4/6/2022 Laura Schmitt
In February, Driggs-Campbell received a $500,000 NSF CAREER research grant for young faculty to develop algorithms that will enable more fluid robot navigation when deployed in real-world situations alongside humans.
Written by Laura Schmitt
Thanks to advances in robotics and autonomous systems research, smaller and smarter robots that work alongside humans—rather than functioning in isolation—are beginning to be deployed in manufacturing, agriculture, and transportation.
According to ECE Assistant Professor Katherine Rose Driggs-Campbell, the gap between theory and full-scale deployment of these robots is closing, but challenges remain.
“People have intuition about where other people or objects around them will be moving, which helps with smooth navigation,” she said. “I’m interested in developing technology that enables robots to have this human intuition so they can navigate safely in complicated settings, like through crowds.”
In February, Driggs-Campbell received a $500,000 NSF CAREER research grant for young faculty to develop algorithms that will enable more fluid robot navigation when deployed in real-world situations alongside humans.
During the five-year research project, she and her students will study trajectory prediction and crowd navigation. Initially, they will introduce interaction graphs as a formal representation that captures the coupling between agents and allows for tractability and computational efficiency through factorizations.
This framework will allow the researchers to model types of interactions that capture variable and dynamic relationships between humans and robots. The prediction insight they gather on human trajectories will be combined into robust navigation, providing safety even in the presence of uncertainty.
“Our aim is to balance efficiency and safety, guaranteeing reliable performance even in the presence of erratic human behavior and sensor uncertainty,” Driggs-Campbell said. “It’s very important to us that we deploy and evaluate our research on real-world robots, so we can have impact across many challenging problem domains. We plan to run experiments in many different applications, including agricultural robots, which can help alleviate labor issues [in farming], collaborative manufacturing or co-robots, which are seeing a rise in popularity in industry, and transportation, where behavior prediction and interaction remains one of the key challenges for autonomous vehicles.”
Driggs-Campbell, who has an ongoing collaboration with U of I-related startup EarthSense, will test the new algorithms in the company’s ultra-compact field robots that monitor crop health and provide farmers with actionable insights.
According to Driggs-Campbell, she will also work with State Farm Insurance, which is interested in modeling human behaviors in the automobile domain, and Foxconn Interconnect Technology, which is interested in deploying collaborative robots in manufacturing and warehouse operations.
Another component of NSF CAREER award grants is course and curriculum development. Driggs-Campbell plans to enhance robotics education by developing new coursework in Prairie Learn, the mastery-based online homework and exam system developed by Grainger College of Engineering faculty.
The NSF CAREER Award is the agency’s most prestigious award in support of early-career faculty who have the potential to serve as academic role models in both research and education and can advance the mission of their respective department or organization.