Vehicle Detection is an important part in intelligent transportation system (ITS) and driver assistance system. Considering vehicles have strong edges and lines in different orientation and scales, in this paper, we p...
详细信息
This paper presents online motion planning for UAV(unmanned aerial vehicle) in complex threat field,including both static threats and moving threats,which can be formulated as a dynamic constrained optimal control ***...
详细信息
This paper presents online motion planning for UAV(unmanned aerial vehicle) in complex threat field,including both static threats and moving threats,which can be formulated as a dynamic constrained optimal control *** horizon control(RHC) based on differential evolution(DE) algorithm is adopted.A location-predicting model of moving threats is established to assess the value of threat that UAV faces in *** flyable paths can be generated by the control inputs which are optimized by DE under the guidance of the objective *** results demonstrate that the proposed method not only generates smooth and flyable paths,but also enables UAV to avoid threats efficiently and arrive at destination safely.
To obtain and update the kernel-bandwidth,we present an adaptive bandwidth obtainment algorithm based on object contour extraction from optical-flow *** combination of modified mountain cluster approach and fast scann...
详细信息
ISBN:
(纸本)9781479900305
To obtain and update the kernel-bandwidth,we present an adaptive bandwidth obtainment algorithm based on object contour extraction from optical-flow *** combination of modified mountain cluster approach and fast scanning window contour extractor guarantees the speed of this algorithm.A novel ellipse detection method based on a modified RANSAC is adopted to reduce the *** results demonstrate that the algorithm select the proper size of tracking kernel-bandwidth with minor extra computational overhead and keep up with the object robustly when the scale changed rapidly.
This article proposes a multi-objective decomposition stochastic particle swarm optimization (MDSPSO) algorithm. In MDSPSO, every particle has a weighted vector constantly. Then, an improved Tchebycheff decomposition ...
详细信息
This article proposes a multi-objective decomposition stochastic particle swarm optimization (MDSPSO) algorithm. In MDSPSO, every particle has a weighted vector constantly. Then, an improved Tchebycheff decomposition method is applied to decompose the multi-objective problem into some single-objective problems. The reference position of every particle is uniformly generated in the zone with the center which is the geometrical center of its current position, the best previous reference position as well as the swarm best reference position. The radius of this zone is the distance from the center to its current position. Then the particle is updated to the new position according to the reference position and its current velocity. The comparisons with the decomposition-based multi-objective particle swarm optimizer (dMOPSO), a multiobjective evolutionary algorithm based on decomposition (MOEA/D), and nondominated sorting genetic algorithm II (NSGA-II) show that the solutions of MDSPSO can be dominated at least with the best diversity. To reduce the computational time by finite element analysis for optimizing the structure parameters of linear motor, artificial neural network is used as the model to evaluate the performance. Finally, MDSPSO is applied to optimize four objectives simultaneously. The practical result is shown that the optimized linear motor has an increased thrust, improved efficiency, reduced fluctuation and manufacturing cost.
This paper proposes a novel sparse variant of auto-encoders as a building block to pre-train deep neural networks. Compared with sparse auto-encoders through KL-divergence, our method requires fewer hyper-parameters a...
详细信息
This paper proposes a novel sparse variant of auto-encoders as a building block to pre-train deep neural networks. Compared with sparse auto-encoders through KL-divergence, our method requires fewer hyper-parameters and the sparsity level of the hidden units can be learnt automatically. We have compared our method with several other unsupervised leaning algorithms on the benchmark databases. The satisfactory classification accuracy (97.92% on MNIST and 87.29% on NORB) can be achieved by a 2-hidden-layer neural network pre-trained using our algorithm, and the whole training procedure (including pre-training and fine-tuning) takes far less time than the state-of-art results.
In the high-precision and high-speed measurement system, the distortion of CCD pixes will give a greater margin of error to measurement results. According to the characteristic of noise leading to the image distortion...
详细信息
In the high-precision and high-speed measurement system, the distortion of CCD pixes will give a greater margin of error to measurement results. According to the characteristic of noise leading to the image distortion, this article establishes the image transformation model. Data fitting based method is used for correcting image distortion. For the distortion caused by camera installation, the perspective transformation is used to correcting the image. And then the four points calibration method is adopted to calibrating the measurement system. Experiments adopt the high speed area array CCD to gather images with the circular facula in the target area launched by the laser, and calculate the real position of the facula in the target area, adopt the high accurate displacement sensor to give the true displacement of the target which is used to verify the real position of the facula in the target area. The results show that the algorithm can reduce the influence of image distortion, which advances the measurement accuracy efficiently.
Hydraulic biped robots have better mobility than conventional wheeled robots, and hydraulic actuator has some incomparable advantages, such as large torque and strong load capacity. In this paper, the biped structure ...
详细信息
Hydraulic biped robots have better mobility than conventional wheeled robots, and hydraulic actuator has some incomparable advantages, such as large torque and strong load capacity. In this paper, the biped structure of robot actuated by hydraulic system is designed to make it simulate human's action better. Meanwhile, for actuating the bipedal locomotion, the design and performance test of electro-hydraulic position servo system based on micro valve-controlled cylinder has been done. Then, the biped robot module can be taken as an inverted pendulum mathematical model to achieve all the gait planning, including starting gait, normal walking gait and stopping gait. Also, the stability of the gait and the feasibility of the gait planning are evaluated through ZMP principle. Finally, the virtual prototype model of biped robot is created to simulate the biped structure of robot and the planning gait, and the stability of walking and the effectiveness of the way of gait planning are verified very well.
The vacuum pumping and liquid injection system is designed to meet the requirement of liquid automatic injection in a closed chamber. It is made up of vacuum pumping subsystem, liquid injection subsystem and control s...
详细信息
This paper focuses on the consensus problem of a class of multiple high-order nonlinear systems with uncertainty under the fixed and undirected communication topology. The distributed virtual control functions of the ...
详细信息
ISBN:
(纸本)9781479900305
This paper focuses on the consensus problem of a class of multiple high-order nonlinear systems with uncertainty under the fixed and undirected communication topology. The distributed virtual control functions of the multi-agent system are constructed by only using their local information in the recursive controller design procedure. A set of distributed cooperative consensus control laws is proposed through combining backstepping and adaptive control techniques. The asymptotic stability of the overall interconnected system is proved relying on Lyapunov stability analysis method. Furthermore, the proposed control scheme can be extended to apply to the condition when the communication graph is directed or time-varying. Finally, simulation is provided to verify the effectiveness of the control algorithms.
We designed a distributed charging coordination method for electric vehicles over a multi-time interval with the so-called progressive second price (PSP) auction mechanism which was proposed by Lasar and Semret in ord...
详细信息
ISBN:
(纸本)9781467357159
We designed a distributed charging coordination method for electric vehicles over a multi-time interval with the so-called progressive second price (PSP) auction mechanism which was proposed by Lasar and Semret in order to efficiently allocate the divisible resources among multi agents. The incentive compatibility holds for the auction games under the PSP mechanism. However due to the cross-elastic correlation among the different charging instants, the marginal valuation of an individual agent at each instant is determined by both the demand at this instant and the total demand at the whole interval. This phenomena makes the underlying auction games distinct from those studied in the literature. As a main contribution of the paper, we showed that the efficient bid profile over the multi-time interval is a Nash equilibrium of the auction systems.
暂无评论