Daedalean and Volocopter conduct autonomy-enabling flight tests using artificial intelligence and computer vision technologies.

Daedalean and Volocopter conducted joint flight tests on Wednesday 27th March 2019 at the airfield in Bruchsal (D) in order to test Daedalean's Visual situational awareness system ("Raven") on board an experimental Volocopter.

The tests demonstrated crucial environmental perception capabilities for visual navigation and collision detection in landing and en-route scenarios, using 3 high definition cameras mounted outside the fuselage of the aircraft, the data from which are fed to the on-board computer vision and artificial intelligence (AI) algorithms.

Daedalean Raven's functions included

1. Navigation without Global Navigation Satellite Systems (GNSS)

2. Identification and assessment of emergency landing areas

3. Detection of non-cooperative collision hazards.

The situational awareness system relies on vision, just as human pilots do under Visual Flight Rules, and while it fuses information from GNSS, Attitude Heading Reference System (AHRS) and cooperative traffic signals (e.g. ADS-B), it is designed to be able to land an aircraft on nothing by vision in emergency situation and to exceed human performance in both normal and abnormal conditions.

During the test scenarios with aborted take-off and various en-route flights, crucial performance objectives were met with respect to flight trajectory reconstruction, semantic terrain understanding and collision hazard detection.

Large scale deployment of the Volocopter in high density airspace will require advanced autonomous capabilities. With these tests Daedalean demonstrates that they have a clear path towards meeting these requirements. Future tests are planned to further increase safety and robustness of Raven during relevant air taxi scenarios in order that the Daedalean's visual situational awareness system can be integrated into the control loop of Volocopter.