ABSTRACT
For constrained image-based visual servoing (IBVS) of robot manipulators, a model predictive control (MPC) strategy tuned by reinforcement learning (RL) is proposed in this study. First, model predictive control is used to transform the image-based visual servo task into a nonlinear optimization problem while taking system constraints into consideration. In the design of the model predictive controller, a depth-independent visual servo model is presented as the predictive model. Next, a suitable model predictive control objective function weight matrix is trained and obtained by a deep-deterministic-policy-gradient-based (DDPG) RL algorithm. Then, the proposed controller gives the sequential joint signals, so that the robot manipulator can respond to the desired state quickly. Finally, appropriate comparative simulation experiments are developed to illustrate the efficacy and stability of the suggested strategy.
Subject(s)
Robotics , Learning , Algorithms , Computer SimulationABSTRACT
The distributed dissipative state estimation issue of Markov jump genetic regulatory networks subject to round-robin scheduling is investigated in this paper. The system parameters randomly change in the light of a Markov chain. Each node in sensor networks communicates with its neighboring nodes in view of the prescribed network topology graph. The round-robin scheduling is employed to arrange the transmission order to lessen the likelihood of the occurrence of data collisions. The main goal of the work is to design a compatible distributed estimator to assure that the distributed error system is strictly (Λ 1,Λ 2,Λ 3) - γ -stochastically dissipative. By applying the Lyapunov stability theory and a modified matrix decoupling way, sufficient conditions are derived by solving some convex optimization problems. An illustrative example is given to verify the validity of the provided method.
