Robust robotic grasping using IR Net-Structure Proximity Sensor to handle objects with unknown position and attitude

Abstract

In this paper, we focus on unknown parameters such as the position and attitude of the object, and describe a short-range, high-speed and noncontact sensing method for obtaining the position and attitude of the object using IR NetStructure Proximity Sensor ("IR-NSPS") which complements the dead region of sensory information between visual and tactile sensing. To be more precise, we propose two effective control methods which are pre-shaping and object positioning using IR-NSPS for robust grasping by adjusting the gripper configuration in response to attitude error of up to ±45 deg and the position error of up to ±80 mm of the unknown object.The methods therefore can significantly increase the speed and effectiveness of grasping objects without requiring a specific approach that depends on a vision sensor. Furthermore, to demonstrate the advantages of pre-shaping and object positioning, object grasping experiments were performed using these two operations to grasp objects placed randomly on a tabletop.

Tactile sensing in dexterous robot hands — Review

“…In some approaches, the robot grasping procedure could be simplified by using proximity sensors on fingertips [128]. There are two main approaches of robot grasping that involve tactile feedback.…”

Integrated control of a multiple-degree-of-freedom hand and arm using a reactive architecture based on high-speed proximity sensing

“…Since our previous sensor (Hasegawa et al, 2015; Ye et al, 2013) did not have these two characteristics, the motion for adjusting the grasping form before contact was slow at distances of 30 mm or more, and it was thus impossible to realize high-speed pre-grasping motion (details of the characteristics are described in Appendix A).…”

“…However, in previous work (Hasegawa et al, 2015; Ye et al, 2013), the control was limited to a low DOF, such as finger opening and closing motions, and only 4-DOF control of the arm tip posture and position. It was impossible to simultaneously control the hand and the arm.…”

Integrated control of a multi-fingered hand and arm using proximity sensors on the fingertips

“…We have developed NetStructure Proximity Sensor and installed it on a robot [18]. We have also demonstrated object tracking using sensors located on the palm of a hand [19] and independent finger posture control using sensors on fingertips [20]. The term "pre-grasp" is used to denote the action in which, the fingertips are placed parallel to and a constant distance from the object surface.…”