Artificial Neural Networks to Solve Forward Kinematics of a Wearable Parallel Robot with Semi-rigid Links

Prado, Antonio; Zhang, Haohan; Agrawal, Sunil K.

doi:10.1109/icra48506.2021.9561246

Cited by 7 publications

(5 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Genetic Algorithms (GA) and Neural Networks (NN) have been successfully employed for other robotic structures ( [31][32][33][34] provides examples for GA, [35][36][37][38][39] for NN, and [40] for a work in which both methodologies are used and compared) but never for 3RRR robots and, as has been shown, they avoid the problem of singularities [40] and can be used for path following [33,39].…”

Section: Introductionmentioning

confidence: 99%

Kinematic Modelling of a 3RRR Planar Parallel Robot Using Genetic Algorithms and Neural Networks

García-Samartín,

Barrientos

2023

Machines

View full text Add to dashboard Cite

Kinematic modelling of parallel manipulators poses significant challenges due to the absence of analytical solutions for the Forward Kinematics (FK) problem. This study centres on a specific parallel planar robot, specifically a 3RRR configuration, and addresses the FK problem through two distinct methodologies: Genetic Algorithms (GA) and Neural Networks (NN). Utilising the Inverse Kinematic (IK) model, which is readily obtainable, both GA and NN techniques are implemented without the need for closed-loop formulations or non-systematic mathematical tools, allowing for easy extension to other robot types. A comparative analysis against an existing numerical method demonstrates that the proposed methodologies yield comparable or superior performance in terms of accuracy and time, all while reducing development costs. Despite GA’s time consumption limitations, it excels in path planning, whereas NN delivers precise results unaffected by stochastic elements. These results underscore the feasibility of using neural networks and genetic algorithms as viable alternatives for real-time kinematic modelling of robots when closed-form solutions are unavailable.

show abstract

Section: Introductionmentioning

confidence: 99%

Kinematic Modelling of a 3RRR Planar Parallel Robot Using Genetic Algorithms and Neural Networks

García-Samartín,

Barrientos

2023

Machines

View full text Add to dashboard Cite

show abstract

“…A basic neural network model proposed by Prado et al. [30] was used to address the forward kinematics of a wearable 3‐RRS (R, S, P, U corresponding to revolute joint, spherical joint, prismatic joint, universal joint, respectively) parallel robot. Similarly, Mohammad et al.…”

Section: Introductionmentioning

confidence: 99%

“…Besides, an adaptive neuro-fuzzy inference structure model was utilised by Azar et al [34] to attain the forward kinematics solution of the 3-DOF planar parallel robot. A basic neural network model proposed by Prado et al [30] was used to address the forward kinematics of a wearable 3-RRS (R, S, P, U corresponding to revolute joint, spherical joint, prismatic joint, universal joint, respectively) parallel robot. Similarly, Mohammad et al [35] presented a neural network model with external forces to estimate the position of the cable-driven parallel robot, whose network error was acquired at approximately 0.38% for positions and 3.87% for angles.…”

mentioning

confidence: 99%

“…In view of the current existing theoretical research results, artificial neural network (ANN), as an alternative approach to the forward kinematics solution of parallel robots, is superior to other methods in terms of computational efficiency and accuracy [30]. For instance, the BP neural network model optimised by GA was used by Liu et al [31] to address the forward kinematics problems of Delta parallel robot.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Kernel extreme learning machine‐based general solution to forward kinematics of parallel robots

Jun-hai

Zhang

2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

The forward kinematics of parallel robots is a challenging issue due to its highly coupled non‐linear relation among branch chains. This paper presents a novel approach to forward kinematics of parallel robots based on kernel extreme learning machine (KELM). To tackle with the forward kinematics solution of fully parallel robots, the forward kinematics solution of parallel robots is equivalently transformed into a machine learning model first. On this basis, a computational model combining sparrow search algorithm and KELM is then established, which can serve as both regression and classification. Based on SSA‐optimised KELM (SSA‐KELM) established in this study, a binary discriminator for judging the existence of the forward kinematics solution and a multi‐label regression model for predicting the forward kinematics solution are built to obtain the forward kinematics general solution of parallel robots with different structural configurations and parameters. To evaluate the proposed model, a numerical case on this dataset collected by the inverse kinematics model of a typical 6‐DOF parallel robot is conducted, followed by the results manifesting that the binary discriminator with the discriminant accuracy of 88.50% is superior over ELM, KELM, support vector machine and logistic regression. The multi‐label regression model, with the root mean squared error of 0.06 mm for the position and 0.15° for the orientation, outperforms the double‐hidden‐layer back propagation (2‐BP), ELM, KELM and genetic algorithm‐optimised KELM. Furthermore, numerical cases of parallel robots with different structural configurations and parameters are compared with state‐of‐the‐art models. Moreover, these results of numerical simulation and experiment on the host computer demonstrate that the proposed model displays its high precision, high robustness and rapid convergence, which provides a candidate for the forward kinematics of parallel robots.

show abstract

“…al. [3]. In this study, forward kinematics of a wearable parallel robot with semi-rigid links are solved by using neural network algorithm.…”

Section: Introductionmentioning

confidence: 99%

Position Analysis of the Slider-Crank (R-RRT) Mechanism Using Artificial Neural Networks

2023

1st International Conference on Modern and Advanced Research Icmar 2023

View full text Add to dashboard Cite

The slider-crank mechanism is a common mechanical linkage that converts rotary motion into reciprocating motion. It finds wide applications in various fields, including internal combustion engines, pumps, compressors, presses, robotics, and human-powered vehicles. Due to its widespread use, several textbooks have covered its position, velocity, and acceleration analyses, with different researchers proposing various analysis solutions. Recently, artificial neural networks (ANN) have been utilized in diverse research areas, including inverse and forward kinematic analysis. However, there has not been a specific use of ANN for position analysis of slider-crank mechanisms. This study aims to addresses that gap by presenting the position analysis of the in-line type slider-crank (R-RRT) mechanism using the ANN algorithm. For this purpose, the Levenberg-Marquardt backpropagation algorithm is selected due to its advantages, such as speed, stable convergence of training error, and the combination of Gauss-Newton training algorithm and steepest descent method. To train the algorithm effectively, 50 data sets are carefully chosen and randomly split for training, validation, and testing. Moreover, an additional 200 data sets are reserved for testing the trained algorithm to evaluate its performance. This study presents the result of the neural network algorithm training, as well as the outcomes of additional testing of the trained algorithm. These results are thoroughly discussed and analyzed.

show abstract

Artificial Neural Networks to Solve Forward Kinematics of a Wearable Parallel Robot with Semi-rigid Links

Cited by 7 publications

References 32 publications

Kinematic Modelling of a 3RRR Planar Parallel Robot Using Genetic Algorithms and Neural Networks

Kinematic Modelling of a 3RRR Planar Parallel Robot Using Genetic Algorithms and Neural Networks

Kernel extreme learning machine‐based general solution to forward kinematics of parallel robots

Position Analysis of the Slider-Crank (R-RRT) Mechanism Using Artificial Neural Networks

Contact Info

Product

Resources

About