A new visual servo control scheme for a robotic manipulator is presented in this paper, where a back propagation (BP) neural network is used to make a direct transition from image feature to joint angles without req...
详细信息
A new visual servo control scheme for a robotic manipulator is presented in this paper, where a back propagation (BP) neural network is used to make a direct transition from image feature to joint angles without requiring robot kinematics and camera calibration. To speed up the convergence and avoid local minimum of the neural network, this paper uses a genetic algorithm to find the optimal initial weights and thresholds and then uses the BP Mgorithm to train the neural network according to the data given. The proposed method can effectively combine the good global searching ability of genetic algorithms with the accurate local searching feature of BP neural network. The Simulink model for PUMA560 robot visual servo system based on the improved BP neural network is built with the Robotics Toolbox of Matlab. The simulation results indicate that the proposed method can accelerate convergence of the image errors and provide a simple and effective way of robot control.
To tackle the multi-objective problem in the process of tandem cold rolling, a mathematical model of multi-object optimization is presented. Taking equal relatively power and prevent slippage as objective functions. A...
详细信息
In this paper,adaptive finite time consensus control problem is investigated for multiple mechanical systems with *** adaptive distributed control algorithms are proposed for the multiple mechanical systems under a sw...
详细信息
ISBN:
(纸本)9781509009107
In this paper,adaptive finite time consensus control problem is investigated for multiple mechanical systems with *** adaptive distributed control algorithms are proposed for the multiple mechanical systems under a switching undirected graph,which is addressed through a novel Markov *** any detailed information of the system model,the adaptive distributed controller has a faster and higher precision tracking *** is shown that the states of the mechanical systems can reach a consensus within finite *** finally,an illustrative simulation on the multiple robotic manipulators is given to demonstrate the effectiveness of the proposed controller.
All space manipulators are debugged on the ground and on-orbit serviced in space. Compared with in ground gravity environment their friction characteristics in space microgravity environment have great changes. For sa...
详细信息
ISBN:
(纸本)9781509009107
All space manipulators are debugged on the ground and on-orbit serviced in space. Compared with in ground gravity environment their friction characteristics in space microgravity environment have great changes. For sake of tracking the desired trajectory, in both ground and space, considering these characteristics, a friction compensation control method based on an Active Disturbance Rejection control(ADRC) is proposed and its effectiveness is validated on a planar 2-DOF free-floating space manipulator. The friction models and the dynamic models under different gravity environment have been derived based on the torque balance, the Kane equation and the Lagrange method. Particle Swarm Optimization(PSO) is put forward to optimize parameters of ADRC so as to improve the efficiency of designing process. Compared with PD controller in tracking simulation under different gravity environment, the results verify the advantage of the proposed improved control method.
Comprehensive learning particle swarm optimization(CLPSO) algorithm has a good performance in overcoming premature convergence and avoiding getting stuck in local minima, which are shortcomings in particle swarm opt...
详细信息
ISBN:
(纸本)9781538629185
Comprehensive learning particle swarm optimization(CLPSO) algorithm has a good performance in overcoming premature convergence and avoiding getting stuck in local minima, which are shortcomings in particle swarm optimization. It can solve complex, multi-modal of single-objective problems, but it has not such performance in handling multi-objective optimization problems because of the difficulty of selective solution mechanism. In this article, a multi-objective decomposition particle swarm optimization based on comprehensive learning strategy is proposed, which uses a comprehensive learning strategy for multi-objective problems to prevent premature convergence;updates the leading particles by decomposition method to enhance the distribution of solutions;adds the archive to preserve non-dominated solutions, and adopts mutation in archive to avoid falling into local optimum. The proposed approach is compared with three multi-objective evolutionary algorithms and the results indicate that the proposed approach is competitive respect to which it is compared in most of the test problems adopted.
Considering that gravity on the ground alignment phase is different from that in space application phase, an adaptive backstepping sliding mode control method is proposed to achieve the attitude control and vibration ...
详细信息
ISBN:
(纸本)9781467374439
Considering that gravity on the ground alignment phase is different from that in space application phase, an adaptive backstepping sliding mode control method is proposed to achieve the attitude control and vibration suppression of the flexible spacecraft under different gravity environment. Fully considering the change of dynamic models, the sliding mode controller is designed according to the backstepping theory to control the flexible spacecraft under the influence of model and disturbances uncertainties, and the adaptive control laws are proposed to estimate the disturbances and gravity item online. The control strategy can guarantee the stability of the system based on the Lyapunov theory. The simulation results show that the controller is effective in attitude control and vibration suppression of the flexible spacecraft under different gravity environment, and has important value for theoretical research and engineering application.
The adaptive H_∞ control problem of multi-machine power system in the case of disturbances and uncertain parameters is discussed,based on a Hamiltonian *** the effect of time delay during control and transmission,a H...
详细信息
The adaptive H_∞ control problem of multi-machine power system in the case of disturbances and uncertain parameters is discussed,based on a Hamiltonian *** the effect of time delay during control and transmission,a Hamilton model with control time delay is ***-Krasovskii function is selected,and a controller which makes the system asymptotically stable is *** controller not only achieves the stability control for nonlinear systems with time delay,but also has the ability to suppress the external disturbances and adaptive ability to system parameter *** simulation results show the effect of the controller.
This paper presents a method of binocular vision obstacle detection based on SIFT feature matching algorithm. First, a model of depth measurement based on stereo vision is built, it does not require resume the three-d...
详细信息
Based on the design concept of virtual instrument and the design method of function modulation, using PC machine and data acquisition card as hardware system, proposed a design of sewage multi-parameter online monitor...
详细信息
In this paper,a compressive feedback scheme based on compressed sensing is investigated to reduce feedback load and enhance the sum throughput at low feedback rates for underwater acoustic MIMO ***,to avoid the outof-...
详细信息
ISBN:
(纸本)9781509009107
In this paper,a compressive feedback scheme based on compressed sensing is investigated to reduce feedback load and enhance the sum throughput at low feedback rates for underwater acoustic MIMO ***,to avoid the outof-date channel state information at the transmitter under the high dynamic underwater channel,we present a modified SL0(M-SLO) algorithm to recover the CSI at the transmitter,which adopts more steep approximate hyperbolic tangent function to approximate the l norm in the *** minimization problem of the l norm canbe transformed into a convex optimization problem for the smoothed ***,in order to solve the problem of slow convergence and inaccuracy estimation caused by notched ejfect of the gradient method,hybrid optimization algorithm that combines the advantages of the gradient method and the revised Newton method is introduced to improve the accuracy of sparse *** simulations show that the recovery accuracy and speed are improved by the proposed M-SL0 algorithm comparing with SL0,OMP ***,CSI feedback based compressive sensing performs better than the feedback based on a vector quantitation codebook.
暂无评论