While drones are increasingly being used in search and rescue missions, there are some problems with the new technology.
That’s why researchers led by Purdue University professors are working to use artificial intelligence and learning algorithms to create a platform that will allow multiple drones to communicate and adapt as missions change.
Shaoshuai Mou and Dan DeLaurentis, professors in aeronautics and astronautics, are leading the research, which received funding from Northrop Grumman Corp. as part of the Real Applications of Learning Machine consortium.
“For the system, we focused on a multi-agent network of vehicles, which are diverse and can coordinate with each other,” Mou said. “Such local coordination will allow them to work as a cohesive whole to accomplish complicated missions such as search and rescue.”
In the new research, AI and machine learning techniques will assist the system in many ways, such as in object recognition and human-machine communication, improving the system’s performance over time, the researchers said. The system allows for input from a human commander, as well as lets the drones provide feedback and even suggestions in natural language, they note.
“For complex situations, we still need to involve humans in the loop and try to do mixed autonomy consisting of machines and humans,” Mou said.
In the mission scenarios, a ground-based vehicle will communicate to either air, ground, or aquatic drones that can cover a wide area.
“The utilization of the combination of heterogenous vehicles should be a key to so many complicated problems,” Mou said.
Mou and DeLaurentis are joined on the project by faculty from the University of Illinois-Chicago and University of Massachusetts at Amherst.
A short animation is available on YouTube.