Airborne Sense and Detect of Drones using LiDAR and adapted PointPillars DNN (2310.09589v1)

Abstract: The safe operation of drone swarms beyond visual line of sight requires multiple safeguards to mitigate the risk of collision between drones flying in hyper localised scenarios. Cooperative navigation and flight coordination strategies that rely on pre-planned trajectories and require constant network connectivity are brittle to failure. Drone embedded sense and detect offers a comprehensive mode of separation between drones for deconfliction and collision avoidance. This paper presents the first airborne LiDAR based solution for drone-swarm detection and localisation using 3D deep learning. It adapts and embeds the PointPillars deep learning neural network on the drone. To collect training data of close-quarter multi drone operations and safety critical scenarios, a scenario Digital Twin is used to augment real datasets with high fidelity synthetic data. The method has been validated in real-world tests. The trained model achieves over 80% recall and 96% precision when tested on real datasets. By incorporating a detection-by-tracking algorithm the system can reliably monitor the separation distance of multiple drones in challenging environments.