KeepEdge: A Knowledge Distillation Empowered Edge Intelligence Framework for Visual Assisted Positioning in UAV Delivery

The Unmanned Aerial Vehicles (UAVs) delivery service is being increasingly used in logistics. However, it challenging for a UAV to precisely identify the position parcel delivering if only aided by GPS, especially some complex environments with weak signals and high interference. For this issue, we present knowledge distillation empowered edge intelligence architecture, KeepEdge, achieve visual information-assisted positioning services. Specifically, integrate deep neural networks (DNN) into an computing framework enable which empowers UAVs autonomously expected position. Deploying DNN model conducting inference on however, requires performance. To manage trade-off between limited resources onboard high-performance requirements, employ produce lightweight accuracy based full trained cloud. significantly lower complexity less latency of accurate positioning. Comprehensive experiments show that proposed architecture achieves satisfactory performance assisted A real-world case study presented demonstrate effectiveness solution