Model-Free Precise in-Hand Manipulation with a 3D-Printed Tactile Gripper

Abstract

Abstract-The use of tactile feedback for precision manipulation in robotics still lags far behind human capabilities. This study has two principal aims: 1) to demonstrate in-hand reorientation of grasped objects through active tactile manipulation; and 2) to present the development of a novel TacTip sensor and a GR2 gripper platform for tactile manipulation. Through the use of Bayesian active perception algorithms, the system successfully achieved inhand reorientation of cylinders of different diameters (20, 25, 30, and 35 mm) using tactile feedback. Average orientation errors along manipulation trajectories were below 5• for all cylinders with reorientation ranges varying from 42• to 67• . We also demonstrated an improvement in active tactile manipulation accuracy when using additional training data. Our methods for active tactile manipulation with the GR2 TacTip gripper are model free, can be used to investigate principles of dexterous manipulation, and could lead to essential advances in the areas of robotic tactile manipulation and teleoperated robots.Index Terms-Dexterous manipulation, force and tactile sensing, grippers and other end-effectors.

From Pixels to Percepts: Highly Robust Edge Perception and Contour Following Using Deep Learning and an Optical Biomimetic Tactile Sensor

“…The pin deflections can accurately characterize contact location, depth, object curvature/sharpness, edge angle, shear and slip. For more details, we refer to recent studies with this tactile sensor [6]- [14], [38]- [42].…”

“…In a major departure from recent work with the TacTip optical biomimetic sensor, here we predict the percepts directly from tactile images with a deep CNN. Prior work with this sensor has used specialised preprocessing to detect then track the pin positions [6]- [14], [38]- [42]. Here, this preprocessing is subsumed into the trained neural network.…”

MultiTip: A multimodal mechano-thermal soft fingertip

“…The first TacTip generation was used for shape recognition [8], manipulation [9], edge detection [10], object exploration [11] and topography reconstruction [12]. The image processing algorithm described in [10] used morphological operators in order to detect edges in real time, which was a clear need for the robotic fingertip.…”

“…The image processing algorithm described in [10] used morphological operators in order to detect edges in real time, which was a clear need for the robotic fingertip. Later, the sensor was integrated with soft robots [13] and robotic hands [9]. In order to detect surface texture, the previously smooth outer skin surface was improved by bumps positioned directly over the papillae pins [14], [15].…”

Soft Fingertips With Tactile Sensing and Active Deformation for Robust Grasping of Delicate Objects

“…Rigid grippers have the advantages of high precision control with the ease of integrating tactile, position, and torque sensors [9]. A stable grasping force and dexterous manipulation of the object can be achieved with force and position feedback [10]. However, rigid grippers are lacking adaptability, and they are prone to cause damages when manipulating very fragile and soft objects.…”