Forward kinematics is essential in robot control. Its resolution remains a challenge for continuum manipulators because of their inherent flexibility. Learning-based approaches allow obtaining accurate models. However, they suffer from the explosion of the learning database that wears down the manipulator during data collection. This paper proposes an approach that combines the model and learning-based approaches. The learning database is derived from analytical equations to prevent the robot from operating for long periods. The database obtained is handled using Deep Neural Networks (DNNs). The Compact Bionic Handling robot serves as an experimental platform. The comparison with existing approaches gives satisfaction.

The problem of finite-time tracking control for n-link flexible-joint robot manipulators is addressed. An adaptive fuzzy finite-time command-filtered backstepping control scheme is presented to solve the following problems: “explosion of terms” problem, finite-time stabilization of the closed-loop system, and the reduction of computational cost. To this end, new virtual adaptive control signals and new finite-time error compensation mechanism are constructed using inherent properties of robot manipulator systems. Based on the Lyapunov theory, the finite-time stabilization of the closed-loop system is proved. Simulation studies show the effectiveness of the proposed method.

The problem of robust adaptive control of a robotic manipulator subjected to uncertain dynamics and joint space constraints is addressed in this paper. Command filters are used to overcome the time derivatives of virtual control, thus reducing the need for desired trajectory differentiations. A barrier Lyapunov function is used to deal with the joint space constraints. A robust adaptive support vector regression architecture is used to reduce filtering errors, approximation errors and handle dynamic uncertainties. The stability analysis of the closed-loop system using the Lyapunov theory permits to highlight adaptation laws and to prove that all signals of the closed-loop system are bounded. Simulations show the effectiveness of the proposed control strategy.

This study derives a robust adaptive control of electrically driven robot manipulators using a support vector regression (SVR)-based command filtered adaptive backstepping approach. The robot system is supposed to be subject to model uncertainties, neglected dynamics, and external disturbances. The command filtered backstepping algorithm is extended to the case of the robot manipulators. A robust term is added to the common adaptive SVR algorithm, to mitigate the effects of the SVR approximation error in the path tracking performance. The stability analysis of the closed loop system using the Lyapunov theory permits to highlight adaptation laws and to prove that all the signals in the closed loop system are bounded. Simulations show the effectiveness of the proposed control strategy.