In order to compensate for the impact of time delay on the estimation of object feature point image and image Jacobian matrix and improve the control precision of image-based visual servo system, a Kalman filtering al...
详细信息
In order to compensate for the impact of time delay on the estimation of object feature point image and image Jacobian matrix and improve the control precision of image-based visual servo system, a Kalman filtering algorithm with colored noise is proposed to obtained the current motion state estimation of the feature point with time-delay compensation in the image space, then the accurate image Jacobian matrix under time delay can be obtained. For the above, the following work will be done in this paper: (1) the current motion state estimation of the feature point in the image space is predicted by Kalman filtering algorithm, combined with practical applications, measurement noise is usually as colored noise and can be regarded as a one-order Markov sequence excited by Gauss white noise, then a Kalman filtering recursive model can be derived according to the variance minimization principle of the estimation error;(2) to obtain the measurement vectors estimation which cannot be acquired in the Kalman filtering model owing to the existence of time delay, the relationship between the motion state of the feature point at the prior and later point is established, and a polynomial is fitted by using some of the observed data under the relationship to realize the measurement vectors estimation in the time-delay period. Thus the estimation of the motion state of the feature point at the current time in the image space can be obtained, and the estimation of image Jacobian matrix with time-delay compensation can be obtained. Experimental results validate the feasibility and superiority of this method.
For large-scale industrial processes under closed-loop control, process dynamics directly resulting from control action are typical characteristics and may show different behaviors between real faults and normal chang...
详细信息
The generation of fuzzy rules from samples is significant for fuzzy modelling. To improve the robustness of Wang-Mendel (WM) method, an improved WM method to extract fuzzy rules from all the regularized sample data wa...
详细信息
This paper presents a four-stage localization method for epileptic seizure onset zones (SOZs). This method combines the advantages of both the Shannon-entropy-based complex Morlet wavelet transform (SE-CMWT) and adapt...
详细信息
Deep neural networks have been successfully applied to many data mining problems in recent works. The training of deep neural networks relies heavily upon gradient descent methods, however, which may lead to the failu...
详细信息
Deep neural networks have been successfully applied to many data mining problems in recent works. The training of deep neural networks relies heavily upon gradient descent methods, however, which may lead to the failure of training due to the vanishing gradient (or exploding gradient) and local optima problems. In this paper, we present SEvoAE method based on using Evolutionary Multiobjective Optimization (EMO) algorithm to train single layer auto-encoder, and sequentially learning deeper representation in a stacking way. SEvoAE is able to achieve accurate feature representation with good sparseness by globally simultaneously optimizing two conflicting objective functions and allows users to flexibly design objective functions and evolutionary optimizers. We compare results of the proposed method with existing architectures for seven classification problems, showing that the proposed method is able to outperform existing methods with a reduced risk of overfitting the training data.
In the blast furnace ironmaking process, the running state of the blast furnace can be directly adjusted by the burden operation. Therefore, the explicit relation between the burden operation and the running state var...
详细信息
Large-scale intersections stamped on maps have diverse visual features for detection, while small-scale urban intersections are hard to be identified especially when GPS signals are missing. In this paper, we propose ...
详细信息
ISBN:
(纸本)9781509048052
Large-scale intersections stamped on maps have diverse visual features for detection, while small-scale urban intersections are hard to be identified especially when GPS signals are missing. In this paper, we propose a Hidden Markov Model (HMM) based small-scale intersection detection method utilizing monocular vision. We extract visual cues of road transformations and dynamic vehicles' tracks, and then design an Intersection Scan Model to obtain the potential traversable direction of the current road, which is the primary criterion of the intersection estimation. For better performances, we take the detections of consecutive frames into consideration and finally integrate them into HMM to estimate the probabilities of intersections. Results from KITTI datasets and real-world experiments have shown the functionality of the presented approach.
For the purpose of enhancing compliance of robot joint,an impedance control strategy with new inner torque controller is *** inertia of the motor can be scaled down thanks to this new type of torque *** of different p...
详细信息
ISBN:
(纸本)9781538629185
For the purpose of enhancing compliance of robot joint,an impedance control strategy with new inner torque controller is *** inertia of the motor can be scaled down thanks to this new type of torque *** of different position（motor-side position 9 and link-side position q） feedback strategies are explored through theoretical deviation,simulation and static stiffness *** expressions of static stiffness under both position feedback strategies are obtained with validity verified by Simulink *** with 9 feedback strategy,static stiffness can exceed spring stiffness under q feedback strategy with high desired stiffness,which means wider variation range of static stiffness and this benefits robot applications that require wider variation range of impedance,such as rehabilitation robots and collaborative ***,several experiments with the compliant joint prototype verify the developed controllers and show the efficiency of the proposed control approach in terms of compliant behavior.
In this paper, we investigate a privacy preservation design in the distributed nonsmooth convex optimization with set constraints. To solve the distributed optimization problem while preserving the privacy, we use pse...
详细信息
In this paper, we investigate a privacy preservation design in the distributed nonsmooth convex optimization with set constraints. To solve the distributed optimization problem while preserving the privacy, we use pseudo-subgradients involved with（non-integrable） set-valued functions. Based on pseudo-subgradients, we propose distributed nonsmooth optimization algorithms with keeping subgradient information confidential. Then we prove the correctness and convergence of the distributed privacy preservation optimization algorithms to achieve the exact solution of the original optimization problem.
The assessment of aircraft damage is a key technology in modern flight missions. For a kind of ultra low altitude aircraft, simulation study of the damage caused by the prefabricated fragments is carried out, which is...
详细信息
暂无评论