Adaptive Integrated Control for Omnidirectional Mobile Manipulators Based on Neural-Network

2009 ◽  
Vol 3 (4) ◽  
pp. 34-53 ◽  
Author(s):  
Xiang-min Tan ◽  
Dongbin Zhao ◽  
Jianqiang Yi ◽  
Dong Xu
Keyword(s):  
Neural Network ◽  
Large Scale ◽  
Integrated Control ◽  
External Disturbance ◽  
Torque Control ◽  
Mobile Manipulator ◽  
Mobile Manipulators ◽  
Modeling And Control ◽  
Control Approach ◽  
Proposed Model

An omnidirectional mobile manipulator, due to its large-scale mobility and dexterous manipulability, has attracted lots of attention in the last decades. However, modeling and control of such systems are very challenging because of their complicated mechanism. In this article, an unified dynamic model is developed by Lagrange Formalism. In terms of the proposed model, an adaptive integrated tracking controller, based on the computed torque control (CTC) method and the radial basis function neural-network (RBFNN), is presented subsequently. Although CTC is an effective motion control strategy for mobile manipulators, it requires precise models. To handle the unmodeled dynamics and the external disturbance, a RBFNN, serving as a compensator, is adopted. This proposed controller combines the advantages of CTC and RBFNN. Simulation results show the correctness of the proposed model and the effectiveness of the control approach.

Adaptive Integrated Control for Omnidirectional Mobile Manipulators Based on Neural-Network

2011 ◽  
pp. 310-325
Author(s):  
Xiang-min Tan ◽  
Dongbin Zhao ◽  
Jianqiang Yi ◽  
Dong Xu
Keyword(s):  
Neural Network ◽  
Large Scale ◽  
Integrated Control ◽  
External Disturbance ◽  
Torque Control ◽  
Mobile Manipulator ◽  
Mobile Manipulators ◽  
Modeling And Control ◽  
Control Approach ◽  
Proposed Model

An omnidirectional mobile manipulator, due to its large-scale mobility and dexterous manipulability, has attracted lots of attention in the last decades. However, modeling and control of such systems are very challenging because of their complicated mechanism. In this paper, an unified dynamic model is developed by Lagrange Formalism. In terms of the proposed model, an adaptive integrated tracking controller, based on the computed torque control (CTC) method and the radial basis function neural-network (RBFNN), is presented subsequently. Although CTC is an effective motion control strategy for mobile manipulators, it requires precise models. To handle the unmodeled dynamics and the external disturbance, a RBFNN, serving as a compensator, is adopted. This proposed controller combines the advantages of CTC and RBFNN. Simulation results show the correctness of the proposed model and the effectiveness of the control approach.

A fully automated method of human identification based on dental panoramic radiographs using a convolutional neural network

2021 ◽  
Author(s):  
Young Hyun Kim ◽  
Eun-Gyu Ha ◽  
Kug Jin Jeon ◽  
Chena Lee ◽  
Sang-Sun Han
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
High Speed ◽  
Large Scale ◽  
Oral Surgery ◽  
Human Identification ◽  
Running Time ◽  
Automated Method ◽  
Image Characteristics ◽  
Proposed Model

Objectives: This study aimed to develop a fully automated human identification method based on a convolutional neural network (CNN) with a large-scale dental panoramic radiograph (DPR) dataset. Methods: In total, 2,760 DPRs from 746 subjects who had 2 to 17 DPRs with various changes in image characteristics due to various dental treatments (tooth extraction, oral surgery, prosthetics, orthodontics, or tooth development) were collected. The test dataset included the latest DPR of each subject (746 images) and the other DPRs (2,014 images) were used for model training. A modified VGG16 model with two fully connected layers was applied for human identification. The proposed model was evaluated with rank-1, –3, and −5 accuracies, running time, and gradient-weighted class activation mapping (Grad-CAM)–applied images. Results: This model had rank-1,–3, and −5 accuracies of 82.84%, 89.14%, and 92.23%, respectively. All rank-1 accuracy values of the proposed model were above 80% regardless of changes in image characteristics. The average running time to train the proposed model was 60.9 sec per epoch, and the prediction time for 746 test DPRs was short (3.2 sec/image). The Grad-CAM technique verified that the model automatically identified humans by focusing on identifiable dental information. Conclusion: The proposed model showed good performance in fully automatic human identification despite differing image characteristics of DPRs acquired from the same patients. Our model is expected to assist in the fast and accurate identification by experts by comparing large amounts of images and proposing identification candidates at high speed.

Modeling and control of a mobile manipulator

Robotica ◽  
1998 ◽  
Vol 16 (6) ◽  
pp. 607-613 ◽  
Author(s):  
J. H. Chung ◽  
S. A. Velinsky
Keyword(s):  
Dynamic Model ◽  
Control Method ◽  
Harmful Effect ◽  
Euler Method ◽  
Friction Model ◽  
Mobile Manipulator ◽  
Wheel Slip ◽  
Modeling And Control ◽  
Control Approach ◽  
And Control

This paper concerns the modeling and control of a mobile manipulator which consists of a robotic arm mounted upon a mobile platform. The equations of motion are derived using the Lagrange-d'Alembert formulation for the nonholonomic model of the mobile manipulator. The dynamic model which considers slip of the platform's tires is developed using the Newton-Euler method and incorporates Dugoff's tire friction model. Then, the tracking problem is investigated by using a well known nonlinear control method for the nonholonomic model. The adverse effect of the wheel slip on the tracking of commanded motion is discussed in the simulation. For the dynamic model, a variable structure control approach is employed to minimize the harmful effect of the wheel slip on the tracking performance. The simulation results demonstrate the effectiveness of the proposed control algorithm.

Research of Torque Control in Large-Scale Wind Turbine

2011 ◽  
Vol 383-390 ◽  
pp. 3479-3485
Author(s):  
Wei Li ◽  
Jian Xu
Keyword(s):  
Neural Network ◽  
Wind Turbine ◽  
Large Scale ◽  
Rbf Neural Network ◽  
Dynamic Performance ◽  
Good Control ◽  
State Equation ◽  
Torque Control ◽  
Scale Variable ◽  
Adaptive Ability

PID torque damper controller was designed and PID parameters were set with RBF neural network for the torque control of large-scale variable speed pitch regulated (VSPR) wind turbine. The system state equation can be extracted by the process of modal linearization using Bladed software, then PID controller was designed, parameters optimized and verification of design test with the control system of 3MW wind turbine was taken finally. The simulation result shows that the damper controller designed reduces driving chain vibration obviously, the adaptive ability and dynamic performance of system is improved with the use of RBF neural network which makes the system with good control quality.

scholarly journals OPTIMUM NUMBERS OF SINGLE NETWORK FOR COMBINATION IN MULTIPLE NEURAL NETWORKS MODELING APPROACH FOR MODELING NONLINEAR SYSTEM

2012 ◽  
Vol 12 (6) ◽  
Author(s):  
Zainal Ahmad ◽  
Rabiatul Adawiah Mat Noor
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Nonlinear Process ◽  
Process Models ◽  
Optimum Number ◽  
Modeling And Control ◽  
Proposed Model ◽  
Multiple Neural Networks ◽  
Combination Approach ◽  
Multiple Network

This paper is focused on finding the optimum number of single networks in multiple neural networks combination to improve neural network model robustness for nonlinear process modeling and control. In order to improve the generalization capability of single neural network based models, combining multiple neural networks is proposed in this paper. By studying the optimum number of network that can be combined in multiple network combination, the researcher can estimate the complexity of the proposed model then obtained the exact number of networks for combination. Simple averaging combination approach is implemented in this paper which is applied to nonlinear process models. It is shown that the optimum number of networks for combination can be obtained hence enhancing the performance of the proposed model.

scholarly journals TANGO: Commonsense Generalization in Predicting Tool Interactions for Mobile Manipulators

2021 ◽  
Author(s):  
Shreshth Tuli ◽  
Rajas Bansal ◽  
Rohan Paul ◽  
Mausam .
Keyword(s):  
Neural Network ◽  
Neural Model ◽  
Mobile Manipulator ◽  
Mobile Manipulators ◽  
Commonsense Knowledge ◽  
Symbolic Action ◽  
World State ◽  
The World ◽  
Human Teachers ◽  
High Level

Robots assisting us in factories or homes must learn to make use of objects as tools to perform tasks, e.g., a tray for carrying objects. We consider the problem of learning commonsense knowledge of when a tool may be useful and how its use may be composed with other tools to accomplish a high-level task instructed by a human. We introduce TANGO, a novel neural model for predicting task-specific tool interactions. TANGO is trained using demonstrations obtained from human teachers instructing a virtual robot in a physics simulator. TANGO encodes the world state consisting of objects and symbolic relationships between them using a graph neural network. The model learns to attend over the scene using knowledge of the goal and the action history, finally decoding the symbolic action to execute. Crucially, we address generalization to unseen environments where some known tools are missing, but alternative unseen tools are present. We show that by augmenting the representation of the environment with pre-trained embeddings derived from a knowledge-base, the model can generalize effectively to novel environments. Experimental results show a 60.5-78.9% improvement over the baseline in predicting successful symbolic plans in unseen settings for a simulated mobile manipulator.

Mobile Operations Performed by Mobile Manipulators on Irregular Terrain - Torque Compensation Using Neural Networks for Disturbance Torques Produced by Irregular Terrain -

1998 ◽  
Vol 10 (5) ◽  
pp. 377-386 ◽  
Author(s):  
Mamoru Minami ◽  
◽  
Masatoshi Hatano ◽  
Toshiyuki Asakura ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Adaptive Control ◽  
Control System ◽  
Horizontal Plane ◽  
Mobile Manipulator ◽  
Mobile Manipulators ◽  
Adaptive Control System ◽  
Control Performance ◽  
Irregular Terrain

In the present study, we propose a control system for mobile operations of mobile manipulators traveling on irregular terrain. Irregularities exist even in structures such as man-made floors of factories and buildings. Since the hand of a mobile manipulator is often required to operate precisely while traveling on irregular terrain and it is subject to disturbance torques caused by traveling on terrain, a method for decreasing control errors caused by disturbances due to terrain must be considered. In the present paper, an adaptive control system including a compensator that uses a neural network, i.e., a neuro adaptive control system, is proposed. In addition, we discuss the control performance of the proposed control system, and show that the control system can decrease control errors occurring on irregular terrain to the levels of errors that occur while traveling on a horizontal plane.

scholarly journals Using Convolution Neural Network for Defective Image Classification of Industrial Components

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Hao Wu ◽  
Zhi Zhou
Keyword(s):  
Neural Network ◽  
Experimental Study ◽  
Deep Learning ◽  
Large Scale ◽  
Intelligent System ◽  
Convolution Neural Network ◽  
Lens Distortion ◽  
Proposed Model ◽  
Industrial Cameras

Computer vision provides effective solutions in many imaging relation problems, including automatic image segmentation and classification. Artificially trained models can be employed to tag images and identify objects spontaneously. In large-scale manufacturing, industrial cameras are utilized to take constant images of components for several reasons. Due to the limitations caused by motion, lens distortion, and noise, some defective images are captured, which are to be identified and separated. One common way to address this problem is by looking into these images manually. However, this solution is not only very time-consuming but is also inaccurate. The paper proposes a deep learning-based artificially intelligent system that can quickly train and identify faulty images. For this purpose, a pretrained convolution neural network based on the PyTorch framework is employed to extract discriminating features from the dataset, which is then used for the classification task. In order to eliminate the chances of overfitting, the proposed model also employed Dropout technology to adjust the network. The experimental study reveals that the system can precisely classify the normal and defective images with an accuracy of over 91%.

scholarly journals Dynamic Multi-Task Learning with Convolutional Neural Network

2017 ◽  
Author(s):  
Yuchun Fang ◽  
Zhengyan Ma ◽  
Zhaoxiang Zhang ◽  
Xu-Yao Zhang ◽  
Xiang Bai
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Flexible Structure ◽  
Strong Assumption ◽  
Task Learning ◽  
Proposed Model ◽  
Task Transfer ◽  
Incremental Training ◽  
Traditional Approaches

Multi-task learning and deep convolutional neural network (CNN) have been successfully used in various fields. This paper considers the integration of CNN and multi-task learning in a novel way to further improve the performance of multiple related tasks. Existing multi-task CNN models usually empirically combine different tasks into a group which is then trained jointly with a strong assumption of model commonality. Furthermore, traditional approaches usually only consider small number of tasks with rigid structure, which is not suitable for large-scale applications. In light of this, we propose a dynamic multi-task CNN model to handle these problems. The proposed model directly learns the task relations from data instead of subjective task grouping. Due to its flexible structure, it supports task-wise incremental training, which is useful for efficient training of massive tasks. Specifically, we add a new task transfer connection (TTC) between the layers of each task. The learned TTC is able to reflect the correlation among different tasks guiding the model dynamically adjusting the multiplexing of the information among different tasks. With the help of TTC, multiple related tasks can further boost the whole performance for each other. Experiments demonstrate that the proposed dynamic multi-task CNN model outperforms traditional approaches.

Sign in / Sign up

Export Citation Format

Share Document