We propose a new robotic system using an automated guided vehicle (AGV for order picking in logistics warehouses. In AGV picking systems, AGVs transport the entire shelves including the required items (inventory shelves) or shipping boxes (sorting shelves) to the pickers instead of the pickers moving to the shelves, which improves the productivity of the picking activity in warehouses. In conventional systems, the sorting shelves are fixed or are transported only after the completion of the sorting work of the shelves. Our new system transports the sorting shelf even if the sorting shelf is in the middle of sorting. This system improves the productivity of the picking activity by transporting both shelves to appropriate locations at the appropriate time. To handle the complex transport tasks, the proposed system requires a real-time scheduling method. This study applies a real-time holonic scheduling method to resolve scheduling problems. We evaluated the productivity of the proposed system and that of the conventional method that transports sorting shelves only after finishing the sorting work. The results show that the larger the working area and the higher-mixed and lower-volume the picking orders, the more efficiently the proposed method solves scheduling problems.
Automated guided vehicle (AGV) systems have been widely used in warehouses to improve productivity and reduce costs. For almost every warehouse, order picking is the most costly activity. In an order picking activity, the picker's travel time is the dominant component. To eliminate the travel time, we have developed a picking system in which AGVs transport the entire shelves including the required items to the pickers instead of the pickers moving to the shelves, which improves the efficiency of the picking activities. To minimize the shelf waiting time for the pickers, an intelligent AGV control method such as route planning is required. While there are already some existing approaches using reinforcement learning for this, reinforcement learning often requires hand-engineered low-dimensional state representation, which results in the loss of some state information. In this paper, we present an AGV route planning method for an AGV picking system using deep reinforcement learning. This method uses raw high-dimensional map information as input instead of hand-engineered low-dimensional state representation and it enables the acquisition of a successful AGV route planning policy. We evaluated the validity of the proposed method using an AGV picking system simulator and found that the proposed method outperforms other route planning strategies including our previous method.
We propose a multi-agent simulation environment for logistics warehouses. Simulation is a crucial part of designing industrial systems, such as logistics warehouses. A warehouse is a multi-agent system (MAS) that consists of various autonomous subsystems with robots, material-handling equipment, and human workers. It is generally difficult to analyze the performance of a MAS thus, it is important to model a warehouse and conduct simulations to design and evaluate the possible system configurations. However, the cost of modeling warehouses and modifying the models is high because there are various components and interactions compared to conventional multi-agent simulations. We proposed a self-contained agent architecture and message architecture of a multi-agent simulation environment for logistics warehouses to reduce the simulation-model development and modification costs. We quantitatively evaluated our environment in terms of development costs by comparing such costs of our environment and a widely used multi-agent simulation environment.
This paper presents a method for solving job shop scheduling (JSS) integrated with dynamic and flexible facility layout planning (FLP). The FLP is formulated as a strip packing problem under certain conditions and incorporated into the Giffler and Thompson (GT) algorithm, which is widely used to solve JSS. The makespan of the schedule is minimized by the tabu search algorithm. The performance of the proposed method is evaluated on the benchmark datasets for FLP integrated JSS (FLPIJSS), which are made anew for FLPIJSS. The evaluation results show that the proposed method can solve FLPIJSS efficiently and outperforms the sequential optimization approach of JSS and FLP.
1 January 2019 in Journal of Industrial and Intelligent Information