Cooperative and individual planning strategies for autonomous robots in warehouse parcel transportation

The paper presents a simulation investigation into the individual time of parcel transportation in a multi-agent robot operated warehouse for two different artificial intelligence planning strategies (independent and cooperative), two different warehouse setups and different number of robots operating at the same time.The robots are assumed to operate in a non-communicating manner, and their only physical interactions are the collision detection and avoidance maneuvers.It is additionally assumed, that every robot is aware of its location, is able to compute the shortest path to the required destination and has access to a global orders list from which orders can be reserved and removed.The warehouse setup and robots movement is simulated using a cellular automata paradigm, and the simulation is implemented in Python.It has been shown that the cooperation of robots passing packages to each other significantly improves the overall work time needed to complete the task and reduces the number of empty runs compared to an individual approach..The presented simulation results suggest it is possible to design a multi-robot delivery system in such a way, that robots do not communicate with each other and that no central planning or global optimization center is needed.The novel cooperative planning algorithm brings a contribution in engineering solutions, mainly for robot development in automated warehouses.