In order to solve the autonomous path planning problem with terrain aided navigation constraints, a navigation-first path planning method was adopted, that is, the distribution of terrain matching regions and the drif...
详细信息
In order to solve the autonomous path planning problem with terrain aided navigation constraints, a navigation-first path planning method was adopted, that is, the distribution of terrain matching regions and the drift of navigation errors were given priority, and the path planning problem was transformed into the shortest path problem of single source directed graph to determine the nodes on the path. Secondly, the path planning between adjacent nodes is transformed into a path planning problem with initial direction constraint and terminal direction freedom/constraint, and the lateral path is smoothed. Finally, for the local path passing through the no-fly zone, the obstacle avoidance path planning with initial and terminal direction constraints is carried out based on convex optimization method. The simulation results show that the autonomous path planning method considering terrain aided navigation constraints can plan the shortest flight path under the constraints of navigation accuracy, maneuverability and no-fly zone.
We present an efficient two-phase approach to motion planning for fixed-wing Unmanned Aerial Vehicles (UAV) navigating in complex 3D air slalom environments. Firstly, in discrete 3D workspace, a global planner compute...
详细信息
ISBN:
(纸本)9781665476881
We present an efficient two-phase approach to motion planning for fixed-wing Unmanned Aerial Vehicles (UAV) navigating in complex 3D air slalom environments. Firstly, in discrete 3D workspace, a global planner computer a obstacle-free path roughly which satisfies the kinematic constraints of the UAV. Given a coarse global path, a local planner generate a Dubins curve with collision avoidance based on the UAS's perception constraints, dynamic constraints and the collision perception information received. We also introduce a method of decoupling the horizontal and vertical motion directions of the fixed-wing UAV, realizing the 2D Dubins curve planning in 3D workspace, along with precomputed sets of motion primitives derived from the vehicle dynamics model in order to achieve high efficiency. Finally, the feasibility of two-phase 3D motion planning in appropriate FOV is experimentally demonstrated.
When the aircraft adopt passive sensors to detect external conditions, the detection information we can directly get is the aspect Angle of target. However, the position, velocity, acceleration and other information o...
详细信息
The fighter's war ability is closely related to its maneuver ability. The maneuver measurement index of the new generation fighter changed greatly compared to the traditional rules. This essay firstly introduced t...
详细信息
In this paper, an autonomous positioning method based on coarse-to-fine multi-modal image matching is proposed for UAV navigation in GPS denied environment. Coarse image matching refers to roughly determining the appr...
详细信息
We proposed a tightly-coupled Lidar-visual-inertial odometry and mapping method, which takes advantage of measurement of Lidar, visual and inertial sensors to achieve highly accurate, real-time 6DoF state estimation a...
We proposed a tightly-coupled Lidar-visual-inertial odometry and mapping method, which takes advantage of measurement of Lidar, visual and inertial sensors to achieve highly accurate, real-time 6DoF state estimation and map-building in GNSS-denied environments. The proposed odometry is a tightly-coupled optimization-based method, obtains robust and low drift odometry by fusing pre-integrated IMU measurements, visual features from the image, and geometric features from Lidar data. Further, we adapt an online method to mitigate degeneracy in optimization problems to improve robustness in environmentally degenerate cases. Simulation and real-world experiments show that the proposed method exhibits similar or better robustness and accuracy with the state-of-the-art SLAM methods.
Global Navigation Satellite systems (GNSS) can provide real-time positioning information for outdoor users, but cannot for indoor scenarios or heavily occluded outdoor scenarios. Strap-down Inertial Navigation system ...
Global Navigation Satellite systems (GNSS) can provide real-time positioning information for outdoor users, but cannot for indoor scenarios or heavily occluded outdoor scenarios. Strap-down Inertial Navigation system (SINS) are widely used to locate people in complex interior or heavily occluded outdoor scenarios due to its light weight and low power consumption. However, IMU of SINS are noisy, and the sampling data error is large, which is a divergence of the error with time. Therefore, it will generate a positioning accumulation error, which affects the final positioning accuracy. The problem of cumulative IMU errors is usually dealt with by Zero-Velocity Update (ZUPT). The zero-velocity detection part of basic ZUPT method usually uses a single threshold to determine the gait of pedestrian, which often has the problem of gait misjudgment and omission. To address these problems, this paper proposes a composite conditional detection method to solve the problem of misjudgment in the zero-velocity interval. In addition, we redesign the zero-velocity update algorithm and uses the Cubature Kalman filter (CKF) for pedestrian positioning error correction. The experimental results demonstrate that the proposed ZUPT method based on dual-threshold detection can better detect the interval between pedestrian motion and stationery than ones with single threshold. The zero-velocity update algorithm based on CKF has higher performance than conventional EKF and UKF methods, which constrains the cumulative error of SINS to about 0.2% of the whole walking distance.
This paper proposes Safe Tracker, an autonomous aerial tracking framework based on vision sensor that can deal with challenging tracking missions and guarantee safety and visibility. Firstly, a RGB-D sensor based segm...
This paper proposes Safe Tracker, an autonomous aerial tracking framework based on vision sensor that can deal with challenging tracking missions and guarantee safety and visibility. Firstly, a RGB-D sensor based segmentation method is employed to locate the target in real-time. Then target motion is predicted for a short time horizon, based on which a heuristic path searching method is applied to generate an occlusion-free path. Finally, particular formulations to balance visibility and safety are designed, and an effective non-linear trajectory optimization method enables to generate an optimal tracking trajectory. Autonomous aerial tracking experiments using a vision sensor are conducted to demonstrate the effectiveness of the proposed Safe Tracker in a challenging cluttered forest and a room full of sharp turns using Gazebo. Benchmark comparisons validate that our method tracks more safely and robustly than the state-of-art method.
As the largest class of small non-coding RNAs, piRNAs primarily present in the reproductive cells of mammals, which influence post-transcriptional processes of mRNAs in multiple ways. Effective methods for predicting ...
As the largest class of small non-coding RNAs, piRNAs primarily present in the reproductive cells of mammals, which influence post-transcriptional processes of mRNAs in multiple ways. Effective methods for predicting piRNA and mRNA target relationships can help identify piRNA functions, investigate the possibility of piRNAs as biomarkers and therapeutic targets. In this study, we propose a computational approach for classifying the relationships of piRNA-mRNA pairs based on an interactive inference network (IIN). First, we gather piRNA-mRNA target data, collect sequence data by position alignment, and construct a benchmark dataset. Furthermore, a reliable negative set is constructed by positive-unlabeled learning. Finally, we view a piRNA and a mRNA sequence as a premise and hypothesis sentence, respectively, and IIN model is used to predict the relationship between them. The experiments demonstrate that our method effectively characterizes piRNA-mRNA interaction and could be beneficial for researchers to investigate piRNA functions.
Low-light image enhancement (LLIE) is an important task in computer vision, aiming to improve the visual perception or interpretability of images captured in poorly illuminated environments. Recently, deep learning ba...
详细信息
ISBN:
(数字)9798350359145
ISBN:
(纸本)9798350359152
Low-light image enhancement (LLIE) is an important task in computer vision, aiming to improve the visual perception or interpretability of images captured in poorly illuminated environments. Recently, deep learning based methods have been extensively explored to address this issue. While many of these methods have achieved significant advancements in various evaluation metrics for LLIE, only a few have made progress in improving inference speed for the resulting images. As a result, achieving both high-quality enhancements and efficient inference speed remains a challenge. To tackle this challenge, we propose SeqEnhance, a fast LLIE method based on a predefined parameterized image processing pipeline. Our approach combines the inference capabilities of deep neural networks for parameter estimation and the efficient processing capabilities of image processing pipelines to generate enhanced images in an end-to-end manner. The experimental results demonstrate that the proposed method achieves competitive performance on image quality evaluation metrics such as PSNR and SSIM with a fast inference speed.
暂无评论