AirLoop: A Simulation Framework for Testing of UAV Services

Sensor fusion is a critical aspect in autonomous drone navigation as several tasks, such object detection and self-pose estimation, require combining information from heterogeneous sources. The performance of these solutions depends on factors, the characteristics sensors environment, well computing platforms, which can heavily impact their accuracy response time. Carrying out evaluations through real flight tests be resource-demanding, time-consuming, and, at times, risky process, why researchers often rely simulation environments for testing validating sensor algorithms. environment should provide photorealistic environmental features, comprehensive set sensors, order to allow test most extensive This paper presents AirLoop, an AirSim-based simulator Hardware-in-the-Loop Software-in-the-Loop algorithm validation. AirLoop extends setup provided by AirSim with FMCW RADAR simulation, has been evaluated based Infineon Technologies BGT60TR13C RADAR. Furthermore, this work provides (SITL) (HITL) demonstrations, including interfacing Pixhawk 2 controller evaluation communication engine NVIDIA Jetson Nano, various use cases, dataset creation, detection, Path Planning, Simultaneous Localization Mapping (SLAM).