Methods, devices, equipment and media for obstacle avoidance control of unmanned aerial vehicles (UAVs) facing linear obstacles.

Abstract

This invention relates to the field of intelligent control technology for unmanned aerial vehicles (UAVs), providing a method, apparatus, device, and medium for UAV obstacle avoidance control targeting linear obstacles. It can construct a spatial representation of each linear obstacle's line segments to accurately quantify the three-dimensional position and shortest distance of the linear obstacle; perform local smoothing processing on the spatial representation of each linear obstacle's line segments to suppress noise and ensure continuous and smooth geometric features; calculate the dynamic safe distance and obstacle risk score corresponding to each linear target based on the influence mechanism of the linear obstacle's geometric structure characteristics, enabling accurate quantification of safe distance and risk from multiple dimensions; detect whether obstacle avoidance conditions are met based on the dynamic safe distance and obstacle risk score corresponding to each linear target, with a multi-trigger mechanism effectively avoiding false triggers; and control the target UAV along the obstacle avoidance path to effectively avoid the current linear target according to the obstacle avoidance control law, ensuring stable UAV flight.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology for unmanned aerial vehicles (UAVs), and in particular to a method, apparatus, device, and medium for UAV obstacle avoidance control for linear obstacles. Background Technology

[0002] Currently, the following solutions are mainly used for obstacle avoidance by drones: (1) Fixed Threshold Based Avoidance: Set a fixed distance (e.g., 1.5m). If the distance to the obstacle is less than the set distance, decelerate or fly around it.

[0003] (2) Real-time obstacle avoidance based on lidar or depth camera: Real-time distance measurement is performed using LiDAR (Light Detection and Range) or ToF (Time of Flight) depth camera, and obstacle avoidance is performed based on the distance. The action logic is still based on a fixed threshold, such as obstacle avoidance if the distance is <2m.

[0004] (3) Simple weighting method based on risk score: Some systems simply weight features such as distance, relative speed, and angle to generate risk scores, and avoid obstacles if the scores exceed a set threshold.

[0005] (4) Limited support for linear obstacles: Some systems can identify obstacles such as large poles and walls, but for thin linear obstacles with a diameter of only 5–25 mm, the obstacle avoidance sensor generally cannot effectively detect them, so a conservative large safety distance is generally adopted.

[0006] It is evident that existing solutions generally employ static rules or simple distance threshold strategies, failing to optimize for the geometric and risk characteristics of linear obstacles. Small linear obstacles (such as power lines) remain among the most dangerous yet difficult-to-detect obstacles in UAV flight. In other words, the current solutions primarily suffer from the following shortcomings: (1) Fixed safety distance cannot adapt to different speeds and directions: When the drone flies at high speed, the braking distance becomes larger, and the fixed safety distance cannot guarantee safety; when the drone flies at low speed, the fixed distance is too conservative, which will lead to excessive obstacle avoidance and low efficiency.

[0007] (2) External factors such as wind disturbance and attitude change are not included in the model: Linear obstacles are often located in open areas with large wind disturbance, which may cause the UAV to deviate instantaneously, but the fixed threshold cannot dynamically adjust the safe distance.

[0008] (3) Linear obstacles are high-risk targets with extremely small cross-sections: for example, wires with a diameter of only 5–25 mm have very weak echoes from depth cameras and lidar, and even a deviation of 10 cm can lead to wire entanglement accidents. Existing obstacle avoidance strategies all assume that the obstacle is a planar or voluminous target, which is not applicable to thin lines.

[0009] (4) Lack of prediction models that incorporate the geometric characteristics of linear obstacles: Linear obstacles have characteristics such as long extension direction, small cross-section, wind vibration causing the line to sway, appearing as continuous thin lines in the image, large distance estimation noise, but extremely high danger. Existing technologies have not modeled these characteristics.

[0010] (5) Lack of adaptive obstacle avoidance control algorithm: Existing obstacle avoidance strategies cannot dynamically adjust the flight trajectory based on the speed, acceleration, direction change, wind disturbance, etc. of the UAV. Summary of the Invention

[0011] In view of the above, it is necessary to provide a method, device, equipment and medium for UAV obstacle avoidance control for linear obstacles, in order to solve the problem of being unable to accurately avoid linear obstacles during UAV flight.

[0012] A method for obstacle avoidance control of a drone facing linear obstacles, the method comprising: In response to the obstacle avoidance control commands of the target UAV to linear obstacles, construct a spatial representation of each linear obstacle in terms of line segments; For each linear obstacle, perform local smoothing on the line segment spatial representation to obtain multiple linear targets; The dynamic safety distance and risk score of each linear target are calculated based on the influence mechanism of the geometric structure characteristics of linear obstacles. The system checks whether obstacle avoidance conditions are met based on the dynamic safety distance and linear obstacle risk score corresponding to each linear target. For a current linear target that meets the obstacle avoidance conditions, an obstacle avoidance control law and an obstacle avoidance path are generated, and the target UAV is controlled to perform obstacle avoidance along the obstacle avoidance path according to the obstacle avoidance control law.

[0013] A drone obstacle avoidance control device for linear obstacles, the drone obstacle avoidance control device for linear obstacles comprising: The building unit is used to construct the spatial representation of each linear obstacle in response to the obstacle avoidance control command of the target UAV to the linear obstacle; A smoothing unit is used to perform local smoothing of the line segment spatial representation of each linear obstacle to obtain multiple linear targets; The calculation unit is used to calculate the dynamic safety distance and linear obstacle risk score for each linear target based on the influence mechanism of the geometric structure characteristics of linear obstacles; The detection unit is used to detect whether the obstacle avoidance conditions are met based on the dynamic safety distance and the risk score of the linear obstacle corresponding to each linear target. An execution unit is configured to generate an obstacle avoidance control law and an obstacle avoidance path for a current linear target that meets the obstacle avoidance conditions, and to control the target UAV to perform obstacle avoidance along the obstacle avoidance path according to the obstacle avoidance control law.

[0014] A computer device, the computer device comprising: A memory for storing at least one instruction; and a processor for executing the instructions stored in the memory to implement the UAV obstacle avoidance control method for linear obstacles.

[0015] A computer-readable storage medium storing at least one instruction, which is executed by a processor in a computer device to implement the UAV obstacle avoidance control method for linear obstacles.

[0016] As can be seen from the above technical solutions, this invention can construct a spatial representation of each linear obstacle segment to accurately quantify the three-dimensional position and shortest distance of the linear obstacle; perform local smoothing processing on the spatial representation of each linear obstacle segment to suppress noise and ensure the continuous smoothness of the geometric features of the segment; calculate the dynamic safe distance and linear obstacle risk score corresponding to each linear target based on the influence mechanism of the geometric structure characteristics of the linear obstacle, and accurately quantify the safe distance and risk from multiple dimensions; detect whether the obstacle avoidance conditions are met according to the dynamic safe distance and linear obstacle risk score corresponding to each linear target, and the multi-trigger mechanism can effectively avoid false triggering; control the target UAV to perform effective obstacle avoidance along the obstacle avoidance path according to the obstacle avoidance control law to ensure the flight stability of the UAV. Attached Figure Description

[0017] Figure 1 This is a flowchart of a preferred embodiment of the UAV obstacle avoidance control method for linear obstacles according to the present invention.

[0018] Figure 2 This is a functional block diagram of a preferred embodiment of the UAV obstacle avoidance control device for linear obstacles of the present invention.

[0019] Figure 3 This is a schematic diagram of the structure of a computer device that implements a preferred embodiment of the UAV obstacle avoidance control method for linear obstacles according to the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] like Figure 1 The diagram shown is a flowchart of a preferred embodiment of the UAV obstacle avoidance control method for linear obstacles according to the present invention. The order of the steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements.

[0022] The aforementioned UAV obstacle avoidance control method for linear obstacles is applied to one or more computer devices. The computer device is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0023] The computer device can be any electronic product that can interact with the user, such as a personal computer, tablet computer, smartphone, personal digital assistant (PDA), interactive network television (IPTV), smart wearable device, etc.

[0024] The computer equipment may also include network equipment and / or user equipment. The network equipment includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of hosts or network servers.

[0025] The server can be a standalone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0026] Artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0027] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0028] The network in which the computer device is located includes, but is not limited to, the Internet, wide area network, metropolitan area network, local area network, and virtual private network (VPN).

[0029] S10, in response to the obstacle avoidance control command of the target UAV to the linear obstacle, constructs a spatial representation of the line segment of each linear obstacle.

[0030] In this embodiment, the target drone can be used to perform tasks such as automatic inspection, power line inspection, wind turbine cable inspection, industrial plant patrol, and bridge cable inspection.

[0031] In this embodiment, the obstacle avoidance control command can be automatically triggered when the target UAV begins to perform its mission.

[0032] In this embodiment, the spatial representation of each linear obstacle as a line segment includes: For each linear obstacle, obtain the first endpoint and the second endpoint of the linear obstacle; The difference between the coordinate vectors of the first endpoint and the second endpoint is normalized to obtain the unit direction vector; Calculate the projection parameters of the target UAV relative to the first endpoint on the unit direction vector; Obtain the length of the line segment of the linear obstacle; When the projection parameter is less than 0, the distance from the target drone to the first endpoint is calculated as the shortest spatial distance from the target drone to the linear obstacle; when the projection parameter is greater than the line segment length, the distance from the target drone to the second endpoint is calculated as the shortest spatial distance; when the projection parameter is greater than or equal to 0 and less than or equal to the line segment length, the vertical distance from the target drone to the linear obstacle is calculated as the shortest spatial distance. The linear obstacle is represented by a line segment space using the three-dimensional coordinates of the first endpoint, the three-dimensional coordinates of the second endpoint, the unit direction vector, and the shortest spatial distance as parameters.

[0033] For example: when the first endpoint is P0, the second endpoint is P1, and the target UAV's position is P, the unit direction vector... =Normalize(P1-P0); Projection parameter t=dot(P-P0, ); Line segment length L = ||P1 - P0||.

[0034] When t < 0, it means the projection point is outside line segment P0P1 and closer to the P0 side, then the shortest spatial distance is... =||P-P0||; When t>L, it means the projection point is outside line segment P0P1 and closer to the P1 side, then the shortest spatial distance is... =||P-P1||; When 0 ≤ t ≤ L, it means the projection point is inside line segment P0P1, and the shortest spatial distance is... =||(P-P0)-t· ||.

[0035] The line segment space is then represented as {P0, P1, ...} , }

[0036] In this embodiment, obtaining the first endpoint and the second endpoint of the linear obstacle includes: When the linear obstacle includes parameters of a three-dimensional reconstruction curve, the endpoint with the smaller parameter value is obtained from the two endpoints of the linear obstacle as the first endpoint, and the other endpoint is obtained as the second endpoint; When the linear obstacle does not include the parameters of the three-dimensional reconstruction curve, the endpoint with the smaller projected coordinate in the main direction of the line segment corresponding to the linear obstacle is obtained from the two endpoints of the linear obstacle as the first endpoint, and the other endpoint is obtained as the second endpoint.

[0037] The above embodiments enable precise quantification of the three-dimensional position and shortest distance of linear obstacles, providing a geometric basis for subsequent detection and adapting to the detection of thin line targets.

[0038] S11, perform local smoothing on the line segment spatial representation of each linear obstacle to obtain multiple linear targets.

[0039] In this embodiment, since there may be noise interference in the linear target, it is necessary to perform local smoothing processing on the spatial representation of each linear obstacle segment first.

[0040] Specifically, the line segment spatial representation of each linear obstacle undergoes local smoothing processing to obtain multiple linear targets, including: Identify valid line segments in the linear obstacle, and multiple candidate line segments belonging to the same connected line segment; The multiple candidate line segments are fitted according to a preset sliding window to obtain at least one fitted line segment; From the effective line segments and the fitted line segments, obtain the line segments whose length is greater than the first threshold, and / or whose number of points is greater than the second threshold, and / or whose noise level is greater than the third threshold, and use them as the line segments to be processed; The line segment to be processed is locally fitted into a curve; The curve increments are replaced with the line segment spatial representation of each linear obstacle to obtain the plurality of linear targets.

[0041] Among them, local B-spline algorithms and polynomial fitting algorithms can be used to smooth the reconstructed points or adjacent line segments of the same linear target, thereby performing local geometric correction and noise reduction on the line segment spatial representation of each linear obstacle, which can make the direction and distance calculations smoother.

[0042] In the above embodiments, local smoothing is enabled when the line segment length, number of points, or noise level exceeds the threshold. Short line segments or high-confidence straight line segments can be directly represented using the original line segment space, which can ensure that the line segment direction is smooth and not affected by noise.

[0043] S12, calculate the dynamic safety distance and linear obstacle risk score for each linear target based on the influence mechanism of the geometric structure characteristics of linear obstacles.

[0044] Unlike traditional methods that use a fixed safety distance, this embodiment calculates a dynamic safety distance based on the geometric characteristics of linear obstacles for the first time. Furthermore, unlike traditional methods that rely solely on distance to assess risk, this embodiment models the direction of the linear target as a physical quantity for obstacle avoidance for the first time.

[0045] Specifically, the calculation of the dynamic safety distance and linear obstacle risk score for each linear target based on the influence mechanism of the geometric structure characteristics of linear obstacles includes: For each linear target, obtain the basic safe distance, the current flight speed of the target UAV, the current wind disturbance, the current depth estimation noise, and the current angle between the motion direction of the target UAV and the line segment direction of the linear target; Calculate the absolute value of the sine of the current included angle; The safe offset distance is obtained by weighting the current flight speed, the current wind disturbance, the current depth estimation noise, and the absolute value according to the adjustment coefficient matrix. The dynamic safety distance is obtained by calculating the sum of the basic safety distance and the safety offset distance; Calculate the reciprocal of the shortest spatial distance corresponding to the linear target to obtain the first value; The current flight speed and the current wind disturbance are weighted and calculated according to the weighting coefficient matrix to obtain the second value; Calculate the sum of the second value and 1 to obtain the third value; Obtain the visual confidence level of the linear target, and calculate the product of the visual confidence level, the first value, and the third value to obtain the risk score of the linear obstacle.

[0046] The modeling result of the dynamic safety distance can be expressed as follows: ; in, Indicates dynamic safety distance; V represents the basic safety distance, ranging from 1.0 to 1.5 m; V represents the current flight speed of the target UAV, in m / s; W represents the current wind disturbance, which can be calculated based on the peak lateral acceleration of the IMU (Inertial Measurement Unit). This indicates the noise in the current depth estimate, which can come from SLAM (Simultaneous Localization and Mapping) or visual depth stability. This represents the current angle between the direction of motion of the target UAV and the direction of the line segment of the linear target; k1, k2, k3, and k4 represent adjustment coefficients, which can be the optimal values ​​obtained after a large number of experiments or training, or they can be obtained through dataset fitting or field experiment calibration. For example, the value range of k1 is 0.2–0.5, the value range of k2 is 0.1–0.3, the value range of k3 is 0.05–0.2, and the value range of k4 is 0.3–0.7.

[0047] The modeling results of the dynamic safety distance show that the higher the UAV's flight speed, the greater the lead time required for control, thus necessitating a larger safety distance; the greater the wind disturbance, the greater the possibility of yaw, thus requiring an increased safety distance; high depth noise makes position estimation unreliable, requiring an increased safety distance; the UAV's flight direction is perpendicular to the line (…). The risk is greatest when the angle is approximately 90°. ≈1, the safe distance is the maximum.

[0048] Furthermore, compared to traditional solutions, this embodiment proposes... The significance lies in: when the drone's flight direction is perpendicular to the line, ≈90°, the risk is highest, and a greater safety distance is needed; when the drone flies along the line, ≈0°, the risk is lowest, and the safety distance needs to be increased.

[0049] The modeling results of the above dynamic safety distance are a modeling method that can explain "why the risks are different under the same distance conditions".

[0050] The modeling results of the linear obstacle risk score can be expressed as follows: ; in, Indicates the risk score for linear obstacles. The larger the value, the higher the risk; C represents the visual confidence level of the linear target, with a value range of (0–1); λ1 and λ2 represent the weighting coefficients.

[0051] The modeling results of the linear obstacle risk score show that, This indicates that the closer the distance, the greater the risk; visual confidence can prevent noise from being mistaken for an obstacle; speed is a factor indicating that at the same distance, high speed is more dangerous; and wind is a factor indicating that the stronger the wind, the more likely the vehicle is to deviate from the finish line.

[0052] The modeling results of the linear obstacle risk score mentioned above solve the problem that traditional risk assessment models only apply to planar or volumetric obstacles.

[0053] In the above embodiments, the geometric characteristics of linear obstacles are introduced for the first time as the basis for dynamic prediction of safe distance. The safe distance is driven by the geometric properties of the linear target and the state of the UAV itself, which is a method not used in the industry. Furthermore, a dynamic risk score is constructed for linear obstacles for the first time, integrating multiple factors such as confidence level, distance, speed, and wind disturbance, which can accurately identify high-risk scenarios and reduce false triggering.

[0054] S13, based on the dynamic safety distance and linear obstacle risk score corresponding to each linear target, detect whether the obstacle avoidance conditions are met.

[0055] In this embodiment, the step of detecting whether the obstacle avoidance conditions are met based on the dynamic safety distance and linear obstacle risk score corresponding to each linear target includes: For each linear target, the first condition is that the risk score of the linear obstacle is greater than a preset score threshold. The second condition is that the shortest spatial distance corresponding to the linear target is less than the dynamic safety distance. The third condition is that the shortest spatial distance corresponding to the linear target within the preset time window changes to be less than the dynamic safety distance within the preset time period. When any one of the first condition, the second condition, or the third condition is met, it is determined that the obstacle avoidance condition is satisfied.

[0056] For example, the preset score threshold can be configured to be 0.7–0.9.

[0057] Among them, the first condition enables risk warning, the second condition enables hard security boundary, and the third condition enables comprehensive risk prediction in advance.

[0058] When the first condition and the second condition are triggered simultaneously, it is considered a higher risk level, and obstacle avoidance should be triggered immediately, with the obstacle avoidance acceleration increased or the offset distance increased.

[0059] The above embodiments enable a multi-trigger mechanism that balances early warning and hardware security, avoiding missed or delayed triggering.

[0060] S14. For a current linear target that meets the obstacle avoidance conditions, generate an obstacle avoidance control law and an obstacle avoidance path, and control the target UAV to perform obstacle avoidance along the obstacle avoidance path according to the obstacle avoidance control law.

[0061] In this embodiment, the generation of the obstacle avoidance control law and obstacle avoidance path includes: Calculate the cross product of the unit direction vector corresponding to the current linear target and the vertical direction of the world coordinate system, and normalize the cross product to obtain the obstacle avoidance direction; Calculate the difference between the dynamic safe distance and the shortest spatial distance corresponding to the current linear target to obtain the current distance difference; The obstacle avoidance control law is obtained by calculating the product of the control gain, the current distance difference, and the obstacle avoidance direction; Calculate the product of the offset coefficient and the obstacle avoidance direction to obtain the three-dimensional offset vector; Obtain the current coordinates of the target UAV's current position, and calculate the sum of the current coordinates and the three-dimensional offset vector to obtain the coordinates of the intermediate point; Based on the original flight path of the target UAV, select the recovery point on the original flight path after obstacle avoidance is completed; The current position is determined as the starting point, the intermediate coordinate point is determined as the intermediate point, and the recovery point is determined as the ending point. A smooth trajectory is generated using a cubic spline algorithm to obtain the obstacle avoidance path.

[0062] The obstacle avoidance direction can be represented as follows: ; Where n represents the obstacle avoidance direction; Indicates the vertical direction of the world coordinate system.

[0063] Because linear obstacles extend long and have small cross-sections, the safest way to avoid them is to be perpendicular to the line and deviate laterally by 0.5–1.5m to bypass linear obstacles such as power lines.

[0064] The obstacle avoidance control law can be expressed as follows: ; in, This represents the obstacle avoidance control law, i.e., obstacle avoidance acceleration; This represents the control gain, and its value can range from 0.4 to 1.2.

[0065] when much smaller At that time, the acceleration increases in order to quickly escape the danger zone.

[0066] The offset coefficient can range from 0.5 to 1.2 m.

[0067] The process involves using the starting point, intermediate point, and ending point as cubic spline control points. Combined with boundary constraints such as the current velocity direction at the starting point and the resumed flight path direction or zero lateral velocity at the ending point, cubic spline coefficients are calculated for the x(t), y(t), and z(t) coordinates to obtain a trajectory with continuous velocity and smooth acceleration. After generation, a safety distance check is required. If the generated trajectory intersects with a linear obstacle safety corridor, the offset coefficient can be increased or the intermediate point adjusted to regenerate the trajectory.

[0068] The value range of all parameters involved in this embodiment can be dynamically adjusted according to the actual scenario.

[0069] Unlike traditional drone obstacle avoidance methods that often involve direct backward movement, lateral movement in a fixed direction, or global path replanning, this embodiment considers that the line has only one dangerous direction (i.e., the vertical direction). It utilizes the physical structure of the line to reduce the complexity of path planning, automatically adjusts the obstacle avoidance amplitude according to the current state, and matches the obstacle avoidance direction with the geometric structure of the linear obstacle. This is safer, more natural, and more efficient, ensuring that the obstacle avoidance path will not intersect with the line, which can significantly reduce the risk of line entanglement accidents.

[0070] The algorithm in this embodiment is lightweight and can run in real time on the onboard computing unit of the UAV.

[0071] As can be seen from the above technical solutions, this invention can construct a spatial representation of each linear obstacle segment to accurately quantify the three-dimensional position and shortest distance of the linear obstacle; perform local smoothing processing on the spatial representation of each linear obstacle segment to suppress noise and ensure the continuous smoothness of the geometric features of the segment; calculate the dynamic safe distance and linear obstacle risk score corresponding to each linear target based on the influence mechanism of the geometric structure characteristics of the linear obstacle, and accurately quantify the safe distance and risk from multiple dimensions; detect whether the obstacle avoidance conditions are met according to the dynamic safe distance and linear obstacle risk score corresponding to each linear target, and the multi-trigger mechanism can effectively avoid false triggering; control the target UAV to perform effective obstacle avoidance along the obstacle avoidance path according to the obstacle avoidance control law to ensure the flight stability of the UAV.

[0072] like Figure 2The diagram shown is a functional block diagram of a preferred embodiment of the UAV obstacle avoidance control device for linear obstacles according to the present invention. The UAV obstacle avoidance control device 11 for linear obstacles includes a construction unit 110, a smoothing unit 111, a calculation unit 112, a detection unit 113, and an execution unit 114. The module / unit referred to in this invention refers to a series of computer program segments that can be executed by a processor and perform a fixed function, and are stored in memory. In this embodiment, the functions of each module / unit will be described in detail in subsequent embodiments.

[0073] The construction unit 110 is used to construct a spatial representation of each linear obstacle in response to the obstacle avoidance control command of the target UAV to the linear obstacle; The smoothing unit 111 is used to perform local smoothing processing on the line segment spatial representation of each linear obstacle to obtain multiple linear targets; The calculation unit 112 is used to calculate the dynamic safety distance and linear obstacle risk score corresponding to each linear target based on the influence mechanism of the geometric structure characteristics of linear obstacles; The detection unit 113 is used to detect whether the obstacle avoidance conditions are met based on the dynamic safety distance and the risk score of the linear obstacle corresponding to each linear target. The execution unit 114 is used to generate an obstacle avoidance control law and an obstacle avoidance path for a current linear target that meets the obstacle avoidance conditions, and to control the target UAV to perform obstacle avoidance along the obstacle avoidance path according to the obstacle avoidance control law.

[0074] As can be seen from the above technical solutions, this invention can construct a spatial representation of each linear obstacle segment to accurately quantify the three-dimensional position and shortest distance of the linear obstacle; perform local smoothing processing on the spatial representation of each linear obstacle segment to suppress noise and ensure the continuous smoothness of the geometric features of the segment; calculate the dynamic safe distance and linear obstacle risk score corresponding to each linear target based on the influence mechanism of the geometric structure characteristics of the linear obstacle, and accurately quantify the safe distance and risk from multiple dimensions; detect whether the obstacle avoidance conditions are met according to the dynamic safe distance and linear obstacle risk score corresponding to each linear target, and the multi-trigger mechanism can effectively avoid false triggering; control the target UAV to perform effective obstacle avoidance along the obstacle avoidance path according to the obstacle avoidance control law to ensure the flight stability of the UAV.

[0075] like Figure 3 The diagram shown is a schematic representation of the computer device used in a preferred embodiment of the UAV obstacle avoidance control method for linear obstacles according to the present invention.

[0076] The computer device 1 may include a memory 12, a processor 13, and a bus (the arrow in the figure represents the bus), and may also include a computer program stored in the memory 12 and executable on the processor 13, such as a drone obstacle avoidance control program for linear obstacles.

[0077] Those skilled in the art will understand that the schematic diagram is merely an example of computer device 1 and does not constitute a limitation on computer device 1. Computer device 1 can be either a bus topology or a star topology. Computer device 1 may also include more or fewer other hardware or software than shown in the diagram, or different component arrangements. For example, computer device 1 may also include input / output devices, network access devices, etc.

[0078] It should be noted that the computer device 1 described is merely an example. Other existing or future electronic products that are adaptable to this invention should also be included within the scope of protection of this invention and are incorporated herein by reference.

[0079] The memory 12 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 12 can be an internal storage unit of the computer device 1, such as a portable hard drive of the computer device 1. In other embodiments, the memory 12 can be an external storage device of the computer device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the computer device 1. Furthermore, the memory 12 can include both internal and external storage units of the computer device 1. The memory 12 can be used not only to store application software and various types of data installed on the computer device 1, such as code for an obstacle avoidance control program for a drone facing linear obstacles, but also to temporarily store data that has been output or will be output.

[0080] In some embodiments, the processor 13 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits packaged with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 13 is the control unit of the computer device 1, connecting various components of the computer device 1 via various interfaces and lines. It executes programs or modules stored in the memory 12 (e.g., executing a drone obstacle avoidance control program for linear obstacles) and calls data stored in the memory 12 to perform various functions of the computer device 1 and process data.

[0081] The processor 13 executes the operating system of the computer device 1 and various installed applications. The processor 13 executes these applications to implement the steps in the various embodiments of the UAV obstacle avoidance control method for linear obstacles described above, for example... Figure 1 The steps are shown.

[0082] For example, the computer program may be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 13 to complete the present invention. The one or more modules / units may be a series of computer-readable instruction segments capable of performing a specific function, which describe the execution process of the computer program in the computer device 1. For example, the computer program may be divided into a construction unit 110, a smoothing unit 111, a calculation unit 112, a detection unit 113, and an execution unit 114.

[0083] The integrated unit implemented as a software functional module described above can be stored in a computer-readable storage medium. This software functional module, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, computer equipment, or network device, etc.) or processor to execute portions of the UAV obstacle avoidance control method for linear obstacles described in various embodiments of the present invention.

[0084] If the modules / units integrated in the computer device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware devices. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above.

[0085] The computer program includes computer program code, which may be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory, etc.

[0086] Furthermore, the computer-readable storage medium may primarily include a stored program area and a stored data area, wherein the stored program area may store the operating system, an application program required for at least one function, etc.; and the stored data area may store data created based on the use of blockchain nodes, etc.

[0087] The blockchain referred to in this invention is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0088] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, in... Figure 3 The bus is represented by only one straight line, but this does not mean that there is only one bus or one type of bus. The bus is configured to enable communication between the memory 12 and at least one processor 13, etc.

[0089] Although not shown, the computer device 1 may also include a power supply (such as a battery) to power various components. Preferably, the power supply can be logically connected to the at least one processor 13 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The computer device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0090] Furthermore, the computer device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the computer device 1 and other computer devices.

[0091] Optionally, the computer device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the computer device 1 and to display a visual user interface.

[0092] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0093] It will be understood by those skilled in the art that Figure 3 The structure shown does not constitute a limitation on the computer device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0094] Combination Figure 1 The memory 12 in the computer device 1 stores multiple instructions to implement a drone obstacle avoidance control method for linear obstacles, and the processor 13 can execute the multiple instructions to achieve the following: In response to the obstacle avoidance control commands of the target UAV to linear obstacles, construct a spatial representation of each linear obstacle in terms of line segments; For each linear obstacle, perform local smoothing on the line segment spatial representation to obtain multiple linear targets; The dynamic safety distance and risk score of each linear target are calculated based on the influence mechanism of the geometric structure characteristics of linear obstacles. The system checks whether obstacle avoidance conditions are met based on the dynamic safety distance and linear obstacle risk score corresponding to each linear target. For a current linear target that meets the obstacle avoidance conditions, an obstacle avoidance control law and an obstacle avoidance path are generated, and the target UAV is controlled to perform obstacle avoidance along the obstacle avoidance path according to the obstacle avoidance control law.

[0095] Specifically, the processor 13's implementation method for the above instructions can be found in [reference needed]. Figure 1 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0096] It should be noted that all the data involved in this case was legally obtained.

[0097] If any AI models, software tools, or components not belonging to this company appear in the embodiments of this invention, they are merely illustrative examples and do not represent actual use. All user personal information involved in the embodiments of this invention has been obtained by an entity authorized (with the knowledge and consent) or fully authorized by all parties through various legal and compliant means. The collection, storage, use, processing, transmission, provision, and disclosure of the information, data, and signals involved all comply with relevant laws and regulations and do not violate public order and good morals.

[0098] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0099] This invention can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This invention can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This invention can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0100] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0101] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0102] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0103] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0104] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices described in this invention can also be implemented by a single unit or device through software or hardware. Terms such as "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for obstacle avoidance control of a UAV facing linear obstacles, characterized in that, The UAV obstacle avoidance control method for linear obstacles includes: In response to the obstacle avoidance control commands of the target UAV to linear obstacles, construct a spatial representation of each linear obstacle in terms of line segments; For each linear obstacle, perform local smoothing on the line segment spatial representation to obtain multiple linear targets; The dynamic safety distance and risk score of each linear target are calculated based on the influence mechanism of the geometric structure characteristics of linear obstacles. The system checks whether obstacle avoidance conditions are met based on the dynamic safety distance and linear obstacle risk score corresponding to each linear target. For a current linear target that meets the obstacle avoidance conditions, an obstacle avoidance control law and an obstacle avoidance path are generated, and the target UAV is controlled to perform obstacle avoidance along the obstacle avoidance path according to the obstacle avoidance control law.

2. The UAV obstacle avoidance control method for linear obstacles as described in claim 1, characterized in that, The line segment spatial representation used to construct each linear obstacle includes: For each linear obstacle, obtain the first endpoint and the second endpoint of the linear obstacle; The difference between the coordinate vectors of the first endpoint and the second endpoint is normalized to obtain the unit direction vector; Calculate the projection parameters of the target UAV relative to the first endpoint on the unit direction vector; Obtain the length of the line segment of the linear obstacle; When the projection parameter is less than 0, the distance from the target drone to the first endpoint is calculated as the shortest spatial distance from the target drone to the linear obstacle; when the projection parameter is greater than the line segment length, the distance from the target drone to the second endpoint is calculated as the shortest spatial distance; when the projection parameter is greater than or equal to 0 and less than or equal to the line segment length, the vertical distance from the target drone to the linear obstacle is calculated as the shortest spatial distance. The linear obstacle is represented by a line segment space using the three-dimensional coordinates of the first endpoint, the three-dimensional coordinates of the second endpoint, the unit direction vector, and the shortest spatial distance as parameters.

3. The UAV obstacle avoidance control method for linear obstacles as described in claim 2, characterized in that, The acquisition of the first and second endpoints of the linear obstacle includes: When the linear obstacle includes parameters of a three-dimensional reconstruction curve, the endpoint with the smaller parameter value is obtained from the two endpoints of the linear obstacle as the first endpoint, and the other endpoint is obtained as the second endpoint; When the linear obstacle does not include the parameters of the three-dimensional reconstruction curve, the endpoint with the smaller projected coordinate in the main direction of the line segment corresponding to the linear obstacle is obtained from the two endpoints of the linear obstacle as the first endpoint, and the other endpoint is obtained as the second endpoint.

4. The UAV obstacle avoidance control method for linear obstacles as described in claim 2, characterized in that, The line segment spatial representation of each linear obstacle is subjected to local line segment smoothing to obtain multiple linear targets, including: Identify valid line segments in the linear obstacle, and multiple candidate line segments belonging to the same connected line segment; The multiple candidate line segments are fitted according to a preset sliding window to obtain at least one fitted line segment; From the effective line segments and the fitted line segments, obtain the line segments whose length is greater than the first threshold, and / or whose number of points is greater than the second threshold, and / or whose noise level is greater than the third threshold, and use them as the line segments to be processed; The line segment to be processed is locally fitted into a curve; The curve increments are replaced with the line segment spatial representation of each linear obstacle to obtain the plurality of linear targets.

5. The UAV obstacle avoidance control method for linear obstacles as described in claim 2, characterized in that, The calculation of the dynamic safety distance and linear obstacle risk score for each linear target based on the influence mechanism of linear obstacle geometric structure characteristics includes: For each linear target, obtain the basic safe distance, the current flight speed of the target UAV, the current wind disturbance, the current depth estimation noise, and the current angle between the motion direction of the target UAV and the line segment direction of the linear target; Calculate the absolute value of the sine of the current included angle; The safe offset distance is obtained by weighting the current flight speed, the current wind disturbance, the current depth estimation noise, and the absolute value according to the adjustment coefficient matrix. The dynamic safety distance is obtained by calculating the sum of the basic safety distance and the safety offset distance; Calculate the reciprocal of the shortest spatial distance corresponding to the linear target to obtain the first value; The current flight speed and the current wind disturbance are weighted and calculated according to the weighting coefficient matrix to obtain the second value; Calculate the sum of the second value and 1 to obtain the third value; Obtain the visual confidence level of the linear target, and calculate the product of the visual confidence level, the first value, and the third value to obtain the risk score of the linear obstacle.

6. The UAV obstacle avoidance control method for linear obstacles as described in claim 5, characterized in that, The step of detecting whether the obstacle avoidance conditions are met based on the dynamic safe distance and linear obstacle risk score corresponding to each linear target includes: For each linear target, the first condition is that the risk score of the linear obstacle is greater than a preset score threshold; The second condition is that the shortest spatial distance corresponding to the linear target is less than the dynamic safety distance. The third condition is that the shortest spatial distance corresponding to the linear target within the preset time window changes to be less than the dynamic safety distance within the preset time period. When any one of the first condition, the second condition, or the third condition is met, it is determined that the obstacle avoidance condition is satisfied.

7. The UAV obstacle avoidance control method for linear obstacles as described in claim 2, characterized in that, The generated obstacle avoidance control law and obstacle avoidance path include: Calculate the cross product of the unit direction vector corresponding to the current linear target and the vertical direction of the world coordinate system, and normalize the cross product to obtain the obstacle avoidance direction; Calculate the difference between the dynamic safe distance and the shortest spatial distance corresponding to the current linear target to obtain the current distance difference; The obstacle avoidance control law is obtained by calculating the product of the control gain, the current distance difference, and the obstacle avoidance direction; Calculate the product of the offset coefficient and the obstacle avoidance direction to obtain the three-dimensional offset vector; Obtain the current coordinates of the target UAV's current position, and calculate the sum of the current coordinates and the three-dimensional offset vector to obtain the coordinates of the intermediate point; Based on the original flight path of the target UAV, select the recovery point on the original flight path after obstacle avoidance is completed; The current position is determined as the starting point, the intermediate coordinate point is determined as the intermediate point, and the recovery point is determined as the ending point. A smooth trajectory is generated using a cubic spline algorithm to obtain the obstacle avoidance path.

8. A drone obstacle avoidance control device for linear obstacles, characterized in that, The UAV obstacle avoidance control device for linear obstacles includes: The building unit is used to construct the spatial representation of each linear obstacle in response to the obstacle avoidance control command of the target UAV to the linear obstacle; A smoothing unit is used to perform local smoothing of the line segment spatial representation of each linear obstacle to obtain multiple linear targets; The calculation unit is used to calculate the dynamic safety distance and linear obstacle risk score for each linear target based on the influence mechanism of the geometric structure characteristics of linear obstacles; The detection unit is used to detect whether the obstacle avoidance conditions are met based on the dynamic safety distance and the risk score of the linear obstacle corresponding to each linear target. An execution unit is configured to generate an obstacle avoidance control law and an obstacle avoidance path for a current linear target that meets the obstacle avoidance conditions, and to control the target UAV to perform obstacle avoidance along the obstacle avoidance path according to the obstacle avoidance control law.

9. A computer device, characterized in that, The computer device includes: A memory for storing at least one instruction; and a processor for executing the instructions stored in the memory to implement the UAV obstacle avoidance control method for linear obstacles as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, which is executed by a processor in a computer device to implement the UAV obstacle avoidance control method for linear obstacles as described in any one of claims 1 to 7.

Images