
Emergency services test the new robot system at the ROMATRIS closing event in Wesel.
Researchers in Germany have developed an AI-backed semi-autonomous robot designed to support disaster relief operations by transporting heavy equipment across difficult terrain.
The robot was made in a joint project between the German Research Center for Artificial Intelligence (DFKI) and the Federal Agency for Technical Relief (THW), under the ROMATRIS (Robotic Material Transport in Disaster Situations) project.
According to the DFKI, the AI-powered machine can carry up to 150 kilograms (approximately 330 pounds) and navigate areas too hazardous for conventional vehicles or stretchers.
Designed specifically for civil protection applications, the robot combines intuitive control, artificial intelligence, and rugged mechanical design to assist emergency workers in some of the most challenging environments.
Daniel Weissenrieder, THW project manager and research officer, explained that the robotic system can support emergency personnel in multiple ways. “Not only does it transport heavy loads, it also helps to make operations safer,” he said.
High-tech for rough terrain
The semi-autonomous mobile robot can carry heavy loads to areas that vehicles or stretchers cannot access. Its development was supported by over 20 volunteers from 14 THW local associations through hands-on testing and expert workshops.
The robot integrates robust mechanical design with state-of-the-art sensor technology and AI-supported control. Its intuitive interface allows for operation with minimal training, either through direct hand gestures or semi-autonomous navigation during transport between deployment sites.
Meanwhile, the system also boasts a depth camera that recognizes the operator and tracks their position. A neural network reliably translates its gestures into commands.
The robot is also equipped with a 3D sensor system for autonomous navigation, allowing it to accurately map its surroundings and move along predefined waypoints. In addition, ultrasonic and laser sensors ensure reliable obstacle detection and avoidance, even in dynamic environments.
With a load capacity of up to 330 lbs (150 kilograms), the system can reliably transport heavy or bulky equipment, such as generators, pumps, or hoses, across long distances and uneven terrain.
The robot offers three operating modes, including manual control with a remote, a “Follow-Me” mode using gesture recognition and person tracking, and a shuttle mode where it autonomously moves between two points.
“With ROMATRIS, we are demonstrating how AI-supported robotics can support the work of emergency services,” Martin Mallwitz, project manager at the DFKI Robotics Innovation Center, revealed.
During the project, engineers conducted two field tests lasting several days at the THW training center in Hoya, Germany, to test the robot in various scenarios.

Intuitive gesture control: A THW volunteer controls the ROMATRIS-robot using hand signals. Image credit: THW / Yann Walsdorf
The project concluded with a large-scale demonstration at the THW training ground in Wesel, where the participants were able to experience the system in action and try it out for themselves.
The results demonstrated that the innovative tech can ease volunteer workloads by moving heavy equipment, saving time, and reaching difficult areas. As per Mallwitz, ROMATRIS marks a great step toward safer, more efficient operations and new crisis logistics solutions.
“Close cooperation with the THW has enabled us to develop the technology directly in line with civil protection requirements and test it under realistic conditions,” Mallwitz concluded in a press release.
MasterCard