Robotic Manipulation Using High Bandwidth Force and Vision Feedback

Abstract

High bandwidth sensor feedback is necessary for performing precise manipulation tasks within imprecisely calibrated and dynamically varying environments. Force controlled manipulation is a common technique for compliantly contacting and manipulating uncertain environments. Visual servoing is an effective technique for guiding imprecisely calibrated manipulators with imprecisely calibrated camera-lens systems. These two types of manipulator feedback, force, and vision, represent complementary sensing modalities: visual feedback provides information over a relatively large area of the workspace without requiring contact with the environment, and force feedback provides highly localized and precise information upon contact. This paper presents three different strategies which combine force and vision within the feedback loop of a manipulator: traded control, hybrid control, and shared control. These strategies can be used alone or in concert with each other, depending on the manipulation task. A discussion of the types of tasks that benefit from the strategies is included. Experimental results are also presented, which show that the use of visual servoing to stably guide a manipulator greatly improves controller performance during contract transitions by allowing fast approach velocities with stable, low impact contact.