Reinforcement learning compensated coordination control of multiple mobile manipulators for tight cooperation

This study presents a coordinated control method based on reinforcement learning for multiple mobile manipulators when strong constraints and close coupling are involved in the tightly cooperative tasks. The reinforcement learning strategy is specifically designed to deal with the unknown vibrations between the mobile manipulators and the common object. Firstly, the problem is converted into a Markov decision process. Next, the grasping forces of the end-effectors are regarded as the parameters to be optimized, and the system states and learning framework are described based on advantage actor-critic algorithm. Thirdly, an agent is trained through interacting with the environment based on a proposed reward policy. To eliminate joint dynamic errors caused by trajectories tracking, an adaptive controller is designed for each mobile manipulator. For the simulations and experiments, two mobile manipulators are employed for transporting a common plate under various conditions. The results demonstrate that the proposed method has better control effects than well-known controllers. This study combines the advantages of both reinforcement learning and model-based method via a coordinated controller designed with the characteristics of tight cooperation.

Automated summary

This study proposes a coordinated control method based on reinforcement learning to address the challenges of strong constraints and close coupling in tightly cooperative tasks involving multiple mobile manipulators. The reinforcement learning strategy is tailored to handle unknown vibrations between the manipulators and the common object. By converting the problem into a Markov decision process, optimizing the grasping forces of the end-effectors, and employing an advantage actor-critic algorithm, the system states and learning framework are described. Simulations and experiments employing two mobile manipulators demonstrate the superior control effects of the proposed method compared to well-known controllers. Overall, this study combines the strengths of reinforcement learning and model-based methods through a coordinated controller designed for tight cooperation.