Factory automation system require ultra-reliable and low latency communication.The aim is to deliver control commands from the controller to mobile robots with stringent requirements of latency and reliability.Therefore,for mobile robots work factory system,deep reinforcement learning-based resource scheduling (DRL-RS) algorithm was proposed.There were two-phase communication scheme in DRL-RS algorithm.The robots worked close to each other in a factory environment and formed clusters for reliable device-to-device communications.With the latency requirements,the combined payload of cluster was transmitted to the leader in the first phase.In the second phase,the leader broadcasted the payload to its members.Under this strategy,the deep reinforcement learning was used to allocate resource.The cluster leader in the first phase acted as the Agent and interacted with the environment to optimally select the access point for connection along with the sub-band and power level.The objective was to maximize the successful payload delivery probability to all the robots.Comparative analyses show that the proposed DRL-RS algorithm can offer average successful payload delivery probability close to that of exhaustive search algorithm.