Augmented reality helps build aircraft tanks
Scientists at Karlsruhe Institute of Technology (KIT) are developing an assistance system based on augmented reality technology which supports engineers in building and maintaining aircraft tanks. The system is currently being tested in industry.
Augmented Reality is gaining more and more in importance in industry: “We are developing software that helps us build and maintain aircraft tanks. It aims to increase the flexibility of the employees, accelerate the workflow, and connect and optimize processes,” says Christian Tesch from the Institute of Anthropomatics and Robotics at KIT, Chair of Intelligent Sensor-Actuator-Systems (ISAS, headed by Prof. Uwe D. Hanebeck).
Many commercial aircraft are at first not equipped for long flights and their fuel tanks are too small. So that they can still travel long distances, additional tanks are required which have to be maintained on a regular basis. To do that, so far engineers have had to climb into the tanks through a small opening. Often, however, they need both hands for assembling components, and new workers in particular also need instructions at the same time.
The AR glasses – at the moment we are using the HoloLens from Microsoft – display the work to be done in the engineers’ field of vision, who then have their hands free to install or repair components,” says Tesch. The glasses are equipped with cameras. Users scan special markers on the tank in advance using the cameras, which communicate the exact location and the size of the tank to the glasses. A transparent 3-D computer model from the inside of the tank is then projected onto the “real” tank; this means that engineers can also look into the closed tank from outside, understand the structure in detail, and get step-by-step instructions on how to install a pipe, for instance.
What’s more, with the help of markings on the ground, the glasses show where to find the required components in the warehouse, the location of which the glasses also recognize thanks to markers that the system has already learned. “We connect the actual work on the tank with locating objects which helps us create an overall concept,” says Tesch.
Full article here.