Filters








63,522 Hits in 4.4 sec

Trajectory control of robotic manipulators using neural networks

T. Ozaki, T. Suzuki, T. Furuhashi, S. Okuma, Y. Uchikawa
1991 IEEE transactions on industrial electronics (1982. Print)  
AbsZruct-This paper presents a nonlinear compensator using neural networks for trajectory control of robotic manipulators.  ...  In [6] -[9], a neural network was used in a feedforward loop with a conventional feedback PD controller for manipulator control. As learning went on, the feedfor- Manuscript received  ...  CONCLUSIONS This paper presented a nonlinear compensator using neural networks for trajectory control of robotic manipulators.  ... 
doi:10.1109/41.87587 fatcat:yaf4sm462ba6ndjjq75xpgxpbu

A dual neural network for redundancy resolution of kinematically redundant manipulators subject to joint limits and joint velocity limits

Yunong Zhang, Jun Wang, Youshen Xia
2003 IEEE Transactions on Neural Networks  
In this paper, a recurrent neural network called the dual neural network is proposed for online redundancy resolution of kinematically redundant manipulators.  ...  The dual neural network is simulated to control the PA10 robot manipulator with effectiveness demonstrated.  ...  To reduce network complexity and increase computational efficiency, an early dual-neural-network model [17] was then proposed for kinematic control of redundant manipulators.  ... 
doi:10.1109/tnn.2003.810607 pmid:18238046 fatcat:7xgb5daombb2ficqaovcjn4xie

A dual neural network for bi-criteria kinematic control of redundant manipulators

Yunong Zhang, Jun Wang, Yangsheng Xu
2002 IEEE Transactions on Robotics and Automation  
A dual neural network is presented for the bi-criteria kinematic control of redundant manipulators.  ...  The single-layer dual neural network model with a simple structure is developed for bi-criteria redundant resolution of redundant manipulators subject to robot physical constraints.  ...  To reduce network complexity and increase computational efficiency, a single-layered dual neural network is proposed for kinematic control of redundant manipulators by Xia and Wang [16] .  ... 
doi:10.1109/tra.2002.805651 fatcat:iqst4b32ufczhjov4nazn3lboq

Mathematical Modeling, Analysis, and Advanced Control of Complex Dynamical Systems

Peng Shi, Hamid Reza Karimi, Xiaojie Su, Rongni Yang, Yuxin Zhao
2014 Mathematical Problems in Engineering  
"Localized and energy-efficient topology control in wireless sensor networks using fuzzy-logic control approaches" by J.-F.  ...  Mu designs a novel commandfiltered adaptive fuzzy neural network backstepping control method to retrain chaotic oscillation of marine power system.  ...  Acknowledgments We would like to express our appreciation to all the authors for their contributions. We also thank all the reviewers for their time and help in assessing all the submissions.  ... 
doi:10.1155/2014/280708 fatcat:k2osepurm5airdwnzle6ncjqbu

Table of Contents

2021 2021 9th RSI International Conference on Robotics and Mechatronics (ICRoM)  
quadrotor with variable dihedral angle ...........391 Experimantal Study on Neural Network-ARX and ARMAX Actuation Identification of a 3-DoF Delta Parallel Robot for Accurate Motion Controller Design  ...  : A Novel Machine Learning Method based on Convolutional Neural Networks and Spiking Neural Networks ..............................................................................................  ... 
doi:10.1109/icrom54204.2021.9663492 fatcat:nchpnhiwjbhazeuq3iw4sp2mxu

A Review on Neural Dynamics for Robot Autonomy

Dechao Chen, Shuai Li, Qing Wu
2018 International Journal of Robotics and Control  
The objective of this paper is to present a comprehensive review of the research on neural networks (especially RNNs) for control problems solving of different kinds of robots.  ...  Exploiting neural networks to solve control problems of robots is becoming commonly and effectively in academia and engineering.  ...  Up to now, a large number of effective approaches for robot systems have been creatively proposed and effectively employed, such as the neural networks approach, [137] the active control approach, [  ... 
doi:10.5430/ijrc.v1n1p20 fatcat:mauh7xiorbd4hbaokmzketn7g4

On-line tuning of fuzzy-neural network for adaptive control of nonlinear dynamical systems

Yih-Guang Leu, Tsu-Tian Lee, Wei-Yen Wang
1997 IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)  
The proposed dual network is also shown to be capable of asymptotic tracking for the motion control of kinematically redundant manipulators.  ...  The proposed neural network is composed of a single layer of neurons, and the number of neurons is equal to the dimensionality of the workspace.  ...  Lam for her help in the simulation of the PA-10 manipulator.  ... 
doi:10.1109/3477.650065 pmid:18263111 fatcat:oofw3nlqgfdmphmmyqnb76bqkm

Implicit Contact Dynamics Modeling With Explicit Inertia Matrix Representation for Real-Time, Model-Based Control in Physical Environment

Takeshi D. Itoh, Koji Ishihara, Jun Morimoto
2021 Neural Computation  
To train the proposed network, we develop a two-stage modeling procedure for contact-rich dynamics from a limited number of samples.  ...  Model-based control has great potential for use in real robots due to its high sampling efficiency.  ...  Council for Science, Technology and Innovation (Cabinet Office, Government of Japan).  ... 
doi:10.1162/neco_a_01465 pmid:34915580 fatcat:fh5cnkmsnjcivdyypnbpdsluoa

A dual neural network for kinematic control of redundant robot manipulators

Youshen Xia, Jun Wang
2001 IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)  
The proposed dual network is also shown to be capable of asymptotic tracking for the motion control of kinematically redundant manipulators.  ...  The proposed neural network is composed of a single layer of neurons, and the number of neurons is equal to the dimensionality of the workspace.  ...  Lam for her help in the simulation of the PA-10 manipulator.  ... 
doi:10.1109/3477.907574 pmid:18244777 fatcat:mztujmwyajawvd55ogi6ees65i

Neural Network Based Kinematic Control of the Hyper-Redundant Snake-Like Manipulator [chapter]

Jinguo Liu, Yuechao Wang, Bin Li, Shugen Ma
2007 Lecture Notes in Computer Science  
In this study, we propose an approach based on BP neural network to kinematic control the hyper-redundant snake-like manipulator.  ...  Effectively control of the snake-like manipulator is difficult for its redundancy.  ...  The authors would like to thank the anonymous reviewers for their kind and insightful comments.  ... 
doi:10.1007/978-3-540-72383-7_90 fatcat:lz2tvsf4sff5dakubzuw7zey7m

Recurrent neural networks for minimum infinity-norm kinematic control of redundant manipulators

Han Ding, Jun Wang
1999 IEEE transactions on systems, man and cybernetics. Part A. Systems and humans  
This paper presents two neural network approaches to minimum infinity-norm solution of the velocity inverse kinematics problem for redundant robots.  ...  In each proposed neural network approach, two cooperating recurrent neural networks are used. The first approach employs two Tank-Hopfield networks for linear programming.  ...  Xia for his help in interpreting the primal-dual network.  ... 
doi:10.1109/3468.759273 fatcat:r73rj4uj6fh7vbdtx4g4qfllwm

2020 Index IEEE Journal of Selected Topics in Signal Processing Vol. 14

2020 IEEE Journal on Selected Topics in Signal Processing  
., +, JSTSP Automated Design of Neural Network Architectures With Reinforcement Learning for Detection of Global Manipulations.  ...  Jordao, A., +, JSTSP May 2020 828-837 Dual Dynamic Inference: Enabling More Efficient, Adaptive, and Controllable Deep Inference.  ... 
doi:10.1109/jstsp.2020.3029672 fatcat:6twwzcqpwzg4ddcu2et75po77u

Efficient Learning of Inverse Dynamics Models for Adaptive Computed Torque Control [article]

David Jorge, Gabriella Pizzuto, Michael Mistry
2022 arXiv   pre-print
cost of cubic time complexity rather than linear, as is the case for deep neural networks.  ...  Modelling robot dynamics accurately is essential for control, motion optimisation and safe human-robot collaboration.  ...  of the efficiency of deep neural networks with the non-parametric nature of GP kernel functions.  ... 
arXiv:2205.04796v1 fatcat:pvhcvafprvbgjpqsv6viywuv4u

Malleable Agents for Re-Configurable Robotic Manipulators [article]

Athindran Ramesh Kumar, Gurudutt Hosangadi
2022 arXiv   pre-print
We perform simulations on a 2D N-link arm to show the ability of our network to transfer and generalize efficiently.  ...  We propose a deep reinforcement learning agent with sequence neural networks embedded in the agent to adapt to robotic arms that have a varying number of links.  ...  Neural networks have also played a vital role in designing controllers for re-configurable manipulators.  ... 
arXiv:2202.02395v2 fatcat:lb3nd3gmivedxgfxeg3oijqcui

Comparison of Neural Network and Fuzzy Logic Control for Nonlinear Model of Two Link Rigid Manipulator

Narinder Singh, Bharti Panjwani
2014 International Journal of Control and Automation  
Comparison of Neural Network and Fuzzy Logic controller designed by utilizing this technique is also presented.  ...  A new intelligent scheme based on fixed stabilization technique is proposed in this paper for controlling the system.  ...  Learning, approximation and generalization capabilities of neural network make it suitable for control of nonlinear robotic manipulator.  ... 
doi:10.14257/ijca.2014.7.4.38 fatcat:iwbfo2wimrcwtoj2xd3lhgzzvq
« Previous Showing results 1 — 15 out of 63,522 results