Adaptive Neural Network Control of a Compact Bionic Handling Arm

Melingui, Achille; Lakhal, Othman; Daachi, B.; Mbede, Jean Bosco; Merzouki, Rochdi

doi:10.1109/tmech.2015.2396114

Cited by 95 publications

(43 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the presence of measurement uncertainties due the cablepotentiometer accuracy can also be a source of this error. 29 The total execution time is about 35 min on 2300 points taken from the path, or a mean value of 0.913 s per point ( Figure 22) while the value of objective function has been reduced from 70.155 to 63.271 ( Figure 23) along the desired trajectory.…”

Section: Numerical Resultsmentioning

confidence: 99%

Generating optimal reference kinematic configurations for hyper-redundant parallel robots

Chibani

Mahfoudi

Chettibi³

et al. 2015

Proceedings of the Institution of Mechanical Engineers, Part I:

Self Cite

View full text Add to dashboard Cite

International audienceIn this article, we propose an optimization process able to generate optimal kinematic configuration for spatial hyper-redundant manipulators with multiple rigid parallel modules. The proposed method uses a deterministic optimization scheme that evaluates the score of trial kinematic configurations while accounting for various geometric constraints. This versatile method is based on a simultaneous search for both the best curve capturing the overall kinematic robot posture and the platform distribution along this curve. This process is carried out using the powerful sequential quadra-tic programming technique. Numerical results are presented to illustrate the efficiency of the proposed approach. Finally, this model was validated by real measurements obtained with the continuum bionic handling arm of a mobile robot called Robotino-XT

show abstract

Section: Numerical Resultsmentioning

confidence: 99%

Generating optimal reference kinematic configurations for hyper-redundant parallel robots

Chibani

Mahfoudi

Chettibi³

et al. 2015

Proceedings of the Institution of Mechanical Engineers, Part I:

Self Cite

View full text Add to dashboard Cite

show abstract

“…4 and 5. Neural Network based qualitative approach [11] is used to calculate IKM of CBHA. In this approach a Distal Supervised Learning (DSL) technique is used to build a relation between effect and cause.…”

Section: B Damped Least Square Methodsmentioning

confidence: 99%

“…The approximation of inverse kinematic model of a soft manipulator is done using a feed-forward Neural Networks (NN) [10]. Neural Network [11] based approach approximates the inverse kinematic model of CBHA robot. Hybrid approach, both quantitative as well as qualitative, is used in [12] for IKM of CBHA.…”

Section: Introductionmentioning

confidence: 99%

Performances evaluation of inverse kinematic models of a compact bionic handling assistant

Singh

Lakhal

Amara

et al. 2017

2017 IEEE International Conference on Robotics and Biomimetics (ROBIO)

Self Cite

View full text Add to dashboard Cite

Abstract-Inverse Kinematic Model (IKM) is very crucial for real-time control of a robot for any application. Computing the IKM of continuum manipulators is a challenging task. Two types of methods exists; quantitative methods describing a model-based approach; and qualitative methods, based on learning approach. As quantitative methods are based on mathematical expression, they are more flexible for extension (increase in number of sections or collaboration between more than one manipulator). In this paper, two quantitative approaches based on Newton Raphson iterative method and Damped Least Square method, are proposed for Compact Bionic Handling Assistant (CBHA) manipulator to solve inverse kinematics directly using Forward Kinematic Model (FKM). Experimental validation is done for these methods as well as they are compared with the existing approaches named Hybrid approach and Neural Network based learning approach.

show abstract

“…A compact bionic handling arm was developed in [24], and it could reproduce biological behaviors of trunks, tentacles, or snakes. In [25], a developed multifingered dexterous hand with flexible tactile skin was presented, which has five fingers with 6-degrees of freedom (DOFs), and each finger is equipped with a small harmonic drive gear and a fine high-power mini actuator, and each fingertip is covered with the tactile array sensors for determination of the force between the finger and the grasped object.…”

Section: A Bio-inspired Locomotion and Mechanismsmentioning

confidence: 99%

Guest Editorial An Overview of Biomedical Robotics and Bio-Mechatronics Systems and Applications

Yang

Burdet

2016

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

Adaptive Neural Network Control of a Compact Bionic Handling Arm

Cited by 95 publications

References 35 publications

Generating optimal reference kinematic configurations for hyper-redundant parallel robots

Generating optimal reference kinematic configurations for hyper-redundant parallel robots

Performances evaluation of inverse kinematic models of a compact bionic handling assistant

Guest Editorial An Overview of Biomedical Robotics and Bio-Mechatronics Systems and Applications

Contact Info

Product

Resources

About