Getting Physical with Collaborative Robots to Program for Adaptability

Rice University

February, 2018

Researchers from Rice University have created a new way to train collaborative robots, also called cobots, to perform tasks within close proximity to humans while working together.

The researchers developed an algorithm that allows a robot working among humans to recalculate its path and goal when interrupted or taught, similarly to how a GPS recalculates and calculates routes.  Doctoral candidate Dylann Losey wants to help humans and robots collaborate by creating interactive tasks and assisting with tasks such as rehabilitation, surgery and training. By using gentle feedback, Losey and his team have found a new way for humans and robots to work cohesively.

According to Marcia O’Mally, a professor of electrical and computer engineering, “Historically, the role of robots was to take over the mundane tasks we don’t want to do: manufacturing, assembly lines, welding and painting.” O’Mally emphasized that, “As we become more willing to share personal information with technology, like the way my watch records how many steps I take, that technology moves into embodied hardware as well.”

For this research group at Rice the ultimate goal is to simplify the training of robots that will work along humans. These researchers plan on further refining their algorithm to help cobots optimize their time to complete tasks.

Learn more about this research here.

Comments are closed.