Landing multi-rotor drones smoothly is difficult. Complex turbulence is created by the airflow from each rotor bouncing off the ground during a descent. This turbulence is not well understood nor is it easy to compensate for, particularly for autonomous drones. That is why takeoff and landing are often the two most difficult parts of a drone flight. Drones typically wobble and inch slowly toward a landing until power is finally cut and they drop the remaining distance to the ground.
A system was developed that uses a deep neural network to help autonomous drones “learn” how to land more safely and quickly while using less power. The system, called the Neural Lander, is a learning-based controller that tracks the position and speed of the drone and modifies its landing trajectory and rotor speed to achieve the smoothest possible landing. It has the potential to help drones fly more smoothly and safely, especially in the presence of unpredictable wind gusts.
Deep neural networks (DNNs) are AI systems inspired by biological systems like the brain. The “deep” part of the name refers to the fact that data inputs are churned through multiple layers, each of which processes incoming information in a different way to tease out increasingly complex details. DNNs are capable of automatic learning, which makes them ideally suited for repetitive tasks.
To make sure that the drone flies smoothly under the guidance of the DNN, a technique known as spectral normalization was used that smooths out the neural net’s outputs so it doesn’t make wildly varying predictions as inputs or conditions shift. Improvements in landing were measured by examining deviation from an ideal trajectory in 3D space. Three types of tests were conducted: a straight vertical landing, a descending arc landing, and flight in which the drone skims across a broken surface, such as over the edge of a table, where the effect of turbulence from the ground would vary sharply.
The new system decreases vertical error by 100 percent, allowing for controlled landings, and reduces lateral drift by up to 90 percent. In experiments, the system achieved actual landing rather than getting stuck about 10 to 15 centimeters above the ground, as unmodified conventional flight controllers often do. Further, during the skimming test, the Neural Lander produced a much smoother transition as the drone transitioned from skimming across the table to flying in the free space beyond the edge.
Besides its obvious commercial applications, the new system could prove crucial to autonomous medical transports that could land in difficult-to-reach locations (such as gridlocked traffic).