Solving Inverse Kinematics of a 7-DOF Manipulator Using Convolutional Neural Network

Elkholy, Hassan Ashraf; Shahin, Abdalla Saber; Abdelaziz, Shaarawy,; Marzouk, Hagar; Elsamanty, Mahmoud

doi:10.1007/978-3-030-44289-7_32

Cited by 6 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…ANNs enable the learning of the intricate relationship between a soft robot’s input and output parameters, enabling precise control over its behavior, motion, and stiffness, thereby facilitating shape adaptation and functional changes [ 36 , 37 ]. Obtaining a kinematic or dynamic model for soft robots is often challenging in model-based control systems [ 38 , 47 ]. To overcome this limitation, learning techniques, including neural networks, have been employed to derive accurate kinematic or dynamic models for soft robots [ 33 , 39 ].…”

Section: Workpace and Kinematic Model For Spmmentioning

confidence: 99%

Soft Pneumatic Muscles: Revolutionizing Human Assistive Devices with Geometric Design and Intelligent Control

et al. 2023

Self Cite

View full text Add to dashboard Cite

Soft robotics, a recent advancement in robotics systems, distinguishes itself by utilizing soft and flexible materials like silicon rubber, prioritizing safety during human interaction, and excelling in handling complex or delicate objects. Soft pneumatic actuators, a prevalent type of soft robot, are the focus of this paper. A new geometrical parameter for soft artificial pneumatic muscles is introduced, enabling the prediction of actuation behavior using analytical models based on specific design parameters. The study investigated the impact of the chamber pitch parameter and actuation conditions on the deformation direction and internal stress of three tested soft pneumatic muscle (SPM) models. Simulation involved the modeling of hyperelastic materials using finite element analysis. Additionally, an artificial neural network (ANN) was employed to predict pressure values in three chambers at desired Cartesian positions. The trained ANN model demonstrated exceptional performance. It achieved high accuracy with training, validation, and testing residuals of 99.58%, 99.89%, and 99.79%, respectively. During the validation simulations and neural network results, the maximum errors in the x, y, and z coordinates were found to be 9.3%, 7.83%, and 8.8%, respectively. These results highlight the successful performance and efficacy of the trained ANN model in accurately predicting pressure values for the desired positions in the soft pneumatic muscles.

show abstract

Section: Workpace and Kinematic Model For Spmmentioning

confidence: 99%

Soft Pneumatic Muscles: Revolutionizing Human Assistive Devices with Geometric Design and Intelligent Control

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…The determination of the Poisson's ratio for auxetic structures was accomplished through the utilization of a cascaded forward propagation-backpropagation neural network model [52][53][54]. The selection of a neural network for this purpose stemmed from the inherent complexity of auxetic structures, which involve a multitude of geometric parameters.…”

Section: Poisson's Ratio Estimationmentioning

confidence: 99%

Investigation and Tailoring of Rotating Squares’ and Rectangles’ Auxetic Structure Behavior through Computational Simulations of 6082T6 Aluminum Alloy Structures

Elsamanty,

Elshokrofy,

Ibrahim

et al. 2023

Materials

Self Cite

View full text Add to dashboard Cite

Auxetic structures, renowned for their unique lateral expansion under longitudinal strain, have attracted significant research interest due to their extraordinary mechanical characteristics, such as enhanced toughness and shear resistance. This study provides a systematic exploration of these structures, constructed from rigid rotating square or rectangular unit cells. Incremental alterations were applied to key geometrical parameters, including the angle (θ) between connected units, the side length (a), the side width (b) of the rotating rigid unit, and the overlap distance (t). This resulted in a broad tunable range of negative Poisson’s ratio values from −0.43 to −1.78. Through comprehensive three-dimensional finite-element analyses, the intricate relationships between the geometric variables and the resulting bulk Poisson’s ratio of the modeled auxetic structure were elucidated. This analysis affirmed the auxetic behavior of all investigated samples, characterized by lateral expansion under tensile force. The study also revealed potential stress concentration points at interconnections between rotating units, which could impact the material’s performance under high load conditions. A detailed investigation of various geometrical parameters yielded fifty unique samples, enabling in-depth observation of the impacts of geometric modifications on the overall behavior of the structures. Notably, an increase in the side width significantly enhanced the Poisson’s ratio, while an increase in the overlap distance notably reduced it. The greatest observable change in the Poisson’s ratio was a remarkable 202.8%, emphasizing the profound influence of geometric parameter manipulation. A cascaded forward propagation–backpropagation neural network model was deployed to determine the Poisson’s ratio for auxetic structures, based on the geometric parameters and material properties of the structure. The model’s architecture consisted of five layers with varying numbers of neurons. The model’s validity was affirmed by comparing its predictions with FEA simulations, with the maximum error observed in the predicted Poisson’s ratio being 8.62%.

show abstract

“…[4] menggunakan pembelajaran mesin (machine learning) untuk menyelesaikan problem kinematika balik. [5] menggunakan convolutional neural netoworks untuk menyelesaikan kinematika balik robot dengan 7 derajat kebebasan. [6] mendapatkan formulasi kinematika balik secara analitik untuk manipulator redundan.…”

Section: Pendahuluanunclassified

Perancangan Jaringan Saraf Tiruan Untuk Menyelesaikan Kinematika Balik Manipulator Robot Denso 6-DoF

Hidayat,

Sahal,

Bilfaqih

et al. 2023

ELE

View full text Add to dashboard Cite

Pada artikel ini, dibahas tentang kinematika balik (inverse kinematics) untuk manipulator robot denso 6-DoF. Kinematika balik adalah metode menentukan konfigurasi sendi dengan mengetahui posisi end-effector yang diinginkan. Kesulitan dari kinematika balik adalah penyelesaiannya yang tidak tunggal. Untuk satu titik end-effector, ada banyak konfigurasi sendi yang mungkin sehingga tidak ada penyelesaian yang unik. Untuk menyelesaikan kinematika balik ini, diusulkan penyelesaian menggunakan jaringan saraf tiruan untuk mendapatkan salah satu penyelesaian berupa posisi dan orientasi dari end-effector.

show abstract

Solving Inverse Kinematics of a 7-DOF Manipulator Using Convolutional Neural Network

Cited by 6 publications

References 16 publications

Soft Pneumatic Muscles: Revolutionizing Human Assistive Devices with Geometric Design and Intelligent Control

Soft Pneumatic Muscles: Revolutionizing Human Assistive Devices with Geometric Design and Intelligent Control

Investigation and Tailoring of Rotating Squares’ and Rectangles’ Auxetic Structure Behavior through Computational Simulations of 6082T6 Aluminum Alloy Structures

Perancangan Jaringan Saraf Tiruan Untuk Menyelesaikan Kinematika Balik Manipulator Robot Denso 6-DoF

Contact Info

Product

Resources

About