Drone Alone: Advanced Air Mobility Advances Pilotlessly

January 3, 2022 | Dave Clarke

SwRI has developed an exploration and mapping solution that enables UAVs to autonomously explore and map nuclear power plants.

During the EnRicH 2021 European Robotics Hackathon, the San Antonio, Texas-based Southwest Research Institute (SwRI) successfully demonstrated an unmanned aircraft system (UAS) that fully autonomously explored and mapped the interior of the Zwentendorf Nuclear Power Plant located in Zwentendorf an der Donau, Austria.

The Zwentendorf plant is the world’s only nuclear facility that has been fully built but never activated. This makes it an ideal training ground to prepare for potential nuclear accidents, radiological spills, and the provision of disaster services during a nuclear accident.

“Today’s drones and ground robots typically require a lot from a human operator,” Eric Thorn, manager of SwRI’s UAS research team explains. “The autonomy we’ve demonstrated has the potential to significantly reduce the burden on human operators, allowing robotic systems to act independently and operate themselves.” Thorn added, “We’ve developed a full autonomy stack that can be paired with a variety of sensors and UAS platforms to perform critical missions.”

A drone's inspection of a nuclear power plant.

The drone autonomously detected two sources of cobalt-60, a radioisotope, hidden in separate locations as part of a preplanned challenge. Participants had no prior information about the facility or the exploration challenges created by a panel of judges.

SwRI demonstrated a four-axis drone equipped with several sensors — light detection and ranging (LIDAR), a time-of-flight camera, and radiation detectors. On-drone processors and ground-based processing performed simultaneous localization and mapping (SLAM), exploration, decision-making, autopilot, computer vision analysis, sensing, and other tasks.

Multicolored drone data visualization of the inside of a power plant.

Using algorithms and modeling tools, SwRI’s technology maps the spatial topography of internal structures and open spaces in real-time. Fusing data from computer vision sensors, the technology maps routes as it explores new locations. Perception techniques to detect people, vehicles and other objects are also available based on convolutional neural networks (CNNs).

Want to continue to stay up-to-date about the latest developments in the eVTOL industry? Subscribe to AeroCar Journal now. It’s FREE (for a limited time)! Join us on Twitter for the latest news, analysis, and insight about the eVTOL industry. AeroCarJ