Synchronized control with neuro-agents for leader-follower based multiple robotic manipulators

In this paper, a new neural network enhanced synchronized control approach is proposed for multiple robotic manipulators systems (MRMS) based on the leader-follower network communication topology. The justification of introducing two adaptive Radial Basis Function Neural Networks (RBF NN), also called neuro-agents, is to facilitate the whole control system design and analysis. Otherwise such design is impossible with classical analytical procedure. The first agent is the neuro-compensator to accommodate uncertainty associated with the follower manipulators, and the second agent is the neuro-estimator to obtain acceleration of the leader manipulator. Correspondingly the stability analysis of the designed control system is formulated with Lyapunov method. Finally numerical bench tests under various critical conditions are conducted to validate the effectiveness of the proposed approach.