Autonomous agents in Industry 4.0 : A self-optimizing approach for automated guided vehicles in Industry 4.0 environments

Abstract: Automated guided vehicles are an integral part of industrial production today. They are moving products to and from shelves in storage warehouses and fetching tools between different workstations in factories. These robots usually follow strict pre-determined paths and are not good at adapting to changes in the environment. Technologies like artificial intelligence and machine learning are currently being implemented in industrial production, a part of what is called Industry 4.0, with the aim of increasing efficiency and automation. Industry 4.0 is also characterized by more connected factory environments, where objects communicate their status, location, and other relevant information to their surroundings. Automated guided vehicles can take advantage of these technologies and can benefit from self-optimizing approaches for better navigation and increased flexibility. Reinforcement learning is used in this project to teach automated guided vehicles to move objects around in an Industry 4.0 warehouse environment. A 10x10 grid world with numerous object destinations, charging stations and agents is created for evaluation purposes. The results show that the agents are able to learn to take efficient routes by balancing the need to finish tasks as fast as possible and recharge their batteries when needed. The agents successfully complete all tasks without running out of battery or colliding with objects in the environment. The result is a demonstration of how reinforcement learning can be applied to automated guided vehicles in Industry 4.0 environments.