WaterRescueDrones Project

Support to fire brigade at a wildfire On May 6th we were preparing a flight test at the beach of St.Peter-Ording to collect training data for the onboard AI. What started as a routine flight test day turned into a real emergency scenario soon. Right before takeoff to our first planned flight we got requested to support the local fire brigades at a wildfire at the salt marshes at the south beach. We did 4 flights with over 20min each providing live video feed from our onboard RGB and IR camera into the ground control van helping the operations team on a live situational awareness. Related media relase https://www.ndr.de/nachrichten/schleswig-holstein/Salzwiesenbrand-in-SPO-hinterlaesst-verheerenden-Schaden,regionheidenews2968.html (German) RGB camera IR camera On the ground

 Payload board rework The drone payload board got two 12W LED search lights mounted that can be controlled from ground either via remote control or from camera operator. With this modification the board has an overall weight with all components of 2,57kg. Actual components mounted -  SIYI ZT30  gimbal camera providing RGB and IR videostream (RTSP). -  NavQplus  (i.MX8M-plus) companion computer running MediaMTX for videostreaming and OpenCV for object detection/classification using AI accelerator  (connected via T1 ethernet to drone internal network) - Servo for release mechanism (controlled from flight control) - 2x 12W LED search light ( controlled from flight control) - smartmicro  DRVEGRD ®  152  radar sensor for obstacle detection (connected via T1 ethernet to drone companion)

UWB guided automatic drone landing  UWB guided automatic landing of our HHLA Sky GmbH NXP Auriol ( X25 ) drone. On the drone and ground we use Murata 2BP UWB development boards based on NXP Semiconductors Trimension™ SR150 UWB solution with custom middleware for two way double sided ranging. Landing control is done within PX 4 1.15.2 flight stack running on our MR-VMU-RT1176 flight management unit.