Multisensor Avionics Architecture for BVLOS Drone Services

Abstract This ADACORSA demonstrator focuses on the implementation of a fail-operational avionics architecture combining Commercial Off-The-Shelf (COTS) elements from automotive, aerospace and artificial intelligence world. A collaborative sensor setup (Time-of-Flight camera FMCW RADAR Infineon Technologies, stereo camera, LiDAR, IMU GPS) allows to test heterogeneous fusion solutions. Tricore Architecture AURIX™ Microcontroller supports execution safety supervision tasks as well data fusion. powerful embedded computer platform (NVIDIA Jetson Nano) accelerates AI algorithms performance processing. Furthermore, an FPGA enables power optimization Artificial Neural Networks. Finally, Pixhawk open-source flight controller ensures stabilization during normal operation provides vision software modules allowing further processing captured, filtered optimized environmental data. paper shows various hardware implementations highlighting their emerging application within BVLOS drone services.