The University of Maryland’s Institute for Advanced Computer Studies Jan. 29 announced that assistant professor Pratap Tokekar has received a National Science Foundation Faculty Early Career Development, or CAREER, award.
Tokekar’s award was given for a project designed to improve the reliability and performance of multi-robot systems in dynamic, outdoor environments.
An Indian American assistant professor of computer science, Tokekar is principal investigator of the NSF award, expected to total $548,808 over five years, the university report said.
The funding supports efforts to make teams of robots more resilient by developing coordination algorithms that can assess the risk of individual robot failure due to unfavorable environments. Current systems can often fail if one of the robots in a team—a single drone within a swarm of small drones, for example—fails due to mechanical or electrical problems, the university said.
“The unique thing to this project is to understand resilience and this notion of risk-awareness from a teaming point of view,” Tokekar, who has appointments in the University of Maryland Institute for Advanced Computer Studies and the Maryland Robotics Center, said in a statement. “That’s something where we hope to make contributions to the broader scientific community.”
Multi-robot systems are currently deployed in warehouse and industrial settings–controlled environments with little risk.
Tokekar and his group will work with teams of robots in more dynamic spaces, where they can address potential challenges like poor weather and cyber-attacks, both of which can disable robots or their sensors, UMD said.
The researchers will use precision agriculture—where farmers use modern technologies like satellite sensing, drones, autonomous vehicles and more—as their domain to field test the coordination algorithms they develop, the university added.
They will be looking at a team of aerial and ground robots with various sensing capabilities to monitor the health of crops on a farm, Tokekar said in the report. Aerial robots can cover relatively large areas at one time, he explains, and can be used as scouts to get an idea of how to coordinate with ground robots that can gather data from more specific locations.
Making multi-robot systems reliable and relatively inexpensive is important for future data-gathering applications like environmental and infrastructure monitoring, as well as studying climate change, Tokekar added in the report.
In addition to understanding multi-robot systems coordination, Tokekar says an important component of the NSF project is educational outreach.
The team intends to introduce outreach efforts for various groups including middle-school students and teachers, underrepresented minorities, undergraduates, graduate students and future faculty.
In addition to graduate and undergraduate students working with Tokekar on the Maryland campus, the project will involve experts from other universities: assistant professor Song Li at Virginia Tech and Prof. Jnaneshwar Das at Arizona State University.
Tokekar says that this type of multi-institutional collaboration makes the research sustainable, so the knowledge learned goes beyond the scope of the five-year project, according to the university.
He envisions multi-robot systems resilience as an essential part of future robotics research.
“The long term is to have teams of robots in the world, collaborating, coordinating, not only amongst themselves,” he said in the report. “It involves a whole bunch of other things like human-robot interactions, communications across different types of infrastructure, and a perception and understanding about what’s happening in the world. Resilient coordination is only one piece of the puzzle.”