Robots for Hazardous Areas Navigation System for Rescue Workers in Underground Operations

Related Vendors

FAULHABER Drive Systems

Taiwan Machine Tool & Accessory Builders' Association (TMBA)

SIMTOS (Seoul International Machine Tool Show)

Using sensors and a self-built ultra-wideband network, emergency responders can navigate and coordinate effectively even without light, GNSS, or external communication.

Underground operations, such as those in subway stations, tunnels, or mines, are often risky and challenging for rescue workers. This is especially true when the technical infrastructure has collapsed due to explosions or fires. There is usually a lack of power, lighting, Wi-Fi, and GNSS and cell phone signals; smoke, debris, and damaged pathways further complicate navigation. The project, called Nike Mate, was developed specifically for such operations. It combines sensor data from robots and rescue workers with a self-established UWB (Ultra-Wideband) network. This creates a dynamic map of the environment that allows the team to locate and coordinate their efforts.

A Team of Humans And Robots

The project’s key innovation is what is known as “teaming.” A robot equipped with advanced sensors first explores the environment and creates a dynamic map. It shares the position data it collects via a UWB transmitter with the following or concurrently operating emergency responders, who are themselves equipped with UWB tags and place UWB anchors along their path. In addition to enabling stable data transmission, the beacons also allow for distance measurements between all participants, even without a direct line of sight. This creates a network of distance measurements in which the positions of robots and people can be determined with an accuracy of less than one meter. “This precise positioning is a crucial safety factor, for example when a person is facing an open elevator door or a precipice,” says project manager Philipp Berglez from the Institute of Geodesy at Graz University of Technology (Germany).

Sensor technology plays a key role in localization. The robot uses a laser scanner, a camera, and wheel sensors to create a map of its surroundings. This means that emergency responders do not have to rely on plans that may be outdated or inaccurate due to damage. The arriving rescue personnel have inertial sensors (accelerometers and gyroscopes) attached to their shoes. Using AI-based analysis, the system recognizes various movement patterns such as running, crawling, or creeping.

Plans to Incorporate Drone Data

To ensure that position calculations are not only accurate but also reliable, the project team uses factor graph optimization methods. This technique originates from robotics and makes it possible to take past measurements into account again, thereby improving the determination of the current position. When robots or people pass the same location at different times, their data can be linked, continuously improving the map.

“During our tests at the Mountain Center of the Montanuniversität Leoben, the prototype we developed proved its operational viability,” says Philipp Berglez. “For real-world deployment, we now need to make the individual components even more robust so that they can withstand real-world conditions and function reliably. We also want to expand the system to include mini-drones so that, in an emergency, we can gather additional data from a slightly elevated position, which can be crucial in helping rescue workers do their jobs.”

Design simulation for industrial robots

How to make your production more flexible with robotics