Autonomous flying drone control system
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ZHENJIANG SHIWUJIE UAV TECHNOLOGY CO LTD
- Filing Date
- 2026-06-09
- Publication Date
- 2026-08-07
AI Technical Summary
[0003]无法有效区分无人机自身飞行位移导致的点云位置偏移与真实障碍物产生的点云变化，容易将机体运动造成的正常点云偏移误判为障碍物，或因运动干扰掩盖真实障碍物，出现误判、漏判问题，障碍识别精度低的同时，环境适应性差
[0025]（1）通过以无人机机体为中心，通过正方体空间框选筛选有效三维点云数据，限定近距离避障感知范围的同时，结合机身三维坐标数据的变化，确定相邻帧点云的理论重合区域，这样能够实现在统一运动基准的区域内做差异比对，过滤无人机自身飞行位移带来的点云偏移干扰，有效提升障碍物的识别稳定性与精度。
Smart Images
Figure CN122526258A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of unmanned aerial vehicle (UAV) control technology, specifically to an autonomous flight UAV control system. Background Technology
[0002] Most existing autonomous drones complete their patrol operations using pre-set fixed routes, and their operational mode heavily relies on pre-built global environmental maps, resulting in insufficient onboard real-time environmental perception and dynamic obstacle avoidance capabilities. For example, existing drone lidar obstacle avoidance technology determines the presence of obstacles in the direction of travel by analyzing changes in point cloud data. However, this approach has the following drawbacks in scenarios where drones are continuously moving:
[0003] It cannot effectively distinguish between point cloud position shifts caused by the drone's own flight displacement and point cloud changes caused by real obstacles. It is easy to misjudge normal point cloud shifts caused by drone movement as obstacles, or to obscure real obstacles due to motion interference, resulting in misjudgment and missed judgment. In addition to low obstacle recognition accuracy, it also has poor environmental adaptability. Summary of the Invention
[0004] In view of the deficiencies in the existing technology, the technical problem to be solved by this application is: how to realize the recognition of sudden obstacles and ensure the automatic obstacle avoidance of the UAV.
[0005] To achieve the above objectives, embodiments of this application provide an autonomous flight unmanned aerial vehicle (UAV) control system, characterized in that it includes:
[0006] The flight trajectory generation module is used to: obtain flight trajectory data based on pre-stored flight mission coordinate parameters;
[0007] The data acquisition module is used to: collect three-dimensional point cloud data of the environment and three-dimensional coordinate data of the fuselage during the flight mission performed by the UAV based on the flight trajectory data;
[0008] The obstacle recognition module is used to determine whether there is an actual obstacle based on flight trajectory data, 3D point cloud data and fuselage 3D coordinate data, and to issue an obstacle avoidance alarm.
[0009] The obstacle avoidance optimization module is used to adjust flight trajectory data based on obstacle avoidance alarms.
[0010] In one embodiment, the data acquisition module includes a multi-source data acquisition unit, a data preprocessing unit, and a point cloud data filtering unit. The multi-source data acquisition unit is connected to the data preprocessing unit, and the data preprocessing unit is connected to the point cloud data filtering unit.
[0011] In one embodiment, the multi-source data acquisition unit is used to acquire three-dimensional point cloud data and fuselage three-dimensional coordinate data;
[0012] The data preprocessing unit is used to filter three-dimensional point cloud data within a cube space of a preset side length as valid three-dimensional point cloud data, with the three-dimensional coordinate data of the fuselage as the center of the cube.
[0013] The point cloud data filtering unit determines the theoretical overlap area of the effective three-dimensional point cloud data of adjacent frames based on the effective three-dimensional point cloud data of adjacent frames and the three-dimensional coordinate data of the fuselage of adjacent frames.
[0014] In one embodiment, the obstacle recognition module includes an obstacle judgment unit and an obstacle avoidance triggering unit, wherein the obstacle judgment unit is connected to the obstacle avoidance triggering unit.
[0015] In one embodiment, the obstacle determination unit is used to determine whether the overlap of the theoretical overlapping areas of the effective three-dimensional point cloud data of adjacent frames is greater than a preset threshold. If so, it is determined that there is no obstacle; otherwise, it is determined that a suspected obstacle has appeared, and the coordinate area of the suspected obstacle is located.
[0016] The obstacle avoidance triggering unit is used to determine whether the coordinate area of the suspected obstacle overlaps with the unexecuted flight trajectory data. If there is an overlap, the suspected obstacle is determined to be an actual obstacle, and an obstacle avoidance alarm is issued.
[0017] In one embodiment, the obstacle avoidance optimization module includes a dynamic analysis unit and an obstacle avoidance processing unit, wherein the dynamic analysis unit is interfaced with the obstacle avoidance processing unit.
[0018] In one embodiment, the dynamic analysis unit is used to receive obstacle avoidance alarms and determine whether the coordinate regions of actual obstacles and suspected obstacles in consecutive frames are offset. If so, the actual obstacle is determined to be a dynamic obstacle, and the obstacle region of the dynamic obstacle is determined; otherwise, the actual obstacle is determined to be a static obstacle.
[0019] The obstacle avoidance processing unit is used to obtain the optimal obstacle avoidance route based on the obstacle area of dynamic obstacles or the coordinate area of static obstacles, combined with flight trajectory data, through an ant colony algorithm.
[0020] In one embodiment, the method of determining that an actual obstacle is a dynamic obstacle and determining the obstacle area of the dynamic obstacle includes:
[0021] The moving speed of the dynamic obstacle is determined based on the acquisition interval of consecutive frames and the changes in the coordinates of the dynamic obstacle.
[0022] The collision time between the drone and the dynamic obstacle is determined based on the current coordinates and moving speed of the dynamic obstacle.
[0023] A spherical obstacle avoidance zone is constructed with the current coordinates of the dynamic obstacle as the center and the product of the movement speed and the collision time as the radius, serving as the obstacle area for the dynamic obstacle.
[0024] Compared with the prior art, the advantages of this application are:
[0025] (1) By using the UAV body as the center and selecting effective three-dimensional point cloud data through a cube space frame, the near-distance obstacle avoidance perception range is limited. At the same time, the theoretical overlapping area of adjacent frame point clouds is determined by combining the changes in the three-dimensional coordinate data of the UAV body. This enables the comparison of differences within a unified motion reference area, filters out the interference of point cloud offset caused by the UAV's own flight displacement, and effectively improves the stability and accuracy of obstacle recognition.
[0026] (2) By distinguishing between static and dynamic obstacles through the change of point cloud coordinates in multiple consecutive frames, static obstacles outside the path are not avoided ineffectively, reducing unnecessary trajectory adjustments and ensuring flight efficiency. For dynamic obstacles with collision risk, a spherical dynamic obstacle avoidance zone is constructed with the obstacle as the center and the product of speed and time as the radius, based on the moving speed of the dynamic obstacle and the collision time of the UAV. The obstacle avoidance range can be adaptively adjusted according to the movement state of the dynamic obstacle to achieve predictive active obstacle avoidance. Attached Figure Description
[0027] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0028] Figure 1 This is a system architecture block diagram of the autonomous flight unmanned aerial vehicle control system in the embodiments of this application. Detailed Implementation
[0029] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0030] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.
[0031] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.
[0032] This application provides an autonomous flight unmanned aerial vehicle (UAV) control system, referring to... Figure 1 The system includes a flight trajectory generation module, a data acquisition module, an obstacle recognition module, and an obstacle avoidance optimization module. The flight trajectory generation module interfaces with the data acquisition module, the data acquisition module interfaces with the obstacle recognition module, and the obstacle recognition module interfaces with the obstacle avoidance optimization module. Specifically:
[0033] The flight trajectory generation module is used to: obtain flight trajectory data (waypoint coordinate sequence, flight speed, flight altitude, heading angle) based on pre-stored flight mission coordinate parameters (take-off point, target point);
[0034] The data acquisition module is used to: collect three-dimensional point cloud data of the environment and three-dimensional coordinate data of the fuselage during the flight mission performed by the UAV based on the flight trajectory data;
[0035] The obstacle recognition module is used to determine whether there is an actual obstacle based on flight trajectory data, 3D point cloud data and fuselage 3D coordinate data, and to issue an obstacle avoidance alarm.
[0036] The obstacle avoidance optimization module is used to adjust flight trajectory data based on obstacle avoidance alarms.
[0037] In one embodiment, the data acquisition module includes a multi-source data acquisition unit, a data preprocessing unit, and a point cloud data filtering unit. The multi-source data acquisition unit interfaces with the data preprocessing unit, and the data preprocessing unit interfaces with the point cloud data filtering unit. The multi-source data acquisition unit is used to acquire 3D point cloud data and fuselage 3D coordinate data. The data preprocessing unit is used to filter 3D point cloud data within a cube space of a preset side length, centered on the fuselage 3D coordinate data, as valid 3D point cloud data. The point cloud data filtering unit determines the theoretical overlap area of valid 3D point cloud data in adjacent frames based on the valid 3D point cloud data and the fuselage 3D coordinate data of adjacent frames.
[0038] By using the drone body as the center and selecting effective 3D point cloud data through a cube-shaped spatial frame, the near-range obstacle avoidance perception range is limited. At the same time, by combining the changes in the drone's 3D coordinate data, the theoretical overlapping area of point clouds in adjacent frames is determined. This enables difference comparison within a unified motion reference area, filtering out point cloud offset interference caused by the drone's own flight displacement, and effectively improving the stability and accuracy of obstacle recognition.
[0039] In one embodiment, the obstacle recognition module includes an obstacle judgment unit and an obstacle avoidance triggering unit, with the obstacle judgment unit and the obstacle avoidance triggering unit interfacing. The obstacle judgment unit is used to determine whether the overlap of the theoretically overlapping regions of effective 3D point cloud data in adjacent frames is greater than a preset threshold. If so, it determines that there is no obstacle; otherwise, it determines that a suspected obstacle has appeared and locates the coordinates of the suspected obstacle.
[0040] The obstacle avoidance triggering unit is used to determine whether the coordinate area of a suspected obstacle overlaps with the unexecuted flight trajectory data. If there is an overlap, the suspected obstacle is determined to be an actual obstacle, and an obstacle avoidance alarm is issued.
[0041] In one embodiment, the obstacle avoidance optimization module includes a dynamic analysis unit and an obstacle avoidance processing unit, with the dynamic analysis unit interfaced with the obstacle avoidance processing unit. The dynamic analysis unit receives obstacle avoidance alarms and determines whether the coordinate regions of actual obstacles and suspected obstacles in consecutive frames have shifted. If so, it determines that the actual obstacle is a dynamic obstacle and identifies the obstacle region of the dynamic obstacle; otherwise, it determines that the actual obstacle is a static obstacle.
[0042] This method distinguishes between static and dynamic obstacles by analyzing the changes in point cloud coordinates across multiple consecutive frames. It avoids unnecessary avoidance of static obstacles outside the path, reducing redundant trajectory adjustments and ensuring flight efficiency.
[0043] The methods for determining the obstacle area of dynamic obstacles mentioned above include:
[0044] The moving speed of the dynamic obstacle is determined based on the acquisition interval of consecutive frames and the changes in the coordinates of the dynamic obstacle.
[0045] Based on the current coordinates and moving speed of the dynamic obstacle, determine the collision time between the drone and the dynamic obstacle (in conjunction with the drone's flight speed).
[0046] Using the current coordinates of the dynamic obstacle as its center and the product of its movement speed and collision time as its radius, a spherical obstacle avoidance zone is constructed to serve as the obstacle area for the dynamic obstacle. This allows the obstacle avoidance range to be adaptively adjusted according to the movement state of the dynamic obstacle, achieving predictive active obstacle avoidance.
[0047] The obstacle avoidance processing unit is used to obtain the optimal obstacle avoidance route based on the obstacle area of dynamic obstacles or the coordinate area of static obstacles, combined with flight trajectory data, through an ant colony algorithm.
[0048] The following describes the steps for using the autonomous flight drone control system, including:
[0049] S1. Obtain flight trajectory data based on the coordinates of the take-off point and target point of the UAV flight mission;
[0050] S2. During the flight mission performed by the UAV according to the flight trajectory data, three-dimensional point cloud data of the environment and three-dimensional coordinate data of the fuselage are collected (collection frequency 100Hz).
[0051] S3. Using the fuselage's three-dimensional coordinate data as the center of a cube, select the three-dimensional point cloud data within a cube space of a preset side length (e.g., 20m) as valid three-dimensional point cloud data.
[0052] S4. Based on the effective 3D point cloud data of adjacent frames and the fuselage 3D coordinate data of adjacent frames, determine the theoretical overlapping area of the effective 3D point cloud data of adjacent frames.
[0053] S5. Determine whether the overlap of the theoretical overlapping areas of the effective 3D point cloud data in adjacent frames is greater than a preset threshold (≥98%). If yes, determine that there are no obstacles; otherwise, proceed to S6.
[0054] S6. Determine if a suspected obstacle has appeared and locate the coordinates of the suspected obstacle area;
[0055] S7. Determine whether the coordinates of the suspected obstacle overlap with the unexecuted flight trajectory data. If yes, proceed to S8; otherwise, proceed to S9.
[0056] S8. If the suspected obstacle is confirmed to be an actual obstacle, an obstacle avoidance alarm is issued.
[0057] S9. Determine whether the coordinate region of the actual obstacle in the continuous frames has shifted. If yes, go to S10; otherwise, go to S11.
[0058] In parallel, it determines whether the coordinate region of a suspected obstacle in consecutive frames has shifted. If so, it proceeds to S10; otherwise, it determines that the suspected obstacle is a static obstacle. Since it does not coincide with the flight trajectory data, the static obstacle is ignored.
[0059] S10. Identify the obstacle as a dynamic obstacle. Determine the moving speed of the dynamic obstacle based on the acquisition interval of consecutive frames and the changes in the coordinates of the dynamic obstacle. Determine the collision time between the UAV and the dynamic obstacle based on the current coordinates and moving speed of the dynamic obstacle. Construct a spherical obstacle avoidance zone with the current coordinates of the dynamic obstacle as the center and the product of the moving speed and the collision time as the radius, which serves as the obstacle area of the dynamic obstacle.
[0060] Based on the obstacle area and flight trajectory data of dynamic obstacles, the optimal obstacle avoidance route is obtained through ant colony algorithm;
[0061] S11. Determine that the actual obstacle is a static obstacle. Based on the coordinate area and flight trajectory data of the static obstacle, obtain the optimal obstacle avoidance route through the ant colony algorithm.
[0062] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.
[0063] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.
[0064] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.
[0065] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.
[0066] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.
[0067] The above are merely specific embodiments of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the scope of the claims.
Claims
1. An autonomous flight unmanned aerial vehicle (UAV) control system, characterized in that, include: The flight trajectory generation module is used to: obtain flight trajectory data based on pre-stored flight mission coordinate parameters; The data acquisition module is used to: collect three-dimensional point cloud data of the environment and three-dimensional coordinate data of the fuselage during the flight mission performed by the UAV based on the flight trajectory data; The obstacle recognition module is used to determine whether there is an actual obstacle based on flight trajectory data, 3D point cloud data and fuselage 3D coordinate data, and to issue an obstacle avoidance alarm. The obstacle avoidance optimization module is used to adjust flight trajectory data based on obstacle avoidance alarms.
2. The autonomous flight unmanned aerial vehicle control system according to claim 1, characterized in that, The data acquisition module includes a multi-source data acquisition unit, a data preprocessing unit, and a point cloud data filtering unit. The multi-source data acquisition unit is connected to the data preprocessing unit, and the data preprocessing unit is connected to the point cloud data filtering unit.
3. The autonomous flight unmanned aerial vehicle control system according to claim 2, characterized in that, The multi-source data acquisition unit is used to acquire three-dimensional point cloud data and fuselage three-dimensional coordinate data; The data preprocessing unit is used to filter three-dimensional point cloud data within a cube space of a preset side length as valid three-dimensional point cloud data, with the three-dimensional coordinate data of the fuselage as the center of the cube. The point cloud data filtering unit determines the theoretical overlap area of the effective three-dimensional point cloud data of adjacent frames based on the effective three-dimensional point cloud data of adjacent frames and the three-dimensional coordinate data of the fuselage of adjacent frames.
4. The autonomous flight unmanned aerial vehicle control system according to claim 3, characterized in that, The obstacle recognition module includes an obstacle judgment unit and an obstacle avoidance triggering unit, and the obstacle judgment unit is connected to the obstacle avoidance triggering unit.
5. The autonomous flight unmanned aerial vehicle control system according to claim 4, characterized in that, The obstacle determination unit is used to determine whether the overlap of the theoretical overlapping areas of the effective three-dimensional point cloud data of adjacent frames is greater than a preset threshold. If so, it is determined that there is no obstacle; otherwise, it is determined that a suspected obstacle has appeared and the coordinate area of the suspected obstacle is located. The obstacle avoidance triggering unit is used to determine whether the coordinate area of the suspected obstacle overlaps with the unexecuted flight trajectory data. If there is an overlap, the suspected obstacle is determined to be an actual obstacle, and an obstacle avoidance alarm is issued.
6. The autonomous flight unmanned aerial vehicle control system according to claim 5, characterized in that, The obstacle avoidance optimization module includes a dynamic analysis unit and an obstacle avoidance processing unit, and the dynamic analysis unit is connected to the obstacle avoidance processing unit.
7. The autonomous flight unmanned aerial vehicle control system according to claim 6, characterized in that, The dynamic analysis unit is used to receive obstacle avoidance alarms and determine whether the coordinate regions of actual obstacles and suspected obstacles in consecutive frames are offset. If so, the actual obstacle is determined to be a dynamic obstacle, and the obstacle region of the dynamic obstacle is determined; otherwise, the actual obstacle is determined to be a static obstacle. The obstacle avoidance processing unit is used to obtain the optimal obstacle avoidance route based on the obstacle area of dynamic obstacles or the coordinate area of static obstacles, combined with flight trajectory data, through an ant colony algorithm.
8. The autonomous flight unmanned aerial vehicle control system according to claim 7, characterized in that, The methods for determining whether an actual obstacle is a dynamic obstacle and for identifying the obstacle area of a dynamic obstacle include: The moving speed of the dynamic obstacle is determined based on the acquisition interval of consecutive frames and the changes in the coordinates of the dynamic obstacle. The collision time between the drone and the dynamic obstacle is determined based on the current coordinates and moving speed of the dynamic obstacle. A spherical obstacle avoidance zone is constructed with the current coordinates of the dynamic obstacle as the center and the product of the movement speed and the collision time as the radius, serving as the obstacle area for the dynamic obstacle.