Force and Visual Control for Safe Human-Robot Interaction

old_uid9988
titleForce and Visual Control for Safe Human-Robot Interaction
start_date2015/09/24
schedule14h
onlineno
summaryApplications of intelligent robots that work in contact with humans are increasing, and thus the problem of controlling the physical interaction between the robot and the human in a safe and depen- dable manner is of concern. This talk is aimed at presenting a unified framework for development of robot interaction control schemes using vision and force; vision provides global information on the surrounding environment to be used for motion planning and obstacle avoidance, while force allows adjusting the robot motion so that the local constraints imposed by the environment are satisfied. The proposed solution is to adopt position-based visual servoing when the robot is far from the object, where the relative pose of the robot with respect to the object is estimated recursively using only vision. The control schemes are expe- rimentally tested on a setup consisting of an industrial robot with open control architecture, force/torque sensor and hybrid camera. Some results with a dual-arm system are also discussed.
responsiblesBaumard