Grasping Force Estimation Recognizing Object Slippage by Tactile Data Using Neural Network (original) (raw)
Related papers
Journal of Intelligent Systems, 2017
This paper presents an artificial neural network (ANN) trained on the patterns of slip signals; these patterns were generated by using conventional sensors with a novel design of fingertip mechanism for detecting the slippage of a grasped object under different types of dynamic loads. This design is to be used with an underactuated triple finger artificial hand based on the pulleys-tendon mechanism. The grasped object is designed in a prism shape with three direct current motors with unbalance rotating mass to generate excitation in the object. Also, this object is covered with different types of surface materials, namely, spongy rubber, glass, and wood. Three types of external loads are used to disturb the grasping process represented by quasi-static pulling on the object, the dynamic load on the object, and on the artificial arm in separate form. The mathematical modeling has been derived for the proposed design to generate the signal of contact force components ratio through usin...
Grasping force estimation detecting slip by tactile sensor adopting machine learning techniques
IEEE Region 10 Annual International Conference, Proceedings/TENCON, 2008
Adequate grasping force estimation and slip detection is a vital problem in wider applications of robots and manipulators in industries as well as in our everyday life. In this paper, a new methodology for slip detection during grasping by robot grippers/end-effectors using tactile sensor has been presented. During the object slippage, the tactile sensor in touch with the object surface travels along the peaks and valleys of surface texture of the object which creates vibratory motions in the tactile. A newly developed mathematical model is used to compute the scattered energy of vibrations, which contains parameters of surface texture geometry as well as trial grasping force, and other relevant parameters. Using the scattered energy of vibrations predicted by soft computing techniques, an attempt to instantly estimate the adequate grasping force has been reasonably successful. Surface texture data, for experimental estimation of grasping force, were collected from a huge number of machined specimens and were used to build four different machine learning estimation techniques. Experimental results using Linear Regression (LR), Simple Linear Regression (SLR), Pace Regression (PR) and Support Vector Machine (SVM) demonstrate a relatively better technique for industrial applications.
Neural network approach to firm grip in the presence of small slips
Journal of Robotic Systems, 2001
This paper presents a two stage method for constructing a firm grip that can tolerate small slips of the fingertips. The fingers are assumed to be of frictionless contact type. The first stage was to formulate the interaction in the gripper–object system as a linear complementarity problem (LCP). Then it was solved using a special neural network to find minimal fingers forces. The second stage was to use the obtained results in the first stage as a static mapping in training another neural network. The second neural network training included emulating the slips by random noise in the form of changes in the positions of the contact points relative to the reference coordinate system. This noisy training increased robustness against unexpected changes in fingers positions. Genetic algorithms were used in training the second neural network as global optimization techniques. The resulting neural network is a robust, reliable, and stable controller for rigid bodies that can be handled by a robot gripper. © 2001 John Wiley & Sons, Inc.
Distinguish the Textures of Grasped Objects by Robotic Hand Using Artificial Neural-Network
Engineering and Technology Journal, 2021
Arduino microcontroller and the Matlab program are integrated to acquire sensor data. Neural-Network used as an intelligent classifier to distinguish the object softness. The object identification properties with tactile sensing are valuable in interaction with the environment for both humans and robots, and it is the core of sensing used for exploration and determining properties of objects that are inaccessible from visual perception. Object identification often involves with rigid mechanical grippers, tactile information and intelligent algorithms. This paper proposes a methodology for feature extraction techniques and discriminates objects for different softness using adaptive robotic grippers, which are equipped with force and angle sensors in each four fingers of an underactuated robot hand. Arduino microcontroller and the Matlab program are integrated to acquire sensor data and to control the gripping action. The neuralnetwork method used as an intelligent classifier to distinguish between different object softness by using feature vector acquired from the force sensor measurements and actuator positions in time series response during the grasping process using only a single closure grasping. The proposed method efficiency was validated using experimental paradigms that involving three sets of model objects and everyday life objects with various shapes, stiffness, and sizes.
Featureless classification of tactile contacts in a gripper using neural networks
Sensors and Actuators A: Physical, 1997
A direct, featureless process to classify contact impressions of objects gripped by a robot hand is presented. The inforlnation about the type of contact allows the selection of the most appropriate manipulating strategy to handle the grasped object. A learning vector quantization (LVQ) network is applied introducing a contact-pattern preprocessing technique to improve the robustness of tbe classification with respect to the pattern variations in position, orientation and size. © 1997 Elsevier Science S.A.
A Neural Network Approach to the Frictionless Grasping Problem
Journal of Intelligent and Robotic Systems, 2000
This article presents a heuristic technique used for solving linear complementarity problems(LCP). Determination of minimum forces needed to firmly grasp an object by a multifingered robot gripper for different external force and finger positions is our proposed application. The contact type is assumed to be frictionless. The interaction in the gripper–object system is formulated as an LCP. A numerical algorithm (Lemke) is used to solve the problem [3]. Lemke is a direct deterministic method that finds exact solutions under some constraints. Our proposed neural network technique finds almost exact solutions in solvable positions, and very good solutions for positions that Lemke fails to find solutions. A new adaptive technique is used for training the neural network and it is compared with the standard technique. Mathematical analysis for the convergence of the proposed technique is presented.
Tactile-Driven Grasp Stability and Slip Prediction
Robotics, 2019
One of the challenges in robotic grasping tasks is the problem of detecting whether a grip is stable or not. The lack of stability during a manipulation operation usually causes the slippage of the grasped object due to poor contact forces. Frequently, an unstable grip can be caused by an inadequate pose of the robotic hand or by insufficient contact pressure, or both. The use of tactile data is essential to check such conditions and, therefore, predict the stability of a grasp. In this work, we present and compare different methodologies based on deep learning in order to represent and process tactile data for both stability and slip prediction.
Artificial Intelligence-Based Optimal Grasping Control
Sensors, 2020
A new tactile sensing module was proposed to sense the contact force and location of an object on a robot hand, which was attached on the robot finger. Three air pressure sensors are installed at the tip of the finger to detect the contacting force at the points. To obtain a nominal contact force at the finger from data from the three air pressure sensors, a force estimation was developed based upon the learning of a deep neural network. The data from the three air pressure sensors were utilized as inputs to estimate the contact force at the finger. In the tactile module, the arrival time of the air pressure sensor data has been utilized to recognize the contact point of the robot finger against an object. Using the three air pressure sensors and arrival time, the finger location can be divided into 3 × 3 block locations. The resolution of the contact point recognition was improved to 6 × 4 block locations on the finger using an artificial neural network. The accuracy and effectiven...
Gaining a Sense of Touch. Physical Parameters Estimation using a Soft Gripper and Neural Networks
ArXiv, 2020
Soft grippers are gaining significant attention in the manipulation of elastic objects, where it is required to handle soft and unstructured objects which are vulnerable to deformations. A crucial problem is to estimate the physical parameters of a squeezed object to adjust the manipulation procedure, which is considered as a significant challenge. To the best of the authors' knowledge, there is not enough research on physical parameters estimation using deep learning algorithms on measurements from direct interaction with objects using robotic grippers. In our work, we proposed a trainable system for the regression of a stiffness coefficient and provided extensive experiments using the physics simulator environment. Moreover, we prepared the application that works in the real-world scenario. Our system can reliably estimate the stiffness of an object using the Yale OpenHand soft gripper based on readings from Inertial Measurement Units (IMUs) attached to its fingers. Additional...
Grasping Force Controlling by Slip Detection for Specific Artificial Hand (ottobock 8E37)
Engineering and Technology Journal, 2018
This paper presents a theoretical and experimental study to control grasping force of specific artificial hand (Otto Bock 8E37), which it uses by amputees. The hand has two rigid fingers actuated by a DC motor through a multigears system. The aim of this work is to give the amputees a feeling of slipping while the hand grasping an object. The mathematical model has been derived to simulate the hand mechanism and analyze the generated signal of contact force between fingertip and the grasped object through a slippage phenomenon. The experimental work consisted of modifying the artificial hand design to aid load cell mounting process in order to measure the grasping force indirectly, then acquiring the measured signal to the PC. An artificial neural network (ANN) was trained on the patterns of the force signals. These patterns were prepared by using force sensors with modified design of the artificial hand for detecting the slippage of the different shapes grasped object. The Neural Network training results have been evaluated and discussed under different conditions, which affect the controller operation such as network error, classification percentage and the response time delay.