On Collaborative Air-Ground Replenishment of Combined UAVs for Live Broadcast

With the availability of Unmanned Air Vehicles (UAVs), low-cost and multi-view drone live broadcasting can present a better live effect for outdoor events. However, small UAVs usually cannot meet the requirements of uninterrupted long-distance live broadcast tasks due to the limitation of its load capacity. In this paper, we focus on the strategy of UAV aerial replenishment with the collaborative air-ground system in order to solve the endurance problem in the marathon drone live broadcast scenario. We adopt reinforcement learning algorithm to optimize the replenishment strategy of the collaborative air-ground system based on the fixed flight path of the Task UAV. Simulation results validate that the reinforcement learning algorithm can greatly reduce the replenishment consumption and ensure the best working status of the Task UAV.