MARL-Based Dual Reward Model on Segmented Actions for Multiple Mobile Robots in Automated Warehouse Environment

Abstract

The simple and labor-intensive tasks of workers on the job site are rapidly becoming digital. In the work environment of logistics warehouses and manufacturing plants, moving goods to a designated place is a typical labor-intensive task for workers. These tasks are rapidly undergoing digital transformation by leveraging mobile robots in automated warehouses. In this paper, we studied and tested realistically necessary conditions to operate mobile robots in an automated warehouse. In particular, considering conditions for operating multiple mobile robots in an automated warehouse, we added more complex actions and various routes and proposed a method for improving sparse reward problems when learning paths in a warehouse with reinforcement learning. Multi-Agent Reinforcement Learning (MARL) experiments were conducted with multiple mobile robots in an automated warehouse simulation environment, and it was confirmed that the proposed reward model method makes learning start earlier even there is a sparse reward problem and learning progress was maintained stably. We expect this study to help us understand the actual operation of mobile robots in an automated warehouse further.

Keywords

• Multi-Agent Reinforcement Learning
• mobile robot
• warehouse environment
• sparse reward
• Reward Shaping