Forward Kinematic Modelling with Radial Basis Function Neural Network Tuned with a Novel Meta-Heuristic Algorithm for Robotic Manipulators
The complexity of forward kinematic modelling increases with the increase in the degrees of freedom for a manipulator. To reduce the computational weight and time lag for desired output transformation, this paper proposes a forward kinematic model mapped with the help of the Radial Basis Function Ne...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Robotics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-6581/11/2/43 |
| _version_ | 1797434255773532160 |
|---|---|
| author | Syed Kumayl Raza Moosavi Muhammad Hamza Zafar Filippo Sanfilippo |
| author_facet | Syed Kumayl Raza Moosavi Muhammad Hamza Zafar Filippo Sanfilippo |
| author_sort | Syed Kumayl Raza Moosavi |
| collection | DOAJ |
| description | The complexity of forward kinematic modelling increases with the increase in the degrees of freedom for a manipulator. To reduce the computational weight and time lag for desired output transformation, this paper proposes a forward kinematic model mapped with the help of the Radial Basis Function Neural Network (RBFNN) architecture tuned by a novel meta-heuristic algorithm, namely, the Cooperative Search Optimisation Algorithm (CSOA). The architecture presented is able to automatically learn the kinematic properties of the manipulator. Learning is accomplished iteratively based only on the observation of the input–output relationship. Related simulations are carried out on a 3-Degrees of Freedom (DOF) manipulator on the Robot Operating System (ROS). The dataset created from the simulation is divided 65–35 for training–testing of the proposed model. The metrics used for model validation include spread value, cost and runtime for the training dataset, and Mean Relative Error, Normal Mean Square Error, and Mean Absolute Error for the testing dataset. A comparative analysis of the CSOA-RBFNN model is performed with an artificial neural network, support vector regression model, and with with other meta-heuristic RBFNN models, i.e., PSO-RBFNN and GWO-RBFNN, that show the effectiveness and superiority of the proposed technique. |
| first_indexed | 2024-03-09T10:30:35Z |
| format | Article |
| id | doaj.art-e2c2610d22054b928097c132086fcad1 |
| institution | Directory Open Access Journal |
| issn | 2218-6581 |
| language | English |
| last_indexed | 2024-03-09T10:30:35Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Robotics |
| spelling | doaj.art-e2c2610d22054b928097c132086fcad12023-12-01T21:22:16ZengMDPI AGRobotics2218-65812022-04-011124310.3390/robotics11020043Forward Kinematic Modelling with Radial Basis Function Neural Network Tuned with a Novel Meta-Heuristic Algorithm for Robotic ManipulatorsSyed Kumayl Raza Moosavi0Muhammad Hamza Zafar1Filippo Sanfilippo2School of Electrical Engineering and Computer Science, National University of Sciences and Technology, Islamabad 44000, PakistanDepartment of Electrical Engineering, Capital University of Science and Technology, Islamabad 44000, PakistanDepartment of Engineering Sciences, University of Agder (UiA), Jon Lilletuns vei 9, NO-4879 Grimstad, NorwayThe complexity of forward kinematic modelling increases with the increase in the degrees of freedom for a manipulator. To reduce the computational weight and time lag for desired output transformation, this paper proposes a forward kinematic model mapped with the help of the Radial Basis Function Neural Network (RBFNN) architecture tuned by a novel meta-heuristic algorithm, namely, the Cooperative Search Optimisation Algorithm (CSOA). The architecture presented is able to automatically learn the kinematic properties of the manipulator. Learning is accomplished iteratively based only on the observation of the input–output relationship. Related simulations are carried out on a 3-Degrees of Freedom (DOF) manipulator on the Robot Operating System (ROS). The dataset created from the simulation is divided 65–35 for training–testing of the proposed model. The metrics used for model validation include spread value, cost and runtime for the training dataset, and Mean Relative Error, Normal Mean Square Error, and Mean Absolute Error for the testing dataset. A comparative analysis of the CSOA-RBFNN model is performed with an artificial neural network, support vector regression model, and with with other meta-heuristic RBFNN models, i.e., PSO-RBFNN and GWO-RBFNN, that show the effectiveness and superiority of the proposed technique.https://www.mdpi.com/2218-6581/11/2/43roboticsartificial intelligenceROSforward kinematic modellingradial basis function neural networkscooperative search optimisation algorithm |
| spellingShingle | Syed Kumayl Raza Moosavi Muhammad Hamza Zafar Filippo Sanfilippo Forward Kinematic Modelling with Radial Basis Function Neural Network Tuned with a Novel Meta-Heuristic Algorithm for Robotic Manipulators Robotics robotics artificial intelligence ROS forward kinematic modelling radial basis function neural networks cooperative search optimisation algorithm |
| title | Forward Kinematic Modelling with Radial Basis Function Neural Network Tuned with a Novel Meta-Heuristic Algorithm for Robotic Manipulators |
| title_full | Forward Kinematic Modelling with Radial Basis Function Neural Network Tuned with a Novel Meta-Heuristic Algorithm for Robotic Manipulators |
| title_fullStr | Forward Kinematic Modelling with Radial Basis Function Neural Network Tuned with a Novel Meta-Heuristic Algorithm for Robotic Manipulators |
| title_full_unstemmed | Forward Kinematic Modelling with Radial Basis Function Neural Network Tuned with a Novel Meta-Heuristic Algorithm for Robotic Manipulators |
| title_short | Forward Kinematic Modelling with Radial Basis Function Neural Network Tuned with a Novel Meta-Heuristic Algorithm for Robotic Manipulators |
| title_sort | forward kinematic modelling with radial basis function neural network tuned with a novel meta heuristic algorithm for robotic manipulators |
| topic | robotics artificial intelligence ROS forward kinematic modelling radial basis function neural networks cooperative search optimisation algorithm |
| url | https://www.mdpi.com/2218-6581/11/2/43 |
| work_keys_str_mv | AT syedkumaylrazamoosavi forwardkinematicmodellingwithradialbasisfunctionneuralnetworktunedwithanovelmetaheuristicalgorithmforroboticmanipulators AT muhammadhamzazafar forwardkinematicmodellingwithradialbasisfunctionneuralnetworktunedwithanovelmetaheuristicalgorithmforroboticmanipulators AT filipposanfilippo forwardkinematicmodellingwithradialbasisfunctionneuralnetworktunedwithanovelmetaheuristicalgorithmforroboticmanipulators |