A novel type of robot that can communicate and share images quickly may be better suited than humans for certain high-risk jobs.

 A new system developed at Cornell University could enable teams of robots to share information as they move around and interpret what they see, which would allow the robots to conduct surveillance as a single entity with many eyes.

This new development could also replace some of human’s most dangerous jobs, including disposing of landmines, cleaning up after a nuclear meltdown or surveying the damage after a flood or hurricane.

“Once you have robots that cooperate, you can do all sorts of things,” Kilian Weinberger, associate professor of computer science, who is collaborating on the project with Silvia Ferrari, professor of mechanical and aerospace engineering, and Mark Campbell, professor of mechanical engineering, said in a statement.

The researchers utilized their experience with computer vision to match and combine images of the same area from several cameras, identifying and tracking objects and people from place to place.

The new system fuses information from fixed cameras, mobile observers and outside sources while the majority of prior work in the field focused on analyzing images from just a single camera as it moves around.

The mobile observers might include autonomous aircraft and ground vehicles and possibly humanoid robots, which move through a crowd and send their images to a central control unit. The robot may have access to other cameras looking at the region of interest, as well as access to the internet for help in labeling what it sees.

Robot observers may be able to detect suspicious actors and activities if they know the context of the scene that otherwise may go unnoticed. For example, a person running may be a common occurrence on a college campus but may require further scrutiny in a secured area.

The next step will be for the researchers to test the system on the Cornell campus, using research robots to surveil crowded areas while drawing on an overview from an existing webcam. This might lead to incorporating the new technology into campus security.