scholarly journals End-Effector Force and Joint Torque Estimation of a 7-DoF Robotic Manipulator Using Deep Learning

Electronics ◽  
2021 ◽  
Vol 10 (23) ◽  
pp. 2963
Author(s):  
Stanko Kružić ◽  
Josip Musić ◽  
Roman Kamnik ◽  
Vladan Papić
Keyword(s):  
Mean Squared Error ◽  
Force Sensor ◽  
Robotic Manipulator ◽  
Joint Torque ◽  
Estimation Methods ◽  
Robot Dynamics ◽  
Force Estimation ◽  
End Effector ◽  
Squared Error ◽  
Torque Estimation

When a mobile robotic manipulator interacts with other robots, people, or the environment in general, the end-effector forces need to be measured to assess if a task has been completed successfully. Traditionally used force or torque estimation methods are usually based on observers, which require knowledge of the robot dynamics. Contrary to this, our approach involves two methods based on deep neural networks: robot end-effector force estimation and joint torque estimation. These methods require no knowledge of robot dynamics and are computationally effective but require a force sensor under the robot base. Several different architectures were considered for the tasks, and the best ones were identified among those tested. First, the data for training the networks were obtained in simulation. The trained networks showed reasonably good performance, especially using the LSTM architecture (with a root mean squared error (RMSE) of 0.1533 N for end-effector force estimation and 0.5115 Nm for joint torque estimation). Afterward, data were collected on a real Franka Emika Panda robot and then used to train the same networks for joint torque estimation. The obtained results are slightly worse than in simulation (0.5115 Nm vs. 0.6189 Nm, according to the RMSE metric) but still reasonably good, showing the validity of the proposed approach.

scholarly journals Reducing the Bias of the Smoothed Log Periodogram Regression for Financial High-Frequency Data

Econometrics ◽  
2020 ◽  
Vol 8 (4) ◽  
pp. 40
Author(s):  
Erhard Reschenhofer ◽  
Manveer K. Mangat
Keyword(s):  
Simulation Study ◽  
High Frequency ◽  
Mean Squared Error ◽  
Estimation Methods ◽  
High Frequency Data ◽  
Frequency Data ◽  
Periodic Patterns ◽  
Typical Sample ◽  
Squared Error ◽  
Proper Interpretation

For typical sample sizes occurring in economic and financial applications, the squared bias of estimators for the memory parameter is small relative to the variance. Smoothing is therefore a suitable way to improve the performance in terms of the mean squared error. However, in an analysis of financial high-frequency data, where the estimates are obtained separately for each day and then combined by averaging, the variance decreases with the sample size but the bias remains fixed. This paper proposes a method of smoothing that does not entail an increase in the bias. This method is based on the simultaneous examination of different partitions of the data. An extensive simulation study is carried out to compare it with conventional estimation methods. In this study, the new method outperforms its unsmoothed competitors with respect to the variance and its smoothed competitors with respect to the bias. Using the results of the simulation study for the proper interpretation of the empirical results obtained from a financial high-frequency dataset, we conclude that significant long-range dependencies are present only in the intraday volatility but not in the intraday returns. Finally, the robustness of these findings against daily and weekly periodic patterns is established.

scholarly journals Comparison of Some of Estimation methods of Stress-Strength Model: R = P(Y < X < Z)

2021 ◽  
Vol 18 (2(Suppl.)) ◽  
pp. 1103
Author(s):  
Sairan Hamza Raheem ◽  
Bayda Atiya Kalaf ◽  
Abbas Najim Salman
Keyword(s):  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Moment Method ◽  
Mean Squared Error ◽  
Rayleigh Distribution ◽  
Minimum Variance ◽  
Estimation Methods ◽  
Strength Model ◽  
Minimum Variance Unbiased Estimator ◽  
Squared Error

In this study, the stress-strength model R = P(Y < X < Z)  is discussed as an important parts of reliability system by assuming that the random variables follow Invers Rayleigh Distribution. Some traditional estimation methods are used    to estimate the parameters  namely; Maximum Likelihood, Moment method, and Uniformly Minimum Variance Unbiased estimator and Shrinkage estimator using three types of shrinkage weight factors. As well as, Monte Carlo simulation are used to compare the estimation methods based on mean squared error criteria.  

scholarly journals Respiratory Rate Estimation Based on Spectrum Decomposition

2018 ◽  
Author(s):  
SeungJae Lee ◽  
Soo-Yong Kim
Keyword(s):  
Respiratory Rate ◽  
Mean Squared Error ◽  
Physiological State ◽  
Singular Spectrum Analysis ◽  
Estimation Methods ◽  
Ecg Signals ◽  
Squared Error ◽  
Transthoracic Impedance ◽  
Electrocardiogram Ecg ◽  
Spectrum Decomposition

We propose an electrocardiogram (ECG) signal-based algorithm to estimate the respiratory rate is a significant informative indicator of physiological state of a patient. The consecutive ECG signals reflect the information about the respiration because inhalation and exhalation make transthoracic impedance vary. The proposed algorithm extracts the respiration-related signal by finding out the commonality between the frequency and amplitude features in the ECG pulse train. The respiration rate can be calculated from the principle components after the procedure of the singular spectrum analysis. We achieved 1.7569 breaths per min of root-mean-squared error and 1.7517 of standard deviation with a 32-seconds signal window of the Capnobase dataset, which gives notable improvement compared with the conventional Autoregressive model based estimation methods.

Estimating the Parameter of a Selected Population

1995 ◽  
Vol 45 (1-2) ◽  
pp. 93-102 ◽  
Author(s):  
Tapan Kumar Nayak
Keyword(s):  
Unbiased Estimator ◽  
Selection Rule ◽  
Random Quantity ◽  
Mean Squared Error ◽  
Minimum Variance ◽  
Estimation Methods ◽  
Unknown Parameters ◽  
Sufficient Statistic ◽  
Minimum Mean Squared Error ◽  
Squared Error

Suppose independent samples from k populations with unknown parameters are taken and one of the populations is selected based on tho data and a prespecified rule. The problem is to estimate the parameter of the selected population. The estimand, G, is a random quantity which depends on both the data and the unknown parameters. While standard estimation methods are inadequate for estimating G, they can be used to estimate the expected value of G. It is shown that the uniformly minimum variance unbiased estimator of E( G) is also the uniformly minimum mean squared error unbiased estimator of G, if the selection rule depends on the data only through a complete sufficient statistic. An approach based on conditional unbiasedness is also discussed.

Correcting the Bias of Spike Field Coherence Estimators Due to a Finite Number of Spikes

2010 ◽  
Vol 104 (1) ◽  
pp. 548-558 ◽  
Author(s):  
D. W. Grasse ◽  
K. A. Moxon
Keyword(s):  
Finite Number ◽  
Bias Correction ◽  
Mean Squared Error ◽  
Estimation Methods ◽  
Oscillatory Activity ◽  
Experimental Conditions ◽  
Squared Error ◽  
Neural Substrate ◽  
Field Coherence ◽  
Single Neuron Action

The coherence between oscillatory activity in local field potentials (LFPs) and single neuron action potentials, or spikes, has been suggested as a neural substrate for the representation of information. The power spectrum of a spike-triggered average (STA) is commonly used to estimate spike field coherence (SFC). However, when a finite number of spikes is used to construct the STA, the coherence estimator is biased. We introduce here a correction for the bias imposed by the limited number of spikes available in experimental conditions. In addition, we present an alternative method for estimating SFC from an STA by using a filter bank approach. This method is shown to be more appropriate in some analyses, such as comparing coherence across frequency bands. The proposed bias correction is a linear transformation derived from an idealized model of spike–field interaction but is shown to hold in more realistic settings. Uncorrected and corrected SFC estimates from both estimation methods are compared across multiple simulated spike–field models and experimentally collected data. The bias correction was shown to reduce the bias of the estimators, but add variance. However, the corrected estimates had a reduced or unchanged mean squared error in the majority of conditions evaluated. The bias correction provides an effective way to reduce bias in an SFC estimator without increasing the mean squared error.

scholarly journals On Estimation of P(Y_1

2020 ◽  
pp. 845-853 ◽  
Author(s):  
Bsma Abdul Hameed ◽  
Abbas N. Salman ◽  
Bayda Atiya Kalaf
Keyword(s):  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Maximum Likelihood ◽  
Mean Squared Error ◽  
Estimation Methods ◽  
Simulation Experiments ◽  
Kumaraswamy Distribution ◽  
Shrinkage Methods ◽  
Squared Error ◽  
The Mean

This paper deals with the estimation of the stress strength reliability for a component which has a strength that is independent on opposite lower and upper bound stresses, when the stresses and strength follow Inverse Kumaraswamy Distribution. D estimation approaches were applied, namely the maximum likelihood, moment, and shrinkage methods. Monte Carlo simulation experiments were performed to compare the estimation methods based on the mean squared error criteria.

Placement of a Robotic Manipulator for Traversing a Path in Minimum Time

1997 ◽  
Author(s):  
Murali Kathari ◽  
Mohamed B. Trabia
Keyword(s):  
Nonlinear Programming ◽  
Robotic Manipulator ◽  
Joint Torque ◽  
End Effector ◽  
Minimum Path ◽  
Traversal Time ◽  
Base Locus ◽  
Programming Techniques ◽  
Joint Limits ◽  
Base Location

Abstract Productivity of a robotic manipulator depends to a large extent on the time it takes to traverse a path. The path traversal time is in turn a dependent, among several other factors, on the manipulator location within the workcell. This paper defines the robot base locus boundaries when the end-effector path is prescribed. Effects of joint limits and obstacle presence on the robot base locus are also considered. The proposed algorithm searches the robot base locus to determine the robot base location that yields the minimum path traversal time, location subject to the robot joint torque constraints, using nonlinear programming techniques.

scholarly journals A Comparative Approach to Hand Force Estimation using Artificial Neural Networks

2012 ◽  
Vol 4 ◽  
pp. BECB.S9335 ◽  
Author(s):  
Farid Mobasser ◽  
Keyvan Hashtrudi-Zaad
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Joint Torque ◽  
Estimation Methods ◽  
Comparative Approach ◽  
Joint Movement ◽  
Force Estimation ◽  
Emg Signal ◽  
Hand Force ◽  
Artificial Neural

In many applications that include direct human involvement such as control of prosthetic arms, athletic training, and studying muscle physiology, hand force is needed for control, modeling and monitoring purposes. The use of inexpensive and easily portable active electromyography (EMG) electrodes and position sensors would be advantageous in these applications compared to the use of force sensors which are often very expensive and require bulky frames. Among non-model-based estimation methods, Multilayer Perceptron Artificial Neural Networks (MLPANN) has widely been used to estimate muscle force or joint torque from different anatomical features in humans or animals. This paper investigates the use of Radial Basis Function (RBF) ANN and MLPANN for force estimation and experimentally compares the performance of the two methodologies for the same human anatomy, ie, hand force estimation, under an ensemble of operational conditions. In this unified study, the EMG signal readings from upper-arm muscles involved in elbow joint movement and elbow angular position and velocity are utilized as inputs to the ANNs. In addition, the use of the elbow angular acceleration signal as an input for the ANNs is also investigated.

scholarly journals Multicomponent Inverse Lomax Stress-Strength Reliability

2020 ◽  
pp. 72-80
Author(s):  
Nada S. Karam ◽  
Shahbaa M. Yousif ◽  
Bushra J. Tawfeeq
Keyword(s):  
Maximum Likelihood ◽  
Mean Squared Error ◽  
Scale Parameter ◽  
Model Systems ◽  
Estimation Methods ◽  
Squared Error ◽  
Mathematical Expressions ◽  
Distribution Parameters ◽  
The Mean ◽  
Inverse Lomax Distribution

In this article we derive two reliability mathematical expressions of two kinds of s-out of -k stress-strength model systems; and . Both stress and strength are assumed to have an Inverse Lomax distribution with unknown shape parameters and a common known scale parameter. The increase and decrease in the real values of the two reliabilities are studied according to the increase and decrease in the distribution parameters. Two estimation methods are used to estimate the distribution parameters and the reliabilities, which are Maximum Likelihood and Regression. A comparison is made between the estimators based on a simulation study by the mean squared error criteria, which revealed that the maximum likelihood estimator works the best.

Different Estimation Methods for System Reliability Multi-Components model: Exponentiated Weibull Distribution

2018 ◽  
pp. 368
Author(s):  
Abbas Najim Salman ◽  
Fatima Hadi Sail
Keyword(s):  
Weibull Distribution ◽  
System Reliability ◽  
Shape Parameter ◽  
Mean Squared Error ◽  
Independent Random Variables ◽  
Estimation Methods ◽  
Monte Carlo Simulation Technique ◽  
Squared Error ◽  
Exponentiated Weibull Distribution ◽  
Exponentiated Weibull

        In this paper, estimation of system reliability of the multi-components in stress-strength model R(s,k) is considered, when the stress and strength are independent random variables and follows the Exponentiated Weibull Distribution (EWD) with known first shape parameter θ and, the second shape parameter α is unknown using different estimation methods. Comparisons among the proposed estimators through  Monte Carlo simulation technique were made depend on mean squared error (MSE)  criteria

Sign in / Sign up

Export Citation Format

Share Document