Traditional manufacturing involves robots working independently in safety fences on a set of well-defined tasks. Although this paradigm has proved to be reliable over the past decades, it sacrifices productivity and flexibility. In recent years, researchers have been exploring the possibilities of physical human robot interaction in manufacturing, but there are two major challenges: safety and robustness. The presence of human workers in robot workspaces introduces uncertainty and the robot system must be capable of distinguishing between physical human interactions and undesired collisions. In our work, we designed a framework that classifies the type of contact using only the robot’s joint currents and the force/torque sensor measurements. We also incorporate three robot operational modes to actively respond to collisions and human interventions. With our system, the robot performs a safety pause when there is a collision and demonstrates compliant behaviors when the human tries to interact with the robot. To evaluate the responsiveness of our system, we conducted a user study to measure the reaction time of the robot when it’s in contact with a human. The results meet our safety requirement, which is 50ms.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
