One day, first responder teams surveying a disaster site for victims might consist of both humans and robots. With multiple types of assets collectively assessing a complex, continuously changing scenario and determining how best to assign their individual skills to a broadly defined problem, human-robot teams could be ideally suited to the task.
But unpredictable environments and ongoing hazards could damage or destroy some of the bots, or disrupt communications between them. That’s a problem the University of Pennsylvania’s School of Engineering and Applied Science is focused on solving, by building robot teams that can reconfigure themselves in response to damage and collaboratively decide how to reorganize and complete their mission.
Robots like this can collectively plan behaviors with teammates. Image credit: Penn Engineering/GRASP Laboratory.To that end, the United States Army Research Laboratory (ARL) has awarded Penn Engineering a five-year, $27 million grant to develop new methods of creating autonomous, intelligent and resilient teams of robots. The aim of the program goes beyond disaster mediation: The robot teams will be designed to assist human partners in a wide range of dynamically changing environments, including search and rescue of hostages, information gathering after terrorist attacks and humanitarian missions.
The award is part of ARL’s Distributed and Collaborative Intelligent Systems and Technology (DCIST) Collaborative Research Alliance, which Penn Engineering will lead. Collaborators include the Aeronautics and Astronautics department at MIT, Georgia Institute of Technology and faculty from UC San Diego, UC Berkeley and the University of Southern California.
“We want to have teams of robots that know how to work together, but can figure out how to keep working even if some of their teammates crash or fail, if GPS signal is unavailable, or if cloud services are disrupted,” said Vijay Kumar, director of the DCIST program. “This means designing networks with loose, flexible connections that can change on the fly. That way, a single event can’t bring down the entire network. More importantly, we want them to learn to perform tasks they may have never performed and work alongside humans that they may never have worked with.”
Three important research focus areas are distributed intelligence and learning; creating a cohesive team of autonomous robots, sensors, computational resources and human experts; and building resiliency in group behaviors.
“The technology we’re working will better allow humans to respond by projecting their intelligence without directly coming in harm’s way,” Kumar said.