Eddy current brake is an electromagnetic device which can outputs the braking force or torque base on Faraday law of electromagnetic induction and the equation of Lorentz force. Relative to the traditional mechanical ...
详细信息
This paper proposes an artificial neural network to determine orientation using polarized skylight. This neural network has specific dilated convolution, which can extract light intensity information of different pola...
详细信息
This paper proposes an artificial neural network to determine orientation using polarized skylight. This neural network has specific dilated convolution, which can extract light intensity information of different polarization directions. Then, the degree of polarization (DOP) and angle of polarization (AOP) are directly extracted in the network. In addition, the exponential function encoding of orientation is designed as the network output, which can better reflect the insect’s encoding of polarization information and improve the accuracy of orientation determination. Finally, training and testing were conducted on a public polarized skylight navigation dataset, and the experimental results proved the stability and effectiveness of the network.
This paper proposed a new disturbance observer (DO) based on the fixed-time supper-twisting algorithm (FTSTA) for rejecting perturbations of secure communication of the fractional-order chaotic systems (FOCSs). First,...
详细信息
Car-following is the most common driving scenario where a following vehicle follows a lead vehicle in the same lane. One crucial factor of car-following behavior is driving style which affects speed and gap selection,...
详细信息
Car-following is the most common driving scenario where a following vehicle follows a lead vehicle in the same lane. One crucial factor of car-following behavior is driving style which affects speed and gap selection, acceleration pattern, and fuel consumption. However, existing car-following research used limited categories of driving style through pre-defined patterns and failed to encode driving style into data-driven car-following models. To address these limitations, we propose the Aggressiveness Informed Car-Following (AICF) modeling approach, which embeds driving style as a dynamic input feature in data-driven car-following models. In detail, We design driving aggressiveness tokens using four physical quantities (jerk, acceleration, relative speed, and relative spacing) to capture the heterogeneity of driving aggressiveness. These tokens were then embedded into a physics-informed Long Short-Term Memory (LSTM) based car-following model for trajectory prediction. To evaluate the effectiveness of our approach, we conducted extensive experiments based on 12,540 car-following events extracted from the HighD dataset and 24,093 events from the Lyft dataset. Compared to models devoid of considerations for driving aggressiveness levels, AICF exhibits superior efficacy in mitigating the Mean Square Error (MSE) of spacing and collision rate. To the best of our knowledge, this is the first work to directly incorporate real-time driving aggressiveness tokens as input features into data-driven car-following models, enabling a more comprehensive understanding of aggressiveness in car-following behavior. IEEE
This paper investigates the influence of permanent magnet (PM) numbers and stator/rotor pole number combinations (S/R combinations) on two asymmetric consequent-pole hybrid excited flux-reversal machines (ACPHEFRMs). ...
详细信息
Microgrids (MGs) have emerged as a promising solution to enhance the reliability and sustainability of modern power distribution systems. In recent years, there has been a growing interest in interconnecting multiple ...
详细信息
With the development of camera technology,high-speed cameras have greatly contributed to capturing the movement and posture of animals,which has dramatically promoted experimental biology *** the same time,with the co...
详细信息
With the development of camera technology,high-speed cameras have greatly contributed to capturing the movement and posture of animals,which has dramatically promoted experimental biology *** the same time,with the concept of bionics gradually gaining popularity among researchers,the design of robots is absorbing more and more biological features,where the interest in the bio-inspired robot is hewed *** with the traditional robot,the bio-inspired robot imitates the motion pattern to achieve similar propulsion features,which may be more effective and *** this paper,the motion patterns of aquatic animals are divided into four categories according to their propulsion mechanisms:drag-based,lift-based,jet-based,and *** bio-inspired robots imitating aquatic prototypes are introduced and ***,the prospect of aquatic bio-inspired robots is discussed.
Wireless power transmission (WPT) systems are usually analyzed and designed with only the resonant frequency space in mind, whereas in practice the use of square-wave inverter sources introduces harmonics into the sys...
详细信息
Origami provides an opportunity to construct a wide range of 3D functional structures by folding a flat sheet. It can be used to develop various soft functional robots by combining soft smart actuators. However, a sim...
详细信息
Multiple microgrids (MGs) being interconnected permits a high penetration of renewable energy sources while also improving the reliability and generation efficiency of the interconnected MG system. However, an effecti...
详细信息
暂无评论