Applying Neural Network Architecture for Inverse Kinematics Problem in Robotics

Daya, Bassam; Khawandi, Shadi; Akoum, Mohamed

doi:10.4236/jsea.2010.33028

Cited by 60 publications

(26 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…According to the ANN based solving inverse kinematics results in the literature [2–6, 10, 11], the proposed approach in this study has a minimized error in the inverse kinematics solution. Table 3 shows system performance comparison between this study and other studies from literature.…”

Section: Experiments Results and Discussionmentioning

confidence: 99%

“…A traditional design for ANN is used in many studies [6, 10, 11]. In order to utilize the advantages of this proposed method, traditional ANN is designed in this study to solve the inverse kinematics.…”

Section: Traditional Design Of Artificial Neural Networkmentioning

confidence: 99%

“…The neural networks were multilayered perceptron (MLP) with a backpropagation training algorithm for reducing the complexity of the algorithm and calculation (matrix inversion) of inverse geometric of robotic arm. The result showed a mean squared error (MSE) in performance near to 10 −5 [6]. A high-order-logic theorem was used for solving the kinematics analysis of six-axis revolute joint robot.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A New Artificial Neural Network Approach in Solving Inverse Kinematics of Robotic Arm (Denso VP6242)

Almusawi

lger

Kapucu

2016

Computational Intelligence and Neuroscience

129

View full text Add to dashboard Cite

This paper presents a novel inverse kinematics solution for robotic arm based on artificial neural network (ANN) architecture. The motion of robotic arm is controlled by the kinematics of ANN. A new artificial neural network approach for inverse kinematics is proposed. The novelty of the proposed ANN is the inclusion of the feedback of current joint angles configuration of robotic arm as well as the desired position and orientation in the input pattern of neural network, while the traditional ANN has only the desired position and orientation of the end effector in the input pattern of neural network. In this paper, a six DOF Denso robotic arm with a gripper is controlled by ANN. The comprehensive experimental results proved the applicability and the efficiency of the proposed approach in robotic motion control. The inclusion of current configuration of joint angles in ANN significantly increased the accuracy of ANN estimation of the joint angles output. The new controller design has advantages over the existing techniques for minimizing the position error in unconventional tasks and increasing the accuracy of ANN in estimation of robot's joint angles.

show abstract

Section: Experiments Results and Discussionmentioning

confidence: 99%

Section: Traditional Design Of Artificial Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A New Artificial Neural Network Approach in Solving Inverse Kinematics of Robotic Arm (Denso VP6242)

Almusawi

lger

Kapucu

2016

Computational Intelligence and Neuroscience

129

View full text Add to dashboard Cite

show abstract

“…At the same time, the relationship between the motion and the linked forces and torques are considered in robot dynamics. Kinematics deals with the geometric motion of a robotic manipulator and the inverse kinematics is considered as the most popular and effective method of controlling robot arm [7]. This method proposes the neural network which is trained by the data given by the direct kinematics .This means the end effecter's position and orientation are given as inputs and the neural network identifies which joint configuration corresponds to the given values of the end effector [4].…”

Section: Nowadaysmentioning

confidence: 99%

Inverse kinematics solution of a five joint robot using Feed forward and Elman network

Raj

Raglend

Anand

2015

2015 International Conference on Circuits, Power and Computing Technologies [ICCPCT-2015]

View full text Add to dashboard Cite

Robotics is one of the emerging fields in today's industries and the motion of a manipulator can be expressed based on the kinematical approach. Generally the process of computing the inverse kinematics solution is a tough assignment. By this method the joint angles of the end effector can be retrieved corresponding to the position and orientation which is provided as input. Here the Neural Network approach is adopted and the algorithms employed are Feed forward and Elman Back propagation Neural Network.Since these algorithms are put to use, the inverse kinematics of a five DOF robot can solved and the fetched result will be more precise and less complex, thus finally it can analyzed and compared.

show abstract

“…There are still many reasons as to why the deviations of feet coordinates or leg trajectory appear. When the number of manipulator degrees of freedom increases, and structural flexibility is included, analytical modeling becomes almost impossible [13]. Even simple real world rigid structure displays errors compared to modeled structure.…”

Section: Hexapod Robot Description and Leg Kinematicsmentioning

confidence: 99%

Minimizing Hexapod Robot Foot Deviations Using Multilayer Perceptron

Valaitis

Luneckas

et al. 2015

Int. j. adv. robot. syst.

View full text Add to dashboard Cite

Rough-terrain traversability is one of the most valuable characteristics of walking robots. Even despite their slower speeds and more complex control algorithms, walking robots have far wider usability than wheeled or tracked robots. However, efficient movement over irregular surfaces can only be achieved by eliminating all possible difficulties, which in many cases are caused by a high number of degrees of freedom, feet slippage, frictions and inertias between different robot parts or even badly developed inverse kinematics (IK). In this paper we address the hexapod robot-foot deviation problem. We compare the foot-positioning accuracy of unconfigured inverse kinematics and Multilayer Perceptron-based (MLP) methods via theory, computer modelling and experiments on a physical robot. Using MLP-based methods, we were able to significantly decrease deviations while reaching desired positions with the hexapod's foot. Furthermore, this method is able to compensate for deviations of the robot arising from any possible reason.

show abstract

Applying Neural Network Architecture for Inverse Kinematics Problem in Robotics

Abstract: One of the most important problems in robot kinematics

Cited by 60 publications

References 4 publications

A New Artificial Neural Network Approach in Solving Inverse Kinematics of Robotic Arm (Denso VP6242)

A New Artificial Neural Network Approach in Solving Inverse Kinematics of Robotic Arm (Denso VP6242)

Inverse kinematics solution of a five joint robot using Feed forward and Elman network

Minimizing Hexapod Robot Foot Deviations Using Multilayer Perceptron

Contact Info

Product

Resources

About