UN agencies test AI tools to reach dangerous areas, track displacement and speed disaster response
UN agencies test AI tools to reach dangerous areas, track displacement, and speed disaster response
GENEVA: United Nations agencies are testing new artificial intelligence (AI) tools to improve humanitarian operations by reaching conflict zones that are too dangerous for aid workers, tracking displaced populations, and accelerating disaster response.
The AI-powered technologies are designed to analyze satellite imagery, social media posts, mobile phone data, and other digital information to provide real-time insights into crises. This enables humanitarian organizations to assess damage, monitor population movements, and identify communities in urgent need of assistance, even when access on the ground is limited.
UN officials say the technology can significantly reduce the time required to respond to emergencies by helping relief teams prioritize resources and make faster, more informed decisions. AI is also being tested to improve early warning systems for natural disasters, including floods, droughts, and storms, allowing authorities to prepare and respond more effectively.
Despite its potential, the UN emphasizes that AI will complement—not replace—human expertise. Agencies are also addressing concerns over data privacy, bias, and ethical use to ensure that AI-driven decisions remain transparent, accurate, and respectful of human rights.
Humanitarian organizations believe that, if deployed responsibly, AI could become a valuable tool for delivering life-saving assistance more efficiently in some of the world’s most challenging environments.
At this week’s AI for Good Summit in Geneva, several humanitarian technology exhibits highlighted how artificial intelligence can be used to save lives and improve aid delivery.
One of the standout innovations was a large white Sherp vehicle—an amphibious, AI-enabled truck built in Ukraine. Equipped with cameras, sensors, and a drone landing pad, the rugged vehicle can float across water, navigate swamps and flooded rivers, and climb obstacles up to one metre (3.3 feet) high.
The World Food Programme (WFP) is preparing to begin field trials of a remotely operated version of
After losing numerous aid drivers in dangerous conflict zones, the World Food Programme (WFP) partnered with the German Aerospace Centre (DLR) to equip Sherp vehicles with artificial intelligence and remote-control technology, allowing them to operate in high-risk areas without putting drivers’ lives at risk.
Under the project, operators would control the vehicles from a secure shipping-container command centre located in a safe area. A human driver would remotely navigate the Sherp through the most dangerous stretch of its journey while delivering humanitarian aid.
The system has already undergone testing in Germany, with field trials scheduled to begin in Uganda in 2028, according to Armin Wedler, coordinator of DLR’s Autonomous Humanitarian Emergency Aid Devices (AHEAD) project.
Wedler said the remote-control system relies on advanced mathematics and conventional engineering, but AI is essential for processing the vast amount of data collected by the vehicle’s cameras and sensors in real time.
Although fully autonomous operation is technically possible, he stressed that humanitarian missions still require human oversight due to the unpredictable nature of conflict zones.
“We’re not talking about driving on clear roads with marked lanes—there are often no roads at all,” Wedler said, noting that aid vehicles can suddenly be surrounded by desperate crowds seeking food, making human judgment indispensable.
Among the more than 200 exhibits at the AI for Good Summit, which ranged from humanoid robots to advanced prosthetics and AI companions, several quieter displays showcased how artificial intelligence is already helping humanitarian agencies improve disaster response, strengthen relief operations, and ultimately save lives.
Among the humanitarian innovations showcased at the AI for Good Summit, the UN refugee agency (UNHCR) introduced a new Legal Virtual AI Assistant designed to support lawyers and legal officers working with refugees. The tool enables them to quickly identify refugees’ rights under country-specific legal systems, helping them prepare cases more efficiently.
Rebeca Moreno Jimenez, lead data scientist at UNHCR’s Innovation Service, said faster case preparation can be “life-saving” for many refugees by improving access to legal protection and assistance.
Another initiative, Data Insights for Social and Humanitarian Action (DISHA), brings together the United Nations and private-sector partners, including Google and McKinsey, to provide humanitarian organisations with data and AI-powered tools that enhance disaster response.
One DISHA project uses AI to analyse anonymised mobile phone data, allowing aid agencies to track large-scale population movements during disasters and identify where displaced people are heading. This helps humanitarian teams direct assistance to the areas of greatest need.
Another project applies AI to compare satellite images taken before and after disasters—such as last month’s earthquakes in Venezuela—to rapidly assess building damage and identify the hardest-hit communities.
According to DISHA Product Lead Andreas Kortis, the goal is to provide humanitarian workers with accurate information early enough to make better decisions, ensuring aid reaches the people who need it most without wasting valuable time or resources.
