Safe2Land and SEA

Safe2Land and its never Version SEA (Smart Emergency Assistance) help pilots in case of emergency due to engine-out or pilot's incapacitation. By means of an Emergency Landing Assistance (ELA) functionality we compute trajectories to close landing opportunities suited for the used aircraft type.

Our moving target approach can compute approximately 1 million (!) trajectories in one second one a COTS-tablet PC. Compared to other conventional methods (like trochoid based computations) our algorithm is more then 1000 times faster. Thus, we can provide permanent recalculations of the trajectories in case that the wind changes. The new SEA models the atmospheric conditions and aircraft properties more precisely by using inverse kinematic (or so-called kinematoid) chains with up to 1000 chain elements. When you fly in Flight Level 300 this provides a fine grained vertical resolution of 30 ft (approx. < 10m) where even small atmospheric changes can be considered precisely.

All official airports worldwide are part of the application. Moreover, we also provide a database of Emergency Landing Fields which can save lives when no official airport is within glide range. Combining geodata like satellite images, LiDAR elevation data and open street maps we can create databases of emergency landing fields. This database isn‘t only use full in case of an engine failure but can also prevent or mitigate damage if there is a fire or a medical emergency on board and thus an immediate landing is required. For the identification we mainly use artificial neural networks to improve recognition accuracy even if the resolution of the elevation data  grid is just in a range less then 10 times 10 meter. Here, we use topology-optimized deep artificial neural networks to find appropriate emergency landing sites. Recently, we have finished a database for two german federal states (e.g. North Rhine Westfalia with more than 102.000 emergency landing fields from 300-500 m length suited for small aircrafts).

Due to the high precision of our kinematoid chain approach we are able to support manual as well as autonomous flight control. For manual control we provide a Smart Flight Director (SFD) which is optimized to guide a pilot (or even a laymen) to safely follow the SEA computed emergency trajectory. For SPO-cockpits it could be used to enable flight attendants to take over the control in case of a pilot's incapacitation. It could be used to allow laymen flying an airtaxi. And last but not least, SFD can also be facilitate and improve flight training. 

Beside SFD we have also integrated conventional Autopilots as well as artificial neural network pilots (ANNPs) thats are trained by reinforcement learning. By means of reinforcement learning we could train artificial neural networks that find the best configuration (e.g. flaps setting and even slipping by crossed aileron and rudder) to bring the aircraft in gliding closely to the threshold - even if there are gusty wind conditions. Moreover we also managed to train neural pilots that learnt to fly the aircraft by trial and error (of cause in simulation!).