Modeling in Two Configurations of a 5R 2-DoF Planar Parallel Mechanism and Solution to the Inverse Kinematic Modeling Using Artificial Neural Network

López, Eusebio Jiménez; Mora-Pulido, Daniel Servin De La; Mora-Pulido, Raúl Servín de la; Ochoa-Estrella, F. J.; Flores, Mario Acosta; Luna-Sandoval, Gabriel

doi:10.1109/access.2021.3073402

Cited by 6 publications

(5 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Algoritma-algoritma ini diterapkan dengan menggunakan data joint space dan end-effector/platform space manipulator paralel berdasarkan jawab kinematika inversnya. Penggunaan artificial neural network (jaringan syaraf tiruan) sebagai salah satu bagian dari pembelajaran mesin cukup banyak dilakukan dalam memodelkan jawab kinematika langsung manipulator paralel [6]- [9]. Sementara itu, penggunaan algoritmaalgoritma pembelajaran mesin seperti decision tree, support vector machines, random forest belum ditemui untuk penentuan jawab kinematika langsung.…”

Section: Pendahuluanunclassified

“…Pembahasan yang cukup mendalam dilakukan oleh Lopez, dkk [6] menggunakan jaringan syaraf tiruan dalam memodelkan jawab kinematika lagsung manipulator paralel bidang 5R. Dataset dari jawab kinematika invers diperoleh dengan mendiskritiasi workspace secara merata.…”

Section: Pendahuluanunclassified

“…Parameter Nilai max_depth_tree [8,12,16,20,24,28,32,None] min_samples_split [2,4,6,8,10] min_samples_leaf [1,2,3,4,5] Penerapan 4-fold cross validation pada penggunaan hyperparameter tuning melalui grid search diilustrasikan pengaplikasiannya seperti pada Gambar 2. Penerapan ini dilakukan untuk setiap dataset dari ketiga dataset yang digunakan.…”

Section: Materials Dan Metodeunclassified

See 2 more Smart Citations

An Application of Decission Tree for Modeling the Direct Kinematic Solution of 5R Planar Parallel Manipulator

Adriyan¹

2021

JTM

View full text Add to dashboard Cite

This article addressed a machine learning approach for determining a solution model for the direct kinematic problems of parallel manipulators. A 5R planar parallel manipulator was utilized for that approach because it had the solution in the closed form. Initially, a dataset was created from an inverse kinematic solution of the manipulator for one of its assembly modes. Then, this dataset was fed as the input (the joint space) and the output (the platform space) for modeling the direct kinematic solution of the manipulator using one of the machine learning algorithms, which was the decision tree. To avoid overfitting during the training, hyperparameter tuning was employed to find the best parameters for the decision tree model, which was later called the best model. Hence, the best model can be validated by using the closed form solution. If the best model failed to model the direct kinematic solution in the validation, remodeling had to be performed and executed the same steps again. For remodeling, the training dataset consisted of all assembly modes of the manipulator. Consequently, the best model after remodeling was able to present the direct kinematic solutions for all possible input domains. Unfortunately, around 5% of solutions shown a higher deviation which had to be investigated in the future.

show abstract

Section: Pendahuluanunclassified

See 1 more Smart Citation

An Application of Decission Tree for Modeling the Direct Kinematic Solution of 5R Planar Parallel Manipulator

Adriyan¹

2021

JTM

View full text Add to dashboard Cite

show abstract

“…Other works including [19,20] briefly study the singularity of a five-bar linkage or a mechanism that can be transposed from a lower-or upper-class mechanism. Other research is oriented in the dimensioning of the DC motors of the five-bar linkage by Shengqi [21], in the development of control strategies of the planar 2 DoF manipulator by Roskam and Luc [22] and by Can and Sen [23] in minimizing the energy consumption through regenerative drives and optimally designed compliant elements.…”

Section: Introductionmentioning

confidence: 99%

Design of the five-bar linkage with singularity-free workspace

et al. 2023

View full text Add to dashboard Cite

This paper shows the kinematic analysis and the synthesis of the five-bar linkage with symmetrical structure and singularity-free dexterous workspace. The type synthesis of the five-bar linkage shows that the number of symmetrical structures of five-bar linkage is limited to eight structures. This study deals with the forward and inverse kinematic analysis and synthesis of the five-bar structure 5-RRRRR. The synthesis equations allow the analytical computation of the link lengths of a symmetrical five-bar linkage using only revolute joints to avoid the singularities in an imposed dexterous workspace. A numerical example of the symmetrical five-bar linkage is analyzed and synthetized theoretically and characterized by computing the performance indices. The tests on an experimental model of the five-bar linkage 5-RRRRR confirm the singularity-free dexterous workspace.

show abstract

“…The authors of [ 11 ] proposed the use of neural networks for the offline estimation of the kinematic analysis of a robot and an online neural network in order to control the trajectory. A multilayer feedforward neural network was trained in [ 12 ] in order to solve the kinematic analysis of a planar parallel mechanism. The proposed solution overcomes some limitations of the Newton–Rapson numerical algorithm in what regards obtaining multiple solutions for the generalized coordinates.…”

Section: Introductionmentioning

confidence: 99%

Estimation of the Kinematics and Workspace of a Robot Using Artificial Neural Networks

Boantă

Brişan

2022

Sensors

View full text Add to dashboard Cite

At present, in specific and complex industrial operations, robots have to respect certain requirements and criteria as high kinematic or dynamic performance, specific dimensions of the workspace, or limitation of the dimensions of the mobile elements of the robot. In order to respect these criteria, a proper design of the robots has to be achieved, which requires years of practice and a proper knowledge and experience of a human designer. In order to assist the human designer in the process of designing the robots, several methods (including optimization methods) have been developed. The scientific problem addressed in this paper is the development of an artificial intelligence method to estimate the size of the workspace and the kinematics of a robot using a feedforward neural network. The method is applied on a parallel robot composed of a base platform, a mobile platform and six kinematic rotational-universal-spherical open loops. The numerical results show that, with proper training and topology, a feedforward neural network is able to estimate properly values of the volume of the workspace and the values of the generalized coordinates based on the pose of the end effector.

show abstract

Modeling in Two Configurations of a 5R 2-DoF Planar Parallel Mechanism and Solution to the Inverse Kinematic Modeling Using Artificial Neural Network

Cited by 6 publications

References 47 publications

An Application of Decission Tree for Modeling the Direct Kinematic Solution of 5R Planar Parallel Manipulator

An Application of Decission Tree for Modeling the Direct Kinematic Solution of 5R Planar Parallel Manipulator

Design of the five-bar linkage with singularity-free workspace

Estimation of the Kinematics and Workspace of a Robot Using Artificial Neural Networks

Contact Info

Product

Resources

About