This paper is concerned with trajectory planning problems for UAVs operating near ground.Most existing studies focus on solving the problem of collision-free trajectory planning between pre-defined path points,but ign...This paper is concerned with trajectory planning problems for UAVs operating near ground.Most existing studies focus on solving the problem of collision-free trajectory planning between pre-defined path points,but ignore the need of navigation method for UAVs working on specific operating surfaces in near-ground space.In this paper,a novel near-ground trajectory planning framework is proposed,where the hybrid voxel-surfel map is developed to model the environment with special attention to the uneven operating surface.To improve the frequency of updates,a probability-based surfel fusion method and a resolution adaptive adjustment method based on the fusion result are proposed in this paper.By using possibility information in the map,a path search method is established to generate the initial trajectory.The trajectory is then further optimized based on map gradient information to generate a final trajectory that tracks the specified operating surface according to the task requirements.Compared with existing methods,the multi-resolution hybrid voxel-surfel map proposed in this paper has advantages in terms of operating efficiency.A series of experiments in simulated and real scenarios validate the effectiveness of the proposed trajectory planning framework.展开更多
The rich data provided by satellites and unmanned aerial vehicles bring opportunities to directly model aerial image features by extracting their spatial and structural patterns.Although convolutional autoencoders(CAE...The rich data provided by satellites and unmanned aerial vehicles bring opportunities to directly model aerial image features by extracting their spatial and structural patterns.Although convolutional autoencoders(CAEs)have been attained a remarkable performance in ideal aerial image feature extraction,they are still challenging to extract information from noisy images which are generated from capture and transmission.In this paper,a novel CAE-based noise-robust unsupervised learning method is proposed for extracting high-level features accurately from aerial images and mitigating the effect of noise.Different from conventional CAEs,the proposed method introduces the noise-robust module between the encoder and the decoder.Besides,several pooling layers in CAEs are replaced by convolutional layers with stride=2.The performance of feature extraction is evaluated by the prediction accuracy and the accuracy loss in image classification experiments.A 5-classes aerial optical scene and a 9-classes hyperspectral image(HSI)data set are utilized for optical image and HSI feature extraction,respectively.Highlevel features extracted from aerial images are utilized for image classification by a linear support vector machine(SVM)classifier.Experimental results indicate that the proposed method improves the classification accuracy for noisy images(Gaussian noise 2Dσ=0.1,3Dσ=60)in both optical images(2D 87.5%)and HSIs(3D 85.6%)compared with the traditional CAE(2D 78.6%,3D 84.2%).The accuracy loss in classification experiments increases with the increment of noise.Compared with the traditional CAE(2D 15.7%,3D 11.8%),the proposed method shows the lower classification accuracy loss in experiments(2D 0.3%,3D 6.3%).The proposed unsupervised noise-robust feature extraction method attains desirable classification accuracy in ideal input and enhances the feature extraction capability from noisy input.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.62225305,12072088,62003117,and 62003118)the National Defense Basic Scientific Research Program of China(Grant No.JCKY2020603B010)+1 种基金the Lab of Space Optoelectronic Measurement&Perception(Grant No.LabSOMP-2021-06)the Natural Science Foundation of Heilongjiang Province,China(Grant No.ZD2020F001)。
文摘This paper is concerned with trajectory planning problems for UAVs operating near ground.Most existing studies focus on solving the problem of collision-free trajectory planning between pre-defined path points,but ignore the need of navigation method for UAVs working on specific operating surfaces in near-ground space.In this paper,a novel near-ground trajectory planning framework is proposed,where the hybrid voxel-surfel map is developed to model the environment with special attention to the uneven operating surface.To improve the frequency of updates,a probability-based surfel fusion method and a resolution adaptive adjustment method based on the fusion result are proposed in this paper.By using possibility information in the map,a path search method is established to generate the initial trajectory.The trajectory is then further optimized based on map gradient information to generate a final trajectory that tracks the specified operating surface according to the task requirements.Compared with existing methods,the multi-resolution hybrid voxel-surfel map proposed in this paper has advantages in terms of operating efficiency.A series of experiments in simulated and real scenarios validate the effectiveness of the proposed trajectory planning framework.
基金supported by the National Defense Basic Scientific Research Program of China(Grant No.JCKY2018603C015)the Cultivation Plan of Major Research Program of Harbin Institute of Technology(Grant No.ZDXMPY20180101)。
文摘The rich data provided by satellites and unmanned aerial vehicles bring opportunities to directly model aerial image features by extracting their spatial and structural patterns.Although convolutional autoencoders(CAEs)have been attained a remarkable performance in ideal aerial image feature extraction,they are still challenging to extract information from noisy images which are generated from capture and transmission.In this paper,a novel CAE-based noise-robust unsupervised learning method is proposed for extracting high-level features accurately from aerial images and mitigating the effect of noise.Different from conventional CAEs,the proposed method introduces the noise-robust module between the encoder and the decoder.Besides,several pooling layers in CAEs are replaced by convolutional layers with stride=2.The performance of feature extraction is evaluated by the prediction accuracy and the accuracy loss in image classification experiments.A 5-classes aerial optical scene and a 9-classes hyperspectral image(HSI)data set are utilized for optical image and HSI feature extraction,respectively.Highlevel features extracted from aerial images are utilized for image classification by a linear support vector machine(SVM)classifier.Experimental results indicate that the proposed method improves the classification accuracy for noisy images(Gaussian noise 2Dσ=0.1,3Dσ=60)in both optical images(2D 87.5%)and HSIs(3D 85.6%)compared with the traditional CAE(2D 78.6%,3D 84.2%).The accuracy loss in classification experiments increases with the increment of noise.Compared with the traditional CAE(2D 15.7%,3D 11.8%),the proposed method shows the lower classification accuracy loss in experiments(2D 0.3%,3D 6.3%).The proposed unsupervised noise-robust feature extraction method attains desirable classification accuracy in ideal input and enhances the feature extraction capability from noisy input.