Grasp Algorithms for Optotactile Robotic Sample Acquistion

Robotic sample acquisition is basically grasping.  Multi-finger robot sample grasping devices are controlled to securely pick up samples.  While optimal grasps for perfectly modeled objects are known, grasping unmodeled objects, like a surface sample, is an open research problem.  A major source of difficulty in robotic grasping, therefore, is the sensing of object parameters and grasp quality.  Humans combine the high information content of vision, several types of haptic/tactile sensors in the fingers, and a sophisticated learning process to grasp unknown objects.  In comparison, current robotic graspers rely on a much more limited set of sensors, particularly for measuring tactile properties.




Force Feedback