SZE’s drone research: successful autonomous flights and camera stabilisation tests

In May, the development of a precursor drone at Széchenyi István University reached another important milestone: there were flights with a self-developed autopilot and the collection of camera footage. Video footage of the successful tests is also available.

The project "Development of innovative automotive testing and inspection competences in the West-Hungarian region based on the infrastructure of the Zalaegerszeg Automotive Test Track GINOP-2.3. 4-15-2020-00009", the complex simulation of the precursor drone concept, including hardware elements, was presented last year in the framework of the FT2’s  subproject "Autonomous Near-Earth Aerial Solutions" at Széchenyi István University in cooperation with the Eötvös Loránd University Research Network and The Institute for Computer Science and Control . The development reached the first test of a proprietary on-board system (camera, navigation sensor, image processing computer, gimbal) built on the DJI M600 hexacopter in April 2022. The aim of the first flights was to test the camera stabilisation gimbal and the autopilot of the hexacopter with the extra weight (and possible electronic interference) of the on-board system.

By May 2022, the development had progressed to flights with a self-developed autopilot and camera footage collection.

The in-house autopilot guided the hexacopter with speed, altitude and heading reference signals. To do this, the experts developed autonomous control systems that allow hovering with position holding, climb and descent, turning to heading, approaching the designated coordinate and returning to the initial position. The on-board system is capable of moving the drone along a triangular orbit, stopping at decision points and turning the device in the appropriate direction. The drone is also capable of autonomous continuous motion.

AdArtDronepic1.jpgThe development has reached a new stage.


In all the tests carried out, the autonomous functions worked flawlessly. The emergency stop function, previously developed and tested in a simulation environment, also worked correctly during real environmental tests.

The data required to develop the algorithm for the pre-runner drone vehicle detection was collected by the system passing over the developers' own cars. The captured imagery was used to test the control of the gimbal mounted on the device and the stabilisation of the recording, as well as the vehicle detection algorithm. The gimbal is shown in flight data to maintain a vertical orientation within 2 - up to 3 - degrees, as confirmed by camera footage.

Vehicle detection was also tested on the footage with an algorithm trained in the UNREAL-Carla simulation and on real image databases. The former tends to lose vehicles, while the latter detects them continuously. At the end of the test, the experts even located their colleague from the air using the camera image.

The next step is to test the algorithms in a targeted urban environment, on the ZalaZone test track.

Contributors. Dr Péter Bauer, Dr Antal Hiba, Mihály Nagy, Ádám Kisari, Ernő Simonyi, Gergely Kuna, István Drotár.


H-9026 Győr, Egyetem tér 1. 


(Administration Building 103.)

0036/96/613-700, 0036/503-419

  am pm
Monday  10:00-12:00 12:30-14:00
Tuesday  10:00-12:00 12:30-14:00
Wednesday  10:00-12:00 12:30-14:00
Thursday  10:00-12:00 12:30-14:00
Friday  10:00-11:00 12:30-14:00