At Northeastern University, researchers are in the process of studying how humans coordinate hand-offs with one another and teaching robots to do the same. There is a great possibility that in the near future, humans and robots will work side-by-side. Thus, the ability to pass tools and objects back and forth becomes vital. Hence, neuroscientists and engineers at Northeastern are working to make sure robots can make it, which is a very complicated task.
According to Mathew Yarossi, an associate research scientist at Northeastern, humans have built predictive models of human behaviour over the course of their lives. For us, to hand objects back and forth, we barely have to take any cues from each other, and are predictive of where that object is going to be handed, the orientation of that object, etc. However, getting robots to do the same is quite difficult.
Another Northeastern professor, Eugene Tunik believes that we are not even close to it. Recently, he and his colleagues received a grant from the National Science Foundation to study how humans coordinate hand-offs and enable robots to make these same adjustments in real time. To act like human collaborators, robots must interpret and adapt to human movements and give cues that humans can follow. Tunik and Yarossi will conduct experiments to understand what humans do during an exchange with one another. That information will help to inform programming and design choices for robots.
“We’re extracting all these biophysical signals from the human, and we’re feeding them into the robot as information,” Tunik says. Thus, they need the help of Northeastern engineers here. Deniz Erdogmus, a professor of Electrical and Computer Engineering, will lead to train robots to use information to infer what a human intends to do and respond accordingly. Taskin Padir, an associate professor of Electrical and Computer Engineering, will focus on making the robots move in ways that help humans understand their intentions as well. The researchers will primarily use Valkyrie, a humanoid robot developed by NASA with four-fingered hands, to test their algorithms and practice exchanges.
Shahjadi Jemim Rahman