A genetic algorithm approach to a neural-network-based inverse kinematics solution of robotic manipulators based on error minimization

Köker, Raşit

doi:10.1016/j.ins.2012.07.051

Cited by 177 publications

(98 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The first issue is to generate a suitable training data set, whereas the second issue is to select the appropriate number of hidden layers for the ELM model. Once the kinematic parameters of the robotic manipulator are known, a forward kinematics model can be formulated using equations (1) to (14). To ensure rationality of the training set, the joint angles qðq 1 ;q 2 ;q 3 ;q 4 ;q 5 ;q 6 Þ of the manipulator are randomly initialized.…”

Section: Proposed Algorithmmentioning

confidence: 99%

Inverse kinematics solution for robotic manipulator based on extreme learning machine and sequential mutation genetic algorithm

Zhou

Guo

Wang

et al. 2018

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

This article presents an intelligent algorithm based on extreme learning machine and sequential mutation genetic algorithm to determine the inverse kinematics solutions of a robotic manipulator with six degrees of freedom. This algorithm is developed to minimize the computational time without compromising the accuracy of the end effector. In the proposed algorithm, the preliminary inverse kinematics solution is first computed by extreme learning machine and the solution is then optimized by an improved genetic algorithm based on sequential mutation. Extreme learning machine randomly initializes the weights of the input layer and biases of the hidden layer, which greatly improves the training speed. Unlike classical genetic algorithms, sequential mutation genetic algorithm changes the order of the genetic codes from high to low, which reduces the randomness of mutation operation and improves the local search capability. Consequently, the convergence speed at the end of evolution is improved. The performance of the extreme learning machine and sequential mutation genetic algorithm is also compared with that of a hybrid intelligent algorithm, and the results showed that there is significant reduction in the training time and computational time while the solution accuracy is retained. Based on the experimental results, the proposed extreme learning machine and sequential mutation genetic algorithm can greatly improve the time efficiency while ensuring high accuracy of the end effector.

show abstract

Section: Proposed Algorithmmentioning

confidence: 99%

Inverse kinematics solution for robotic manipulator based on extreme learning machine and sequential mutation genetic algorithm

Zhou

Guo

Wang

et al. 2018

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

show abstract

“…It achieves optimal classification in linear separable case. It is better than neural networks [8], decision trees [9] and Bayesian classifiers [10] in some applications. SVM offers a hyperplane that represents the largest separation (or margin) between two classes [11].…”

Section: Support Vector Machinementioning

confidence: 99%

Study of Classification of Diseases by Genetic Algorithm for Multiclass Support Vector Machine Using Hadoop

Deshmukh¹

2016

IJECS

View full text Add to dashboard Cite

Abstract:Since many years ago, the scientific community is concerned about how to increase the accuracy of different classification methods, and major achievements have been made so far. Hadoop and MapReduce are used to handle these large volumes of variable size data. This work focuses on the combining a feature selection technique based on genetic algorithm and support vector machines (SVM) of medical disease classification. SVM is relatively a novel classification technique and has been shown higher performance than traditional learning methods in many applications. The idea is to use GA as an optimizer to find the optimal values of hyper-parameters of SVM and adopt a supervised learning approach to train the SVM model. In this paper we propose a genetic algorithm (GA) based classification method.

show abstract

“…Artificial bee colony GA was presented and used to optimize the controller's parameters. Neural networks was used to get an approximate inverse kinematics solution and then the solution to the inverse kinematics problem was optimized by applying GA for error minimization in [32]. In addition to research related to application of GA and similar algorithms, combinations and improvement of the algorithms themselves also has received a fair share of research [31,[33][34][35].…”

Section: Introductionmentioning

confidence: 99%

A Closed Loop Inverse Kinematics Solver Intended for Offline Calculation Optimized with GA

Bjørlykhaug

2018

Robotics

View full text Add to dashboard Cite

This paper presents a simple approach to building a robotic control system. Instead of a conventional control system which solves the inverse kinematics in real-time as the robot moves, an alternative approach where the inverse kinematics is calculated ahead of time is presented. This approach reduces the complexity and code necessary for the control system. Robot control systems are usually implemented in low level programming language. This new approach enables the use of high level programming for the complex inverse kinematics problem. For our approach, we implement a program to solve the inverse kinematics, called the Inverse Kinematics Solver (IKS), in Java, with a simple graphical user interface (GUI) to load a file with desired end effector poses and edit the configuration of the robot using the Denavit-Hartenberg (DH) convention. The program uses the closed-loop inverse kinematics (CLIK) algorithm to solve the inverse kinematics problem. As an example, the IKS was set up to solve the kinematics for a custom built serial link robot. The kinematics for the custom robot is presented, and an example of input and output files is also presented. Additionally, the gain of the loop in the IKS is optimized using a GA, resulting in almost a 50% decrease in computational time.

show abstract

A genetic algorithm approach to a neural-network-based inverse kinematics solution of robotic manipulators based on error minimization

Cited by 177 publications

References 48 publications

Inverse kinematics solution for robotic manipulator based on extreme learning machine and sequential mutation genetic algorithm

Inverse kinematics solution for robotic manipulator based on extreme learning machine and sequential mutation genetic algorithm

Study of Classification of Diseases by Genetic Algorithm for Multiclass Support Vector Machine Using Hadoop

A Closed Loop Inverse Kinematics Solver Intended for Offline Calculation Optimized with GA

Contact Info

Product

Resources

About