Article
A Non-Array Type Cut to Shape Soft Slip Detection
Sensor Applicable to Arbitrary Surface
Sung Joon Kim , Seung Ho Lee , Hyungpil Moon , Hyouk Ryeol Choi and Ja Choon Koo *
School of Mechanical Engineering, Sungkyunkwan University, Suwon 16419, Korea; sjkim314@skku.edu (S.J.K.);
smilepop@skku.edu (S.H.L.); hyungpil@me.skku.ac.kr (H.M.); hrchoi@me.skku.ac.kr (H.R.C.)
* Correspondence: jckoo@skku.edu
Received: 10 October 2020; Accepted: 28 October 2020; Published: 30 October 2020
Abstract:
The presence of a tactile sensor is essential to hold an object and manipulate it without
damage. The tactile information helps determine whether an object is stably held. If a tactile sensor
is installed at wherever the robot and the object touch, the robot could interact with more objects.
In this paper, a skin type slip sensor that can be attached to the surface of a robot with various
curvatures is presented. A simple mechanical sensor structure enables the cut and fit of the sensor
according to the curvature. The sensor uses a non-array structure and can operate even if a part of
the sensor is cut off. The slip was distinguished using a simple vibration signal received from the
sensor. The signal is transformed into the time-frequency domain, and the slippage was determined
using an artificial neural network. The accuracy of slip detection was compared using four artificial
neural network models. In addition, the strengths and weaknesses of each neural network model
were analyzed according to the data used for training. As a result, the developed sensor detected slip
with an average of 95.73% accuracy at various curvatures and contact points.
Keywords: tactile sensor; e-skin; slip detection
1. Introduction
The sense of touch is a handy tool when picking up or manipulating objects. Checking the
hardness of an object, distinguishing the texture of the surface, and determining the degree of friction
are very difficult without the sense of touch. Just as a person acquires information about an object by
tactile sense, a robot can also acquire information of an object using a tactile sensor [1]. When a robot
repeats routine tasks in a factory, tactile sensors are rarely needed. All objects to be manipulated are in a
known state, and tactile sensors have no role. However, as robotic technology advances, robots are now
out of the factory to do a dexterous task, and tactile sensors can be utilized at this time [
2
]. In particular,
tactile sensors play a significant role when holding and manipulating unknown objects [
3
]. When a
robot gets out of the existing factory and performs the role of a service robot, it is essential to grasp
and manipulate the unknown objects [4].
Conventional tactile sensors measure the vertical force, shear force, torque, and temperature when
interacting with an object. Now, sensors that acquire higher-level information using signal processing
are being developed [
5
]. They measure the normal force, shear force, and vibration of the surface to
distinguish the material or detect slip on objects. Knowing the slip between an object and a tactile
sensor is of great benefit when manipulating an object. If the gripping force increased when the object
is slipping, the risk of the robot hand dropping the object could be eliminated [
6
]. Furthermore, if the
robot changes the control method, it can avoid the risk of breaking the object with excessive force [
7
].
For this reason, research on the slip detection sensor is very active [8].
Various signal processing methods are performed to determine the surface information of an
object or whether it slips [
5
]. Numerous studies have used artificial neural networks (ANN), a type
Sensors 2020, 20, 6185; doi:10.3390/s20216185 www.mdpi.com/journal/sensors
