Modelling of Continuum Robotic Arm Using Artificial Neural Network (ANN)

Alphonse, Albert Ashraf; Abbas, Ahmed Ashraf; Fathy, Amr Medhat; Elsayed, Nada Saif; Ammar, Hossam Hassan; Elsamanty, Mahmoud

doi:10.1109/niles.2019.8909308

Cited by 10 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Z -axis represents the upper and lower sides of the robot, the θ -axis corresponds to the rotational part of the robot, and the R -axis corresponds to the linear motion part of the end effector. 14 Therefore, the robot arms are operable in various moving directions and at optimized speeds during the transfer process, and the optimal adhesive forces between the BDAPs and wafers for each motion are required.…”

Section: Resultsmentioning

confidence: 99%

Bio-inspired dry adhesive pads using multi-walled carbon nanotube/polydimethylsiloxane composites for efficient wafer transfer robot arms in smart factories

Lee,

Ko,

Kim

et al. 2023

Mol. Syst. Des. Eng.

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

Bio-inspired dry adhesive pads using multi-walled carbon nanotube/polydimethylsiloxane composites for efficient wafer transfer robot arms in smart factories

Lee,

Ko,

Kim

et al. 2023

Mol. Syst. Des. Eng.

View full text Add to dashboard Cite

show abstract

“…It is possible to describe the function relation g by developing a static model. However, in reality, the manufacturing and assembly error of the CM cannot be well modeled [21], but this systematic error also satisfies a specific relation ϕ as shown in the following, where ε is an unpredictable random term: For a rigid-link manipulator, the robot starts motion from the current position, and in most applications, it then moves on a trajectory on a sequential point path. The inclusion of the current joint configuration in the artificial neural network has a positive effect on the estimation of joint angles for the next desired position 32 .…”

Section: Problem Descriptionmentioning

confidence: 99%

“…Compared to this, Braganza et al 20 used artificial neural network (ANN) algorithms to compensating for the nonlinear uncertain dynamics of the CM. In addition to this, many scholars have used ANN algorithms for the kinematic modeling [21][22][23][24] , shape estimation 25 , adaptive neural network control 26 of a CM. Although the ANN-based modeling approach relies more on training data, it can take into account the manufacturing and assembly errors of the CM, the period of tendon contracting or stretching, and so on.…”

mentioning

confidence: 99%

A learning-based tip contact force estimation method for tendon-driven continuum manipulator

Feng

Hong

Xie

2021

Sci Rep

View full text Add to dashboard Cite

Although tendon-driven continuum manipulators have been extensively researched, how to realize tip contact force sensing in a more general and efficient way without increasing the diameter is still a challenge. Rather than use a complex modeling approach, this paper proposes a general tip contact force-sensing method based on a recurrent neural network that takes the tendons’ position and tension as the input of a recurrent neural network and the tip contact force of the continuum manipulator as the output and fits this static model by means of machine learning so that it may be used as a real-time contact force estimator. We also designed and built a corresponding three-degree-of-freedom contact force data acquisition platform based on the structure of a continuum manipulator designed in our previous studies. After obtaining training data, we built and compared the performances of a multi-layer perceptron-based contact force estimator as a baseline and three typical recurrent neural network-based contact force estimators through TensorFlow framework to verify the feasibility of this method. We also proposed a manually decoupled sub-estimators algorithm and evaluated the advantages and disadvantages of those two methods.

show abstract

“…Subsequently, the relationship between the output and input will be used to derive the model of the system. For robotic arm, (Alphonse et al, 2019;Hassan et al, 2019;Rehiara, 2011) designs models using system identification. In (Hassan et al, 2019), the shaft motion and the angles of the robotic arm were the inputs of the model while the positions of the end effector (in x, y and z coordinates) and the angles (roll, pitch and yaw) were the respective output of the model.…”

Section: Modelling Of Pick and Place Robotic Armmentioning

confidence: 99%

Modelling and Design of State Estimator for a Pick and Place Robotic Arm

Dandago¹,

Mohammed²,

Ubadike³

et al. 2021

FUOYEJET

View full text Add to dashboard Cite

A robust model is essential for the design of system components such as controllers, observers state estimators, and simulators. State estimators are becoming increasingly important in modern systems, especially systems with states that may not be measured with sensors. Therefore, it is imperative to analyze the performance of different modelling and state estimator design techniques. In this research work, a parametric model of a pick and place robotic arm was obtained using system identification technique. Pick and place robotic arms have a lot of industrial applications. The parameters of the obtained model were determined using the general second-order characteristics equation and manual tuning. Furthermore, five state estimators were designed based on the developed model. The accuracy of the model, and the performance of the observers were analyzed. The model was found to provide a good representation of the system. Nonetheless, with very small divergence between the model and the real system. The performance of the observers was found to be dependent on their pole locations; the higher the magnitude of the poles, the higher the state estimators’ gain and the better the estimation provided. It was found out that the state estimators with high gains were more susceptible to measurement noise. Keywords— Modelling, pick and place robots, observers, and state estimators.

show abstract

Modelling of Continuum Robotic Arm Using Artificial Neural Network (ANN)

Cited by 10 publications

References 21 publications

Bio-inspired dry adhesive pads using multi-walled carbon nanotube/polydimethylsiloxane composites for efficient wafer transfer robot arms in smart factories

Bio-inspired dry adhesive pads using multi-walled carbon nanotube/polydimethylsiloxane composites for efficient wafer transfer robot arms in smart factories

A learning-based tip contact force estimation method for tendon-driven continuum manipulator

Modelling and Design of State Estimator for a Pick and Place Robotic Arm

Contact Info

Product

Resources

About