Robot Collaboration in Warehouse

In this work, we consider the problem of robot warehouse systems using Automated Guided Vehicle (AGV). The problem consists of a transportation of multiple items to stations that make request. We use multi-robot systems to collect and deliver those items from their location back to the station with restriction on the limit carrying capacity. The environment is a simulated warehouse consisting of markers as nodes for robots travel. Since finding the optimum solution is an NP-hard problem, the greedy method is utilized. We use the Manhattan distance to approximate the nearest item for each robot and employed Dijkstras algorithm for path planning and obstacle avoidance. Moreover, we use the local search to find nearby target items. We compare two collection strategies, namely the individual collection method that let each robot takes responsibility for its own station and the collaborative collection method that allows robots take nearest items and deliver them to all stations. The performance of both methods has been verified by the simulation using MATLAB. The collaborative collection method is able to surpass the individual collection method with up to 15.4% reduction in maximum traveling cost.