Adaptive Task Planning for Multi-Robot Smart Warehouse

Abstract

Using autonomous mobile robots is now a necessity for today's large e-commerce warehouses to save time and energy, and to prevent human-based errors. Robotic Mobile Fulfillment System (RMFS) controls these robots as well as all other resources and tasks in a warehouse. There are challenges in the management of an RMFS-based smart warehouse because of the high dynamics in the system. Limited resources such as robots, stations, totes, and item spaces should be managed efficiently after tracking their status continuously. In this study, we propose a centralized task management approach that is adaptive to the system dynamics. We describe a novel task conversion algorithm that generates tasks from a batch of orders and provides a high pile-on value. Then we propose an adaptive heuristic approach to assign generated tasks to robots, considering system dynamics such as the location of robots and pods, utilization of totes, and age of the tasks. To evaluate the proposed algorithms, we perform an extensive set of simulations in a highly realistic environment including robot charging, replenishment process, and path planning algorithms. We show that the proposed task planning approach significantly reduces order completion time even for a high number of stock-keeping units (SKU). It also provides a balanced workload among robots. We analyze the optimal value of order batch size and the effect of important system parameters such as robot count, order count, and SKU. The obtained results shade light on how to design a smart warehouse system with high efficiency.