Multi-AMR Communication-Computing Resource Joint Allocation Method Based on MAPPO

In recent years, the rapid growth of Industry 4.0 has promoted the intelligent and digital transformation of the manufacturing industry. Traditional means cannot meet the requirements of intelligent factories for low latency and high bandwidth. This paper addresses the scenario of multi-robot collaboration in a factory workshop environment by proposing a resource allocation algorithm based on a Multi-Agent Proximal Policy Optimization (MAPPO) approach, aimed at minimizing overall latency and energy consumption. Simulation results demonstrate that the proposed algorithm exhibits advantages such as fast convergence speed, high robustness, and good stability. Compared to traditional algorithms, this method reduces latency by about 94% and the energy consumption by about 46%.