Methods and Sensors for Slip Detection in Robotics: A Survey

Romeo, Rocco Antonio; Zollo, Loredana

doi:10.1109/access.2020.2987849

Cited by 64 publications

(41 citation statements)

References 149 publications

(228 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In all the 50 grasping experiments, the reaction time

was smaller than 100 ms. This is in line with the human hand reaction time [ 20 ], which is also the most dexterous type of gripper in nature [ 1 ].…”

Section: Experiments and Resultssupporting

confidence: 72%

See 1 more Smart Citation

Combining Sensors Information to Enhance Pneumatic Grippers Performance

Romeo

Gesino

Maggiali

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

The gripper is the far end of a robotic arm. It is responsible for the contacts between the robot itself and all the items present in a work space, or even in a social space. Therefore, to provide grippers with intelligent behaviors is fundamental, especially when the robot has to interact with human beings. As shown in this article, we built an instrumented pneumatic gripper prototype that relies on different sensors’ information. Thanks to such information, the gripper prototype was able to detect the position of a given object in order to grasp it, to safely keep it between its fingers and to avoid slipping in the case of any object movement, even very small. The gripper performance was evaluated by means of a generic grasping algorithm for robotic grippers, implemented in the form of a state machine. Several slip tests were carried out on the pneumatic gripper, which showed a very fast response time and high reliability. Objects of various size, shape and hardness were employed to reproduce different grasping scenarios. We demonstrate that, through the use of force, torque, center of pressure and proximity information, the behavior of the developed pneumatic gripper prototype outperforms the one of the traditional pneumatic gripping devices.

show abstract

“…In all the 50 grasping experiments, the reaction time

was smaller than 100 ms. This is in line with the human hand reaction time [ 20 ], which is also the most dexterous type of gripper in nature [ 1 ].…”

Section: Experiments and Resultssupporting

confidence: 72%

“…One of such capabilities is that of slip avoidance [ 1 ]. To securely grasp an object, the gripper must not only grip it but also promptly react if slip takes place [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

Combining Sensors Information to Enhance Pneumatic Grippers Performance

Romeo

Gesino

Maggiali

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…An Inertial Measurement Unit (IMU) (Pololu, NV, USA) was attached on the object and stability of object was monitored by tracing the acceleration of IMU in three axis. Time series of IMU sensor readings and embedded force sensor readings were continuously recorded at 100 Hz which is within the range of 50–500 Hz of mechanical transients sensing by fast adapting type I (FA-I) and fast adapting type II (FA-II) tactile afferents in human skin sense (Romeo and Zollo, 2020 ). In post processing, rate of change of IMU acceleration in three axis (Ax, Ay, and Az) were analyzed.…”

Section: Grip State Estimation Network and Experimentsmentioning

confidence: 99%

Development and Grasp Stability Estimation of Sensorized Soft Robotic Hand

et al. 2021

View full text Add to dashboard Cite

This paper introduces the development of an anthropomorphic soft robotic hand integrated with multiple flexible force sensors in the fingers. By leveraging on the integrated force sensing mechanism, grip state estimation networks have been developed. The robotic hand was tasked to hold the given object on the table for 1.5 s and lift it up within 1 s. The object manipulation experiment of grasping and lifting the given objects were conducted with various pneumatic pressure (50, 80, and 120 kPa). Learning networks were developed to estimate occurrence of object instability and slippage due to acceleration of the robot or insufficient grasp strength. Hence the grip state estimation network can potentially feedback object stability status to the pneumatic control system. This would allow the pneumatic system to use suitable pneumatic pressure to efficiently handle different objects, i.e., lower pneumatic pressure (50 kPa) for lightweight objects which do not require high grasping strength. The learning process of the soft hand is made challenging by curating a diverse selection of daily objects, some of which displays dynamic change in shape upon grasping. To address the cost of collecting extensive training datasets, we adopted one-shot learning (OSL) technique with a long short-term memory (LSTM) recurrent neural network. OSL aims to allow the networks to learn based on limited training data. It also promotes the scalability of the network to accommodate more grasping objects in the future. Three types of LSTM-based networks have been developed and their performance has been evaluated in this study. Among the three LSTM networks, triplet network achieved overall stability estimation accuracy at 89.96%, followed by LSTM network with 88.00% and Siamese LSTM network with 85.16%.

show abstract

“…The sensor precisely recognized the vibration with a microscale amplitude, which shows the possibility that the sensor detects the microstructured surface topology and the slipping of objects. [43]…”

Section: Sensor Characterizationmentioning

confidence: 99%