A Lightweight, Mobility-Aware, Geospatial & Temporal Data Store for Multi-UAV Systems

Abstract

The meteoric rise in cutting-edge research in the area of cyber-physical systems has made it possible for UAVs to serve as computing infrastructure for processing the data collected from on-board sensors as well as ground-based IoT (Internet of Things) devices. To enable UAVs to perform edge computing tasks on the data received from cameras and other sensors in a near real-time manner, the input data or its associated metadata needs to be stored and processed locally, i.e., on the UAVs themselves. To that end, we present the design of DroneDB - a lightweight data storage engine that can process geospatial and time series data on a multi-UAV system comprising: A) a swarm of UAVs fitted with onboard computers, and B) ground-based fog servers. DroneDB is mobility-aware and has been optimized to perform efficient processing of different possible combinations of spatial and temporal queries, which are typically performed on time series data by real-world applications such as pollution, weather, and traffic monitoring.