Despite the fact that drones are flying to new heights across many industries including mining, agriculture, energy and research, the educational curve necessary to manually pilot UAVs may cause the best laid promises to crash and burn because of lack of skilled pilots. Check Skyreat Lens Cap Cover page.
If drones will be to ever become main-stream, advanced innovation in semi-autonomous and autonomous models must still expand. In fact, researchers using the Swiss Federal Institute of Technology are developing drones which could someday make driver’s seat in commercial applications.
The team has created a prototype AscTec Firefly that will, in accordance with the MIT Technology Review, “build a 3-D map of your unfamiliar environment with minimal assistance from a human operator, and after that plan a unique routes around an area and its obstacles autonomously.” More about Skyreat page.
“This would be the first time you can show full mapping, relocalization—finding the drone about the map—and considering board,” researcher Michael Burri tells MIT.
The Swiss model weighs approximately 3.5 pounds and is also equipped with a high-def camera and sensor array that could self-report the drone’s orientation, velocity and also other data that may then allow software to render a 3D map by comparing video footage using the data.
The project is comparable to a Japanese effort to produce an autonomous drone the visible difference being the project in Japan uses laser guidance to prevent obstacles because it surveys the inside of buildings at Tokyo Electric Power Co.’s Fukushima No. 1 plant.
Like the Japanese model, the Swiss research team successfully tested the drone in a industrial setting, turning the drone loose at the former industrial site replete with tricky duct work, pipes and equipment. The Japanese drone completed an exam flight on the nuclear plant’s No. 5 reactor building, which escaped severe damage from the March 2011 nuclear disaster.
Autonomy in drone flight is really a growing topic of research throughout the world. At Mexico’s National Institute of Astrophysics, Optics and Electronics (INAOE), José Martínez Carranza is breeding a cutting-edge UAV autonomy system that can allow drones to “learn” to navigate and not using a GPS signal or pilot backup. According to Science Daily, Martinez’s system will “estimate the positioning and orientation on the vehicle, letting it to recognize its environment, hence to change the GPS location system for low-cost sensors for instance accelerometers, gyroscopes and camcorders.” Known as the oddly named RAFAGA (Robust Autonomous Flight of unmanned aerial vehicles in GPS-denied outdoor areas), it will use the drone’s cam corder and apply an algorithm to assist the UAV orient and navigate by way of a map-drawing function that judges the drone’s position in accordance with its destination.
MIT Reports that this Swiss team will keep work on improvements to its autonomous model, such as “ability to prevent collisions with moving objects that don’t be visible on its map—for example humans or moving equipment.”