Distributed Neural-Network-Based Cooperation Control for Teleoperation of Multiple Mobile Manipulators Under Round-Robin Protocol

Area of Science:

• Robotics
• Control Systems Engineering
• Artificial Intelligence

Background:

• Teleoperation systems with multiple mobile manipulators face challenges like communication bandwidth limitations and time delays.
• Ensuring cooperative control and synchronized object grasping in such systems is complex.

Purpose of the Study:

• To design a distributed cooperative control strategy for sampled-data teleoperation systems with multiple slave mobile manipulators.
• To achieve task-space position synchronization between the master and the grasped object while maintaining a fixed formation.

Main Methods:

• A fully distributed control strategy is proposed, incorporating neural-network-based controllers for synchronization and formation.
• Radial basis function (RBF) neural networks are utilized for adaptive compensation of dynamical uncertainties.
• The Round-Robin (RR) scheduling protocol is employed to manage data transmission from multiple slaves.

Main Results:

• The stability and synchronization/formation features of the single-master-multiple-slaves (SMMS) teleoperation system were analyzed.
• A relationship was established between control parameters, time delay bounds, and the maximum sampling interval.
• Experimental validation confirmed the effectiveness of the proposed control algorithm.

Conclusions:

• The developed distributed control strategy effectively addresses challenges in multi-robot teleoperation.
• The use of RBF neural networks provides robust compensation for system uncertainties.
• The findings offer a framework for stable and synchronized cooperative control in complex teleoperation scenarios.