--- title: "Smart drones and robots backed by German military track radioactive waste in minutes" description: "CBRNe World provides those tasked with defending against CBRN and IED threats with the essential practical, scientific and political information. Access the current and previous issues of the magazine by registering as a member." url: "https://cbrneworld.com/news/smart-drones-and-robots-backed-by-german-military-track-radioactive-waste-in-minutes" date: "2026-07-30T21:15:00+00:00" language: "en-GB" --- # Smart drones and robots backed by German military track radioactive waste in minutes [Zoe Rutherford](#) Author 03 February 2026 Originally published by Scientists in Germany have developed AI-powered automated drones and robots that are capable of detecting radioactive waste in hazardous environments where human access is unsafe or impossible. The innovative project is carried out by researchers at the Fraunhofer Institute for Communication, Information Processing and Ergonomics (FKIE). The scientists are combining uncrewed aerial systems (UAS) and uncrewed ground vehicles (UGW) with advanced sensor fusion, automation and probabilistic search algorithms. Their goal is to notably shorten the time required to find radioactive, chemical or biological hazards during emergencies. The technology demonstrator can localize radioactive sources to within a few feet. Field trials have shown promising results. Supported by the Bundeswehr Research Institute for Protective Technologies and CBRN Protection (WIS), the research is led by Fraunhofer FKIE’s Sensor Data and Information Fusion department. #### Highly automated UAS According to the research team, in 2023, a tiny radioactive caesium-137 capsule, measuring eight millimeters in length, fell from a truck while being transported between Perth and a Rio Tinto mine site in Australia’s Pilbara region. At the time, officials launched a major search operation along a 869-mile (1,400-kilometer) stretch of highway. Specialist teams dove at around 43 mph (70 km/h) while using radiation-detection equipment to scan the roadside. “The cesium capsule in Australia could only be found after days of searching with handheld detectors,” Claudia Bender, a researcher at Fraunhofer FKIE who worked on the technology, stressed. “We could have found the radioactive capsule much more quickly using our UAS.” The team said the technology’s detection process is highly automated and carried out in an exploration phase and a search phase. During the exploration phase, the drone follows a [predefined flight pattern](https://interestingengineering.com/transportation/when-ai-flying-passenger-planes) and continuously measures background radiation. If the system detects an anomaly, it switches into a targeted search mode. During this phase, the drone dynamically adjusts its flight path based on [real-time sensor](https://interestingengineering.com/innovation/programmable-robotic-sheet-innovation) input and previously collected data. “Once the pilot launches the drone, it initially follows a fixed flight pattern,” the team said. “As soon as sufficient sensor data is available, the system switches to adaptive search mode, using the accumulated information to independently calculate where the source might be.” #### Detecting radiation The system relies on [stochastic algorithms](https://machinelearningmastery.com/stochastic-optimization-for-machine-learning/) which estimate the probability of the radioactive source’s location. As the drone collects data, it generates waypoints autonomously until it converges on the most likely position. The system maps radiation intensity in real time using spatial heat maps. It also has probability maps, which highlight the areas with the highest likelihood of containing hazardous material. The drone is equipped with a gamma detector, and additional sensors for the detection process. These are supported by electro-optical and infrared cameras, an Intel NUC computer for data processing, an inertial measurement unit (IMU) and a LTE comms module for monitoring the data from the ground. The cameras show the live image viewed by the drone. They can detect objects including people, buildings and vehicles and can display these on a map with georeferencing. The IMU records the position and movement of the drone in 3D. In parallel, Fraunhofer FKIE’s Cognitive Mobile Systems department is developing uncrewed ground robots to operate in environments that remain too dangerous even after aerial reconnaissance. They integrate [CBRNE sensors](https://www.bruker.com/en/products-and-solutions/cbrne-detectors.html), autonomous navigation, and geodata processing to confirm threats, map hazardous zones, and support recovery operations. One of the prototypes features a ‘click and grasp’ system that allows operators to select objects directly from a live video feed. Its robotic arm can autonomously pick up, analyze, and secure radioactive material. It can also perform complex actions such as opening car doors. Additional research is exploring 3D visualization and intuitive controls which let robots mirror human arm movements. “We call this new support function ‘jacket control,'” the researchers said in a [press release](https://www.fraunhofer.de/en/press/research-news/2026/february-2026/quickly-and-precisely-localizing-radioactive-material.html). “This also enables emergency personnel who are not trained specialists to control the robot intuitively.” ## Schema ```json { "@context": "https://schema.org", "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "News", "item": "https://cbrneworld.com/news" }, { "@type": "ListItem", "position": 2, "name": "Smart drones and robots backed by German military track radioactive waste in minutes", "item": "https://cbrneworld.com/news/smart-drones-and-robots-backed-by-german-military-track-radioactive-waste-in-minutes" } ] } ``` ```json { "@context": "https://schema.org", "@type": "NewsArticle", "mainEntityOfPage": { "@type": "WebPage", "@id": "https://cbrneworld.com/news/smart-drones-and-robots-backed-by-german-military-track-radioactive-waste-in-minutes" }, "headline": "Smart drones and robots backed by German military track radioactive waste in minutes", "description": "Originally published by https://interestingengineering.com/ Scientists in Germany have developed AI-powered automated drones and robots that are capable of detecting radioactive waste in hazardous environments where human access is unsafe or impossible. The innovative project is carried out by researchers at the Fraunhofer Institute for Communication, Information Processing and Ergonomics (FKIE). The scientists are combining uncrewed aerial systems (UAS) and uncrewed ground vehicles (UGW) with advanced sensor fusion, automation and probabilistic search algorithms. Their goal is to notably shorten the time required to find radioactive, chemical or biological hazards during emergencies. The technology demonstrator can localize radioactive sources to within a few feet. Field trials have shown promising results. Supported by the Bundeswehr Research Institute for Protective Technologies and CBRN Protection (WIS), the research is led by Fraunhofer FKIE’s Sensor Data and Information Fusion department. Highly automated UAS According to the research team, in 2023, a tiny radioactive caesium-137 capsule, measuring eight millimeters in length, fell from a truck while being transported between Perth and a Rio Tinto mine site in Australia’s Pilbara region. At the time, officials launched a major search operation along a 869-mile (1,400-kilometer) stretch of highway. Specialist teams dove at around 43 mph (70 km/h) while using radiation-detection equipment to scan the roadside. “The cesium capsule in Australia could only be found after days of searching with handheld detectors,” Claudia Bender, a researcher at Fraunhofer FKIE who worked on the technology, stressed. “We could have found the radioactive capsule much more quickly using our UAS.” The team said the technology’s detection process is highly automated and carried out in an exploration phase and a search phase. During the exploration phase, the drone follows a predefined flight pattern and continuously measures background radiation. If the system detects an anomaly, it switches into a targeted search mode. During this phase, the drone dynamically adjusts its flight path based on real-time sensor input and previously collected data. “Once the pilot launches the drone, it initially follows a fixed flight pattern,” the team said. “As soon as sufficient sensor data is available, the system switches to adaptive search mode, using the accumulated information to independently calculate where the source might be.” Detecting radiation The system relies on stochastic algorithms which estimate the probability of the radioactive source’s location. As the drone collects data, it generates waypoints autonomously until it converges on the most likely position. The system maps radiation intensity in real time using spatial heat maps. It also has probability maps, which highlight the areas with the highest likelihood of containing hazardous material. The drone is equipped with a gamma detector, and additional sensors for the detection process. These are supported by electro-optical and infrared cameras, an Intel NUC computer for data processing, an inertial measurement unit (IMU) and a LTE comms module for monitoring the data from the ground. The cameras show the live image viewed by the drone. They can detect objects including people, buildings and vehicles and can display these on a map with georeferencing. The IMU records the position and movement of the drone in 3D. In parallel, Fraunhofer FKIE’s Cognitive Mobile Systems department is developing uncrewed ground robots to operate in environments that remain too dangerous even after aerial reconnaissance. They integrate CBRNE sensors, autonomous navigation, and geodata processing to confirm threats, map hazardous zones, and support recovery operations. One of the prototypes features a ‘click and grasp’ system that allows operators to select objects directly from a live video feed. Its robotic arm can autonomously pick up, analyze, and secure radioactive material. It can also perform complex actions such as opening car doors. Additional research is exploring 3D visualization and intuitive controls which let robots mirror human arm movements. “We call this new support function ‘jacket control,'” the researchers said in a press release. “This also enables emergency personnel who are not trained specialists to control the robot intuitively.”", "image": { "@type": "ImageObject", "url": "https://cbrneworld.com/" }, "publisher": { "@type": "Organization", "name": "CBRNe World Magazine", "logo": { "@type": "ImageObject", "url": "https://cbrneworld.com/images/default/Asset%201.png" } }, "author": { "@type": "Person", "name": "Zoe Rutherford", "url": "https://cbrneworld.com/news/smart-drones-and-robots-backed-by-german-military-track-radioactive-waste-in-minutes" }, "datePublished": "2026-02-03T10:09:25+00:00", "dateCreated": "2026-02-03T10:09:25+00:00", "dateModified": "2026-02-03T10:09:25+00:00" } ```