Experimental Evaluation of Tactile Sensors for Compliant Robotic Hands

Abstract

The sense of touch is a key aspect in the human capability to robustly grasp and manipulate a wide variety of objects. Despite many years of development, there is still no preferred solution for tactile sensing in robotic hands: multiple technologies are available, each one with different benefits depending on the application. This study compares the performance of different tactile sensors mounted on the variable stiffness gripper CLASH 2F, including three commercial sensors: a single taxel sensor from the companies Tacterion and Kinfinity, the Robotic Finger Sensor v2 from Sparkfun, plus a self-built resistive 3 × 3 sensor array, and two self-built magnetic 3-DoF touch sensors, one with four taxels and one with one taxel. We verify the minimal force detectable by the sensors, test if slip detection is possible with the available taxels on each sensor, and use the sensors for edge detection to obtain the orientation of the grasped object. To evaluate the benefits obtained with each technology and to assess which sensor fits better the control loop in a variable stiffness hand, we use the CLASH gripper to grasp fruits and vegetables following a published benchmark for pick and place operations. To facilitate the repetition of tests, the CLASH hand is endowed with tactile buttons that ease human–robot interactions, including execution of a predefined program, resetting errors, or commanding the full robot to move in gravity compensation mode.

Mass-Manufacturable 3D Magnetic Force Sensor for Robotic Grasping and Slip Detection

“…Despite this concern, piezo-resistive sensors constitute a solid alternative, and no single sensor (or sensing technologies) stands out. An optimum tactile sensor might be multi-modal, as suggested in [ 35 ].…”

Application of High-Photoelasticity Polyurethane to Tactile Sensor for Robot Hands

“…Various grasp sensors have been proposed [ 46 , 47 , 48 , 49 , 50 , 51 , 52 , 53 , 54 , 55 , 56 , 57 , 58 , 59 , 60 , 61 , 62 , 63 , 64 , 65 ], including MEMS sensors [ 51 , 52 , 53 , 54 , 55 , 56 , 57 , 58 , 59 , 60 , 61 , 62 , 63 ], some of which were able to measure normal and tangential forces [ 58 , 59 , 60 ]. However, they had complex structures and required special detection circuits.…”

Spectro-Temporal Recurrent Neural Network for Robotic Slip Detection with Piezoelectric Tactile Sensor

“…While this line of work relies on the assumption of a characteristic frequency pattern of slippage dynamics, research does not seem to converge to a simple solution and the vibration profile is dependent on a number of parameters of the environment, the robot sensor, and the interaction. Reported relevant frequencies for slip detection can range from 40Hz to 1kHz [11] [7] [2]. This again makes learning methods particularly relevant as they can extract features and find patterns for a wide range of setups, provided that training data has sufficient variability.…”