Since helicopters spend almost all of their mission time close to the ground and since landings ‘on the spot’ are the standard procedure for these vehicles, the sense of vision seems especially useful for this type of flight vehicles; landmark navigation using visually prominent geographical structures (single mountains, rivers with special bends, confluence of two rivers) or human made structures like big highways, their junctions, railroad lines, cities and buildings etc. may thus be made available for autonomous landmark navigation also for unmanned small flight devices (figure at left). Landing spots are often marked for human pilots by the capital letter ‘H’; autonomous systems should be able to use these installations as well (see bottom figure).
With increasing computing power becoming available in the 1990’s, S. Werner started investigating dynamic vision for helicopter flight guidance. Due to the specific principles of generating lift, propulsion and control, the dynamic models for helicopter flight are rather involved; hovering helicopters are not stable, usually.
The principles for dynamic vision need not be changed for this application, but the viewing directions have to be much more flexible than for conventional aircraft. The figure shows the landmarks used and tested in HIL-simulation, superimposed with edge features extracted for landmark recognition. A small mission in the vicinity of the airport of Brunswick in northern Germany has been demonstrated in real-time with HIL-simulation in 1997.
Video – HelicopterMissionBsHIL-Sim 1997
Werner S, Buchwieser A, Dickmanns ED (1995). Real-Time Simulation of Visual Machine Perception for Helicopter Flight Assistance. Proc. SPIE – Aero Sense, Orlando, FL
Werner S, Fürst S, Dickmanns D, Dickmanns ED (1996). A vision-based multi-sensor machine perception system for autonomous aircraft landing approach. Enhanced and Synthetic Vision AeroSense ’96, SPIE, Vol. 2736, Orlando, FL, April 1996, pp 54-63
Werner S (1997). Maschinelle Wahrnehmung für den bordautonomen automatischen Hubschrauberflug. Dissertation, UniBwM, LRT. Kurzfassung
Fürst S, Werner S, Dickmanns D, Dickmanns E.D (1997). Landmark navigation and autonomous landing approach with obstacle detection for aircraft. AeroSense ’97, SPIE Proc. Vol. 3088, Orlando FL, pp 94-105.
Fürst S, Werner S, Dickmanns ED (1997). Autonomous Landmark Navigation and Landing Approach with Obstacle Detection for Aircraft. 10th European Aerospace Conference ‘Free Flight’, Amsterdam, NL, pp 36-1 – 36-11
Fürst S., Werner S., Dickmanns D.; Dickmanns E.D. 1997: Landmark Navigation and Autonomous Landing Approach with Obstacle Detection for Aircraft. AGARD MSP Symp. On System Design Considerations for Unmanned Tactical Aircraft (UTA), Athens, Greece, October 7-9, pp 20-1 – 20-11 pdf
Fürst S, Werner S, Dickmanns ED (1998). A single-computer HWIL simulation facility for real-time vision systems. SPIE Proc. Vol. 3368, Technologies for Synthetic Environments: Hardware-in-the-loop Testing III AeroSense ’98, Orlando, FL, pp 13-17