Listen to this article

A drone using autonomy software developed by Southwest Research Institute navigated a nuclear facility. SwRI built a map of the facility using LIDAR data and exploration algorithms. | Photo credit: Southwest Research Institute

The Southwest Research Institute (SwRI) developed a drone with a simultaneous localization and mapping (SLAM) system that can operate completely autonomously without any previous knowledge of its environment.

SwRI tested the autonomous drone’s capabilities during the EnRicH 2021 European Robotics Hackathon. During the hackathon, the drone was tasked with entering the Zwentendorf Nuclear Power Plant and detecting radiation sources without the aid of a human pilot.

The team created a drone that used new algorithms and computer vision to explore and map unknown environments. The drone is equipped with a LiDAR sensor, a time-of-flight camera and radiation detectors. During the trial, the team used on-drone processors and ground-based processors to perform SLAM, exploration, decision-making, autopilot, computer vision analysis, sensing and other tasks.

SwRI’s drone was able to successfully locate two sources of cobalt-60, a radioisotope, hidden in different locations as part of the challenge.

The Zwentendorf Nuclear Power Plant is located about 20 miles northwest of Vienna. It is the world’s only nuclear power plant that was completed but never put into operation. It was completed in 1978 and loaded with fuel, but Austria then decided it didn’t trust nuclear energy and the project was scrapped.

“The planner showed robust flexibility, adeptly operating in previously unknown environments,” said Chris Bang, a SwRI program manager in the intelligent systems division. “It proved its ability to adapt, learn and perform tasks in real-time, which is crucial in time-critical search-and-rescue and hazardous scenarios.”

LiDAR point clouds were reconstructed to create the high-resolution image of electric turbines. | Photo Credit: Southwest Research Institute

Unlike other mapping technology, which requires a robot to be manually driven around an area to map it, SwRI’s drone is able to map the spatial topography of internal structures and open spaces in real-time as it explores autonomously.

“Today’s drones and ground robots typically require a lot from a human operator,” said Eric Thorn, manager of SwRI’s UAS research team. “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.”

SwRI’s drone could be used to do jobs that are dangerous for humans to do alone, such as assisting in dangerous search and rescue missions as well as in hazardous inspections at industrial facilities or infrastructure following natural disasters.

At EnRicH 2021, SwRI received an award for UAV mapping. SwRI participated in two of the three events, the exploration task and the search-and-rescue task. The goal of the event is to provide developers with a chance to test their technology in real-world environments.

SwRI isn’t the only organization developing this kind of technology. In April 2021, Exyn Technologies announced it had achieved level 4A autonomy, which means it’s capable of free-flight exploration of complex spaces. At this level, no human operator is required to be present and available to take control of the system at any time.

Left, a LIDAR image shows the drone’s point of view as it hovers above the containment vessel entrance. The dark rectangle at bottom right is a ventilation shaft. Right, the drone flew in the ventilation shaft. A radiation detector identified Cobalt-60 in a red pipe located in the shaft. | Photo Credit: Southwest Research Institute