Research On Compliance Control For Robotic Systems Based On Neural Network Impedance Control Methods

As a kind of advanced and efficient operating equipment,robotic manipulators have been widely used in various fields.Since the control tasks have become increasingly complex,the compliance requirements of industrial robots cannot usually be satisfied by the traditional position-based tracking control methods.It has become a challenge problem to effectively improve the compliance under the presence of modeling uncertainties and external disturbances.Based on the impedance control method,this thesis focuses on devloping the position/force tracking control methods of uncertaint rigid-joint robotic manipulator,which can work both in free and in contact with the environment.In general,the uncertainties of robotic system and the overshoot of contact force may cause instability of the control system when the end-effector of the manipulator contacts with the environment.In Chapter 3,by analyzing the principle of positionbased impedance control method,a position/force tracking impedance control scheme is proposed for robotic systems with uncertainties based on adaptive Jacobian and neural network.The proposed controller consists of two parts: the outer-loop force impedance control and the inner-loop position tracking control.In the outer-loop,an improved impedance controller,which combines the traditional impedance relationship with the PID-like scheme,is designed to eliminate the force tracking error quickly and to reduce the force overshoot effectively.In the inner-loop,an adaptive Jacobian method is proposed to estimate the task-space velocities and interaction torques due to the system kinematical uncertainties.The system uncertainties and the uncertain term of adaptive Jacobian are compensated by an adaptive radial basis function neural network(RBFNN).Then,a robust term is designed to compensate the external disturbances and the approximation errors of RBFNN.Based on the Lyapunov stability theorem,it is proved that all the signals in closed-loop system are bounded.Finally,compared with the traditional adaptive impedance control method,the results show that the proposed control scheme demonstrate the better position/force tracking performance.Assumed that the joint velocities of the manipulator are unknown and unmeasured,in Chapter 4,a nonlinear velocity observer is designed to estimate the joint velocities of the manipulator,and the adaptive method is used to compensate the robotic model uncertainties to improve the performance of the observer.Based on Lyapunov stability theorem,the estimation errors can be guaranteed to be globally asymptotically converged to zero.Then,by improving the traditional impedance relationship,the manipulator can work both in free space and in contact space.Based on the estimated joint velocities,an adaptive RBFNN positon/force tracking impedance controller is developed to track the desired contact force of the end-effector and the desired trajectories of the robotic manipulator,where the RBFNN is used to compensate the system uncertainties so that the accuracy of the joint positions and force tracking can be then improved,and a robust term is designed to compensate the external disturbances and the approximation errors of RBFNN.Based on the Lyapunov stability theorem,the stability of the whole closed-loop system is guaranteed.The feasibility of the control scheme is verified by simulation and comparison experiments.In Chapter 5,the motor dynamical model is considered in the motor-driven robotic manipulator system.And the joint velocities of the robotic manipulator are still assumed to be unknown and unmeasured.Then,a neural network adaptive observer is designed to estimate the unknown system states.Considering the relationship between motor voltages and control torques,an adaptive RBFNN impedance control scheme is proposed based on the back-stepping technique,where the RBFNN is used to compensates the robotic model uncertainties and the motor dynamic uncertainties to improve the control performance.Based on the Lyapunov stability theory,the stability of the observer and controller can be guaranteed.Finally,the simulation results show that the feasibility of the proposed control method.