In this paper, a new estimation model based on least squares support vector machine (LS-SVM) is proposed to build up the relationship between Surface electromyogram (sEMG) signal and joint angle of the lower limb. The...
详细信息
The robotic fish with two long fins is one kind of underwater robot system imitating stingray's motion. The robotic fish generates thrust by use of two long fins located on both sides of body symmetrically. A driv...
详细信息
The robotic fish with two long fins is one kind of underwater robot system imitating stingray's motion. The robotic fish generates thrust by use of two long fins located on both sides of body symmetrically. A driver control system for the motion control of fin rays is designed based on FPGA(Field Programmable Gate Array). Several kinds of motion modes can be achieved through tuning motion parameters. In order to facilitate updating control algorithm, reducing the probability of damaging the robot system and improving debugging efficiency, a solution for remote updating the driver program of the robotic fish wirelessly is proposed in this paper based on the dedicated remote system update circuitry integrated in ALTERA FPGA. In addition, a remote update system is designed in this paper. The designed control program updating system facilitates the debugging and optimization of multi-fin coordination control algorithm for the robotic fish with two long fins greatly.
In this paper, a novel learning optimal control scheme is established to design the robust controller of a class of uncertain nonlinear systems. The robust control problem is transformed into the optimal control probl...
详细信息
In this paper, a novel learning optimal control scheme is established to design the robust controller of a class of uncertain nonlinear systems. The robust control problem is transformed into the optimal control problem by properly choosing a cost function that reflects the uncertainty, regulation, and control. Then, the online policy iteration algorithm is presented to solve the Hamilton-Jacobi-Bellman (HJB) equation by introducing a critic neural network. The approximate expression of the optimal control policy can be derived directly. Moreover, the closed-loop system is proved to be uniformly ultimately bounded. The equivalence of the neural-network-based HJB solution of the optimal control problem and the solution of the robust control problem is developed as well. Finally, an example is provided to verify the effectiveness of the constructed approach.
This paper solves distributed consensus tracking problems where the task is to make the multi-agent network, with each agent described by a general linear dynamics, to reach consensus with a leader whose control input...
详细信息
This paper solves distributed consensus tracking problems where the task is to make the multi-agent network, with each agent described by a general linear dynamics, to reach consensus with a leader whose control input is nonzero and not available to any followers. A set of sliding mode surfaces are defined and then fast sliding mode controllers are designed for both reduced order and non-reduced order cases. It is shown that all the trajectories exponentially converge to the sliding mode surfaces in a finite time if the leader has a directed path to at least one of the followers in a strongly connected and detailed balanced directed interaction graph and the leader's control input is bounded. The control Lyapunov function for exponential finite time stability, motivated by the fast terminal sliding mode control, is used to prove the reachability of the sliding mode surfaces. Simulation examples are given to illustrate the theoretical results.
In this paper, we design and develop Vehicle License Plate Recognition (VLPR) System, which is one part of comprehensive video management platform for parking lot. Combined with intelligent video analysis module, the ...
详细信息
As the computing technology develops, micro-simulation becomes more and more important in the Intelligent Transportation systems (ITS) research, because it can provide detailed descriptions of the system. However, for...
详细信息
Feature representations play a crucial role in modern face recognition systems. Most hand-crafted image descriptors usually provide low-level information. In this paper, we propose a novel feature learning method base...
详细信息
ISBN:
(纸本)9781479923427
Feature representations play a crucial role in modern face recognition systems. Most hand-crafted image descriptors usually provide low-level information. In this paper, we propose a novel feature learning method based on deep neural networks to obtain high-level, hierarchical representations for face verification. Learning proceeds in two phases. In the pre-training phase, we train Restricted Boltzmann Ma-chine(RBM) networks for each modular region in the image separately. In the fine-tuning phase, in order to develop good discriminative ability, we stack the RBM networks of each region in deep architecture and combine deep learning with side information constraints in the whole image scale. Finally, we formulate the proposed method as an appropriate optimization problem and adopt gradient descent algorithm to get the optimal solution. We evaluate our method on the LFW dataset. Representations learned from the networks achieve comparable performance (93.11%) to the state-of-art method.
This article describes the control algorithm and software implementation of astronomical tracking based on the mechanical analysis for Five-hundred-meter Aperture Spherical Telescope(FAST) that is being built in Guizh...
详细信息
This article describes the control algorithm and software implementation of astronomical tracking based on the mechanical analysis for Five-hundred-meter Aperture Spherical Telescope(FAST) that is being built in Guizhou province of China, which aims to help astronomers resolve questions in cosmology. On the basis of position and attitude feedback algorithm of cable driven parallel robot, the control of X-Y positioner with feed-forward was introduced and the astronomical tracking experiments were conducted on scale model to verify the validity of control strategy. The future works for focus cabin suspension of FAST are also pointed out.
Facility layout problem (FLP) which deals with the placement of facilities in the plant area is one of the most critical problems in manufacturing systems design. This paper presents a novel facility layout approach b...
详细信息
ISBN:
(纸本)9781479927456
Facility layout problem (FLP) which deals with the placement of facilities in the plant area is one of the most critical problems in manufacturing systems design. This paper presents a novel facility layout approach based on differential evolution (DE) algorithm. Firstly, mathematical model with constraints for the FLP is established. Then, a new facility layout algorithm based on DE is proposed, which can improve the convergence rate by using the interference checking method. Finally, a simulation platform with three-dimensional visualization is developed. The comparison experiments of the proposed method and genetic algorithm (GA) based on robot work cell layout problem show that the proposed method converges faster and can obtain better optimal layout.
Despite the growing number of videos featuring electronic cigarettes, there has been no investigation of the portrayal of these videos. This paper presents the first surveillance data of electronic cigarette videos on...
详细信息
暂无评论