This paper focuses on the problem of ultra-low-altitude flight obstacle distance estimation for monocular vision-assisted aircraft. First, the basic error model of distance estimation using sequence images is derived ...
详细信息
Point cloud preprocessing is still a challenging task in the marine environment, for it is difficult to filter out non-obstacle points while avoiding damage to the obstacle completeness. In this paper, we propose a no...
详细信息
ISBN:
(数字)9781728152240
ISBN:
(纸本)9781728152257
Point cloud preprocessing is still a challenging task in the marine environment, for it is difficult to filter out non-obstacle points while avoiding damage to the obstacle completeness. In this paper, we propose a novel data preprocessing method on 3D LiDAR data for the unmanned surface vehicle in the marine environment. It consists of two tasks: outlier removal and wake filtering. As the spatial resolution of LiDAR changes with distance, we exploit distance normalization on statistical outlier filter for robust outlier removal. Considering the gradient difference between wave wake and obstacle surface near the water, we define and calculate the vertical state of point cloud on the range image to obtain the pre-filtering point set, and then use the RANSAC method to filter out the wake points. Experiments on real data has demonstrated the effectiveness of the proposed algorithm both in terms of feasibility and accuracy.
Traditional aircraft control algorithms have a strong dependence on system models, and are difficult to cope with the increasingly complex battlefield environment for intelligent aircrafts. In this paper, a model-free...
详细信息
ISBN:
(数字)9781728176871
ISBN:
(纸本)9781728176888
Traditional aircraft control algorithms have a strong dependence on system models, and are difficult to cope with the increasingly complex battlefield environment for intelligent aircrafts. In this paper, a model-free reinforcement learning is proposed to solve an attitude stabilization problem of an aircraft based online intelligentcontrol strategy. The attitude control problem is firstly formulated as an optimal control problem, and then an adaptive dynamic programming (ADP) technology is applied to compute the corresponding nonlinear Hamilton-Jacobi-Bellman (HJB) equation. Then, an actor-critic neural network structure is established to learn the optimal controller online not requiring the information of the aircraft dynamics. The proposed intelligentcontrol strategy enables the aircraft to adjust its attitude according to the actual mission targets and environments under the proposed online control strategy, so that autonomous learning and intelligent operation can be realized. Finally, simulation examples are presented to validate the proposed model-free based control strategy.
Multi-UAV cooperative formation flying has significant advantages in broadening the scope of UAV operations and improving combat effectiveness. How to realize the cooperative path planning of multi-UAV is an open issu...
详细信息
With the development of modern weapon techniques, radio frequency integrated technology has attracted widespread attention as a key technology to improve the informationalised level of missiles. Radar and communicatio...
详细信息
In many-objective optimization problems (MaOPs), it is a difficult task for evolutionary algorithms to balance convergence and diversity while rapidly converging to the Pareto front. As the number of objectives increa...
详细信息
Aiming at the problem of sudden threat avoidance in the process of aircraft formation cooperative penetration, formation collision avoidance strategies based on improved artificial potential field method are proposed....
详细信息
ISBN:
(数字)9781728180250
ISBN:
(纸本)9781728180267
Aiming at the problem of sudden threat avoidance in the process of aircraft formation cooperative penetration, formation collision avoidance strategies based on improved artificial potential field method are proposed. The effective range of the artificial repulsion potential field and the collision avoidance airspace of the sudden threat source are established. To improve the artificial potential field, the formation velocity correction coefficient and the threat source entry angle correction coefficient are introduced. In addition, the improved artificial repulsion potential energy function is defined. Based on the improved artificial potential filed in three-dimensional space, the formation collision avoidance controller on the horizontal and altitude channel are proposed respectively. Flight control commands such as rudder angle, aileron rudder angle, and elevator yaw angle are given. The simulation results confirm the security and efficiency of the formation collision avoidance strategy.
Zero-shot Object Detection (ZSD) aims to locate and classify instances of unseen categories. Existing methods focus on learning the mapping from visual space to semantic space, while the learning of discriminative rep...
详细信息
ISBN:
(数字)9781728192284
ISBN:
(纸本)9781728185361
Zero-shot Object Detection (ZSD) aims to locate and classify instances of unseen categories. Existing methods focus on learning the mapping from visual space to semantic space, while the learning of discriminative representations for ZSD has not gained enough attention. In this paper, we demonstrate the necessity to learn discriminative semantic representations for ZSD, and propose a new end-to-end framework for this task. Our framework is able to learn discriminative semantic representations in an augmented space introduced for both user-defined and latent attributes, and refine the user-defined attributes with the help of unseen and external classes. The proposed method is extensively evaluated on two challenging ZSD datasets, and the experimental results show that our method significantly outperforms several existing methods.
The low-cost inertial navigation system/global navigation satellite system (INS/GNSS) integration has been widely used to vehicle navigation. However, the positioning performance often declines due to the weak satelli...
详细信息
ISBN:
(数字)9781728167916
ISBN:
(纸本)9781728167923
The low-cost inertial navigation system/global navigation satellite system (INS/GNSS) integration has been widely used to vehicle navigation. However, the positioning performance often declines due to the weak satellite signals. This paper presents a new approach to improve the accuracy of the vehicle navigation. In contrast to the current methods, a new velocity constraint model is developed to aid the estimation of the navigation errors. The altitude accuracy of GNSS is challenged in comparison with its position in the horizonal plane. Thus, an auxiliary low-cost barometer is used to obtain the height as well. The experimental results demonstrate the benefit of the proposed multi-constraints aiding algorithm.
In order to improve the prediction accuracy of the carbon brush temperature trend of the generator, analyzing the operating state of the generator more accurately, and reduce other accidents like the unplanned outage ...
详细信息
暂无评论