scholarly journals Tactile-Driven Grasp Stability and Slip Prediction

Robotics ◽  
2019 ◽  
Vol 8 (4) ◽  
pp. 85 ◽  
Author(s):  
Brayan S. Zapata-Impata ◽  
Pablo Gil ◽  
Fernando Torres
Keyword(s):  
Deep Learning ◽  
Contact Pressure ◽  
Contact Forces ◽  
Robotic Hand ◽  
Robotic Grasping ◽  
Grasp Stability ◽  
The Stability

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.

On the Influence of Contact Geometry on Grasp Stability

2008 ◽  
Author(s):  
Gert A. Kragten ◽  
Just L. Herder ◽  
A. L. Schwab
Keyword(s):  
Contact Stiffness ◽  
Contact Geometry ◽  
Contact Forces ◽  
Minor Effect ◽  
Dynamic Simulations ◽  
Normal Contact ◽  
Contact Points ◽  
Grasp Stability ◽  
The Stability ◽  
A Minor

This paper demonstrates that the predicted grasp stability is highly sensitive to only small changes in the character of the contact forces. The contribution of the geometry and stiffness at the contact points to the grasp stability is investigated by a planar grasp with three contact points. Limit cases of zero and infinite contact curvatures, and finite to infinite contact stiffnesses are considered. The stability is predicted based on the approach of Howard and Kumar [1], and verified with multibody dynamic simulations. For rigid objects and fingers with only normal contact stiffness, the grasp stability is dominated by the contact geometry, whereas the local contact stiffness and preload have a minor effect. Furthermore, grasps with pointed finger tips are more likely to be stable than grasps with flat finger tips.

scholarly journals On-Orbit Robotic Grasping of a Spent Rocket Stage: Grasp Stability Analysis and Experimental Results

2021 ◽  
Vol 8 ◽  
Author(s):  
Nikos Mavrakis ◽  
Zhou Hao ◽  
Yang Gao
Keyword(s):  
Space Debris ◽  
Robotic Grasping ◽  
Target Mass ◽  
Grasp Stability ◽  
Grasping And Manipulation ◽  
Real Robot ◽  
The Subject ◽  
The Stability ◽  
Intrinsic Stiffness ◽  
Robotic Grasp

The increased complexity of the tasks that on-orbit robots have to undertake has led to an increased need for manipulation dexterity. Space robots can become more dexterous by adopting grasping and manipulation methodologies and algorithms from terrestrial robots. In this paper, we present a novel methodology for evaluating the stability of a robotic grasp that captures a piece of space debris, a spent rocket stage. We calculate the Intrinsic Stiffness Matrix of a 2-fingered grasp on the surface of an Apogee Kick Motor nozzle and create a stability metric that is a function of the local contact curvature, material properties, applied force, and target mass. We evaluate the efficacy of the stability metric in a simulation and two real robot experiments. The subject of all experiments is a chasing robot that needs to capture a target AKM and pull it back towards the chaser body. In the V-REP simulator, we evaluate four grasping points on three AKM models, over three pulling profiles, using three physics engines. We also use a real robotic testbed with the capability of emulating an approaching robot and a weightless AKM target to evaluate our method over 11 grasps and three pulling profiles. Finally, we perform a sensitivity analysis to demonstrate how a variation on the grasping parameters affects grasp stability. The results of all experiments suggest that the grasp can be stable under slow pulling profiles, with successful pulling for all targets. The presented work offers an alternative way of capturing orbital targets and a novel example of how terrestrial robotic grasping methodologies could be extended to orbital activities.

Robotic grasping: from wrench space heuristics to deep learning policies

2021 ◽  
Vol 71 ◽  
pp. 102176
Author(s):  
João Pedro Carvalho de Souza ◽  
Luís F. Rocha ◽  
Paulo Moura Oliveira ◽  
A. Paulo Moreira ◽  
José Boaventura-Cunha
Keyword(s):  
Deep Learning ◽  
Robotic Grasping ◽  
Learning Policies

scholarly journals CAPSULE NETWORK BASED BIOMETRIC RECOGNITION SYSTEM

2019 ◽  
Vol 2019 (2) ◽  
pp. 83-94 ◽  
Author(s):  
Dr. I. Jeena Jacob
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Recognition System ◽  
Noise Removal ◽  
Personal Identification ◽  
Biometric Recognition ◽  
Learning Techniques ◽  
Frame Work ◽  
The Stability

The biometric recognition plays a significant and a unique part in the applications that are based on the personal identification. This is because of the stability, irreplaceability and the uniqueness that is found in the biometric traits of the humans. Currently the deep learning techniques that are capable of strongly generalizing and automatically learning, with the enhanced accuracy is utilized for the biometric recognition to develop an efficient biometric system. But the poor noise removal abilities and the accuracy degradation caused due to the very small disturbances has made the conventional means of the deep learning that utilizes the convolutional neural network incompatible for the biometric recognition. So the capsule neural network replaces the CNN due to its high accuracy in the recognition and the classification, due to its learning capacities and the ability to be trained with the limited number of samples compared to the CNN (convolutional neural network). The frame work put forward in the paper utilizes the capsule network with the fuzzified image enhancement for the retina based biometric recognition as it is a highly secure and reliable basis of person identification as it is layered behind the eye and cannot be counterfeited. The method was tested with the dataset of face 95 database and the CASIA-Iris-Thousand, and was found to be 99% accurate with the error rate convergence of 0.3% to .5%

Calculation of Contact Forces of Large-Scale Heavy Forging Manipulator Grippers

2009 ◽  
Vol 419-420 ◽  
pp. 645-648 ◽  
Author(s):  
Qun Ming Li ◽  
Dan Gao ◽  
Hua Deng
Keyword(s):  
Large Scale ◽  
Optimization Method ◽  
Contact Forces ◽  
Robotic Hand ◽  
Closure Condition ◽  
Contact Points ◽  
Robot Hands ◽  
Calculation Results ◽  
Forging Manipulator ◽  
Gripping Force

Different from dexterous robotic hands, the gripper of heavy forging manipulator is an underconstrained mechanism whose tongs are free in a small wiggling range. However, for both a dexterous robotic hand and a heavy gripper, the force closure condition: the force and the torque equilibrium, must be satisfied without exception to maintain the grasping/gripping stability. This paper presents a gripping model for the heavy forging gripper with equivalent friction points, which is similar to a grasp model of multifingered robot hands including four contact points. A gripping force optimization method is proposed for the calculation of contact forces between gripper tongs and forged object. The comparison between the calculation results and the experimental results demonstrates the effectiveness of the proposed calculation method.

Rolling Condition and Gyroscopic Moments in Curve Negotiations

2012 ◽  
Author(s):  
Ahmed A. Shabana ◽  
Martin B. Hamper ◽  
James J. O’Shea
Keyword(s):  
Coordinate System ◽  
Degrees Of Freedom ◽  
The Body ◽  
Contact Forces ◽  
Body Motion ◽  
Global Coordinate System ◽  
Gyroscopic Moment ◽  
Absolute Angular Velocity ◽  
Pure Rolling ◽  
The Stability

In vehicle system dynamics, the effect of the gyroscopic moments can be significant during curve negotiations. The absolute angular velocity of the body can be expressed as the sum of two vectors; one vector is due to the curvature of the curve, while the second vector is due to the rate of changes of the angles that define the orientation of the body with respect to a coordinate system that follows the body motion. In this paper, the configuration of the body in the global coordinate system is defined using the trajectory coordinates in order to examine the effect of the gyroscopic moments in the case of curve negotiations. These coordinates consist of arc length, two relative translations and three relative angles. The relative translations and relative angles are defined with respect to a trajectory coordinate system that follows the motion of the body on the curve. It is shown that when the yaw and roll angles relative to the trajectory coordinate system are constrained and the motion is predominantly rolling, the effect of the gyroscopic moment on the motion becomes negligible, and in the case of pure rolling and zero yaw and roll angles, the generalized gyroscopic moment associated with the system degrees of freedom becomes identically zero. The analysis presented in this investigation sheds light on the danger of using derailment criteria that are not obtained using laws of motion, and therefore, such criteria should not be used in judging the stability of railroad vehicle systems. Furthermore, The analysis presented in this paper shows that the roll moment which can have a significant effect on the wheel/rail contact forces depends on the forward velocity in the case of curve negotiations. For this reason, roller rigs that do not allow for the wheelset forward velocity cannot capture these moment components, and therefore, cannot be used in the analysis of curve negotiations. A model of a suspended railroad wheelset is used in this investigation to study the gyroscopic effect during curve negotiations.

Study of grasp-energy based optimal distribution of contact forces on a humanoid robotic hand during object grasp

Robotica ◽  
2021 ◽  
pp. 1-26
Author(s):  
Sourajit Mukherjee ◽  
Abhijit Mahapatra ◽  
Amit Kumar ◽  
Avik Chatterjee
Keyword(s):  
Optimization Algorithm ◽  
Degrees Of Freedom ◽  
Simulated Data ◽  
Performance Measure ◽  
Contact Forces ◽  
Contact Model ◽  
Robotic Hand ◽  
Net Energy ◽  
Optimal Distribution

Abstract A novel grasp optimization algorithm for minimizing the net energy utilized by a five-fingered humanoid robotic hand with twenty degrees of freedom for securing a precise grasp is presented in this study. The algorithm utilizes a compliant contact model with a nonlinear spring and damper system to compute the performance measure, called ‘Grasp Energy’. The measure, subject to constraints, has been minimized to obtain locally optimal cartesian trajectories for securing a grasp. A case study is taken to compare the analytical (applying the optimization algorithm) and the simulated data in MSC.Adams $^{^{\circledR}}$ , to prove the efficacy of the proposed formulation.

scholarly journals An Intelligent Multi-View Active Learning Method Based on a Double-Branch Network

Entropy ◽  
2020 ◽  
Vol 22 (8) ◽  
pp. 901
Author(s):  
Fucong Liu ◽  
Tongzhou Zhang ◽  
Caixia Zheng ◽  
Yuanyuan Cheng ◽  
Xiaoli Liu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Active Learning ◽  
Sample Selection ◽  
Training Dataset ◽  
Learning Method ◽  
Active Learning Method ◽  
Level Information ◽  
The Stability ◽  
Different Characteristics

Artificial intelligence is one of the most popular topics in computer science. Convolutional neural network (CNN), which is an important artificial intelligence deep learning model, has been widely used in many fields. However, training a CNN requires a large amount of labeled data to achieve a good performance but labeling data is a time-consuming and laborious work. Since active learning can effectively reduce the labeling effort, we propose a new intelligent active learning method for deep learning, which is called multi-view active learning based on double-branch network (MALDB). Different from most existing active learning methods, our proposed MALDB first integrates two Bayesian convolutional neural networks (BCNNs) with different structures as two branches of a classifier to learn the effective features for each sample. Then, MALDB performs data analysis on unlabeled dataset and queries the useful unlabeled samples based on different characteristics of two branches to iteratively expand the training dataset and improve the performance of classifier. Finally, MALDB combines multiple level information from multiple hidden layers of BCNNs to further improve the stability of sample selection. The experiments are conducted on five extensively used datasets, Fashion-MNIST, Cifar-10, SVHN, Scene-15 and UIUC-Sports, the experimental results demonstrate the validity of our proposed MALDB.

Object Manipulation Using Compliant Fingerpads: Modeling and Control

1993 ◽  
Vol 115 (4) ◽  
pp. 638-648 ◽  
Author(s):  
A. M. Annaswamy ◽  
D. Seto
Keyword(s):  
Adaptive Control ◽  
Feedback Linearization ◽  
Industrial Robots ◽  
Dynamic Interactions ◽  
Modeling And Control ◽  
Grasp Stability ◽  
Grasping And Manipulation ◽  
End Effectors ◽  
Geometric Techniques ◽  
The Stability

Current industrial robots are often required to perform tasks requiring mechanical interactions with their environment. For tasks that require grasping and manipulation of unknown objects, it is crucial for the robot end-effector to be compliant to increase grasp stability and manipulability. The dynamic interactions that occur between such compliant end-effectors and deformable objects that are being manipulated can be described by a class of nonlinear systems. In this paper, we determine algorithms for grasping and manipulation of these objects by using adaptive feedback techniques. Methods for control and adaptive control of the underlying nonlinear system are described. It is shown that although standard geometric techniques for exact feedback linearization techniques are inadequate, yet globally stable adaptive control algorithms can be determined by making use of the stability characteristics of the underlying nonlinear dynamics.

Optimization of Quadriceps Force Distribution for Minimization of Patellofemoral Contact Pressure During a Squat

2007 ◽  
Author(s):  
Aarthi S. Shankar ◽  
Trent M. Guess
Keyword(s):  
Contact Pressure ◽  
Vastus Lateralis ◽  
Rectus Femoris ◽  
Strong Relationship ◽  
Lateral Force ◽  
Quadriceps Muscle ◽  
Contact Forces ◽  
In Vivo Studies ◽  
Muscle Forces

Patellofemoral Pain (PFP) syndrome is a very common knee disorder. A possible cause may be excessive lateral force applied by the quadriceps and the patellar tendon producing an abnormal distribution of force and pressure within the patellofemoral joint [1]. EMG and in-vivo studies have been conducted to understand the function of the quadriceps and its relationship with PFP [2,3]. These studies suggest a strong relationship between muscle forces and PFP which originates from high lateral retropatellar contact forces. A dynamic computational model of the knee was developed which includes the quadriceps muscles Rectus Femoris (RF), Vastus Intermedius (VI), Vastus Lateralis (VL), and Vastus Medialis (VM) represented as force vectors. The model can predict retro-patellar contact pressures and the action of the individual quadriceps muscles based on the predicted pressures. The objective of this study was to develop a control system which could optimize the distribution of quadriceps muscle forces to minimize contact pressure between the patella and the femur of the knee during a squat.

Sign in / Sign up

Export Citation Format

Share Document