Physical Simulation for Multi-agent Multi-machine Tending
This work addresses automation for manufacturing tasks, but it is incremental as it uses a simplistic setup to bridge simulation and real-world deployment.
The paper tackled the problem of workforce shortages in manufacturing by using reinforcement learning to train robots in a simulated environment, then successfully demonstrated similar behavior on a real-world tabletop setup with robots, providing initial insights into deployment challenges.
The manufacturing sector was recently affected by workforce shortages, a problem that automation and robotics can heavily minimize. Simultaneously, reinforcement learning (RL) offers a promising solution where robots can learn through interaction with the environment. In this work, we leveraged a simplistic robotic system to work with RL with "real" data without having to deploy large expensive robots in a manufacturing setting. A real-world tabletop arena was designed with robots that mimic the agents' behavior in the simulation. Despite the difference in dynamics and machine size, the robots were able to depict the same behavior as in the simulation. In addition, those experiments provided an initial understanding of the real deployment challenges.