OISMTC method.

Design of Super Twisting Integral Sliding Mode Control for Industrial Robot Manipulator

“…The term 𝑑 involves, d=d 1 ‖x‖+d 2 where d 1 ≤∆ 1 besides d 2 ≤∆ 2 Super twisting multivariable control u is given below (6) where k i >0,i=1,2,3,4 are the constant parameters chosen in way that the aforementioned controller would be able to stabilize the MIMO structure in finitetime. Putting 𝑢 as of ( 6) to (5), we can write (7) By specifying 𝜂 = 𝑣 + d 2 , we get (7) (8) State variables finite-time convergence 𝑥, 𝑥̇ as well 𝜂 are to be achieved and keep zero for subsequent time by k 1 , k 2 , k 3 , k 4 . As of eq (8) when states touches origin we get, η=v+d 2 =0…”

“…Putting 𝑢 as of ( 6) to (5), we can write (7) By specifying 𝜂 = 𝑣 + d 2 , we get (7) (8) State variables finite-time convergence 𝑥, 𝑥̇ as well 𝜂 are to be achieved and keep zero for subsequent time by k 1 , k 2 , k 3 , k 4 . As of eq (8) when states touches origin we get, η=v+d 2 =0…”

“…Thereafter, the Lyapunov scheme was introduced for proofs by [6]. From the several SMC approaches, integral SMC [7][8][9][10][11][12][13][14]17], may be readily integrated other new latest control strategies like proportional integral derivative (PID) control, linear feedback control, model predictive control, optimum control and so on, while retaining their features. As a result, ISMC may be described as bridge in between other control methods plus sliding mode which has greater robustness than other existing control systems.…”

Adaptive super-twisting global nonsingular terminal sliding mode control for robotic manipulators

“…Subsequently, it was integrated into second-order SMC approaches, which can enhance the tracking property and robustness of the controlled systems and attenuate chattering phenomena [41,42]. Besides, integral SMC strategies have been utilized to omit the reaching stage [43,44]. However, these methods only guarantee the asymptotic convergence of trajectory tracking errors.…”