The project, part of NSF’s Community Infrastructure for Research in Computer and Information Science and Engineering program, will be led by OSU’s Bill Smart and Naomi Fitter, who both study human-robot interaction. The program’s goal is to advance computing and communication technologies, computer and network systems and “information and intelligent systems,” and improve how humans and robots communicate and work together.
“A big hurdle in robotics research has been the lack of a common robot to work with,” Smart said in the statement. “It’s tough to compare results and replicate and build on each other’s work when everyone is using a different type of robot. Robots come in many shapes and sizes, with different types of sensors and varying capabilities.”
Smart told Government Technology that this NSF initiative will build off another recent NSF-funded project involving the University of Pennsylvania, the University of Southern California and Semio to build and test out 10 Quori robot prototypes. Smart said the current project will involve the design and distribution of 50 Quori robots to act as a common hardware/software platform for other university research teams.
The robots will enable several research teams across the U.S. to swap ideas in their focus areas and build on each other’s work.
“The idea [is] that if you are working in human-robot interaction and you’re sharing a common platform and using the same kind of robot as other researchers are using, then it’s easier to transfer your results to those people and it’s easier for you to verify others’ results. This award is just to scale that up,” he said. “We’re going to do a little bit of redesign, and then we’re going to try to distribute them to the human-robot interaction community across the country.
“They’re going to be designed to be low cost so we can get a lot of them out there,” he said. “This is less about what robots do, but much more about, ‘What are the fundamental building blocks or things to understand to make these interactions work well?’”
Smart added that the project hopes to design and build robots for other university research efforts that are more affordable and easier to work with compared to others on the market, adding that they’re aiming for a “low five figure” price point for the model in order to “get them out there” as quickly as possible. From there, OSU researchers can help advance collaborative research focusing on the “social psychology of humans and robots together,” amid advances in autonomous technologies and robotics.
“What we’re trying to do with the robots is make them modular. … If you want a better arm, it should be easy to design a better arm and put it on the robot,” he said. “There’s still a lot of fairly foundational work to be done in human-robot interaction, and I think this robot is a good starting point. We’ll learn a lot from it.”
The funding will provide a path for researchers to advance for some time.
“The first phase of this is doing a redesign of the robot and working with some companies to help us do a design for manufacturing so we can produce it at scale. The first prototypes will [likely] be coming out within a year, and then the first production robots within a couple of years,” he said.
According to the announcement, Oregon State’s role in the project is to create and maintain a network of resources dedicated to researching and advancing the use of the Quori robot, as well as beta testing. Smart noted that while their current capabilities are fairly limited, Quori robots have expressive faces and arms that can make gestures, among other functions, and are perfectly designed for lab testing to further robotics research and development moving forward. The project team aims to connect students and researchers using Quori through online collaboration and other networking opportunities to build a “community of roboticists that can learn from one another and advance the pace of research.”
“The current work will incorporate the lessons learned to improve the robot’s design, making it easier to manufacture at scale, and to distribute it to a broader set of research groups,” Fitter said in a statement.
Smart said the project aims to increase the number of labs doing this kind of research, and added that further details on distribution remain pending as of this week.
