As the saying goes, "there's no I in team," but there is one in robotics. And a new research award from the National Science Foundation will study how robots can work better as a team.
Temple University College of Engineering assistant professor of mechanical engineering Philip Dames, PhD, recently secured a 5-year, $557,678 NSF Faculty Early Career Development (CAREER) award to further study robotic coordination. According to Dames, the project takes inspiration from sports analytics, which quantifies contributions from individual players toward the team-level objective of winning. Using that data, sports managers try to assemble and field the best team possible. Dames will translate these concepts to the field of robotics, where "winning" is now defined as finishing a collective task, such as finding all survivors after a natural disaster.
As outlined in the award, multi-robot analytics is a new field of study, providing an unconventional approach to developing effective multi-robot teams. Multi-robot analytics greatly extends the concepts of sport analytics, a data-driven analytical decision-making methodology for improving performance in team sports that has transformed the study and business of athletics, to study how robots within a team coordinate, how to develop these multi-robot teams, and how to field a team most efficiently.
This matters greatly in search-and-rescue emergencies, where fielding the most effective available team possible would make a significant difference in the outcome and overall safety. The specific needs and robot platforms will differ depending on the specific situation, but the goal is to develop theoretical tools that can be used across in any generic setting.
"I hope to have two main research outputs to the project. First, an open-source software toolkit for testing and development. This will allow roboticists to develop coordination strategies that best take advantage of the unique sensing, actuation, computation, and/or communication capabilities of each individual platform or platform type within a heterogeneous multi-robot system (MRS) to enable robots to replace or coordinate with human workers in complex scenarios. Second, a collection of new theoretical tools that allow roboticists to predict the range of performance of an MRS quickly and confidently in a new situation," Dames added.
This project is supported by the cross-directorate Foundational Research in Robotics program, jointly managed and funded by the Directorates for Engineering (ENG) and Computer and Information Science and Engineering (CISE).
In addition to the research goals of the project, Dames also aims to develop a stronger robotics workforce in Philadelphia, while creating and running a multi-robot competition for area high school students.
To learn more about Prof. Dames and his research interests, visit https://engineering.temple.edu/about/faculty-staff/philip-dames-tug85627 and https://sites.temple.edu/trail/