eduzhai > Applied Sciences > Engineering >

Federated Learning for Cellular-connected UAVs Radio Mapping and Path Planning

  • king
  • (0) Download
  • 20210507
  • Save

... pages left unread,continue reading

Document pages: 6 pages

Abstract: To prolong the lifetime of the unmanned aerial vehicles (UAVs), the UAVs needto fulfill their missions in the shortest possible time. In addition to thisrequirement, in many applications, the UAVs require a reliable internetconnection during their flights. In this paper, we minimize the travel time ofthe UAVs, ensuring that a probabilistic connectivity constraint is satisfied.To solve this problem, we need a global model of the outage probability in theenvironment. Since the UAVs have different missions and fly over differentareas, their collected data carry local information on the network sconnectivity. As a result, the UAVs can not rely on their own experiences tobuild the global model. This issue affects the path planning of the UAVs. Toaddress this concern, we utilize a two-step approach. In the first step, byusing Federated Learning (FL), the UAVs collaboratively build a global model ofthe outage probability in the environment. In the second step, by using theglobal model obtained in the first step and rapidly-exploring random trees(RRTs), we propose an algorithm to optimize UAVs paths. Simulation resultsshow the effectiveness of this two-step approach for UAV networks.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×