Unmanned aerial vehicle flight control intelligent obstacle avoidance method, device, system, equipment, medium and product

Abstract

The invention discloses an unmanned aerial vehicle flight control intelligent obstacle avoidance method, device, system, equipment, medium and product, and relates to the technical field of unmanned aerial vehicle flight control. The method comprises the steps of firstly obtaining video data, ranging data and positioning data of the surrounding environment of the unmanned aerial vehicle, then carrying out obstacle detection real-time processing on the video data by adopting a deep learning algorithm to obtain a real-time obstacle detection result, and aiming at each detected obstacle, according to the ranging data and the positioning data, carrying out obstacle detection on the unmanned aerial vehicle. The method comprises the steps of performing real-time analysis to obtain a corresponding position, a moving speed and a moving track, and then performing real-time calculation by adopting an obstacle avoidance path planning algorithm according to positioning data and the real-time position, the moving speed and the moving track of each obstacle to obtain an optimal obstacle avoidance path of the target unmanned aerial vehicle. And finally, controlling the target unmanned aerial vehicle to execute the walking operation on the optimal obstacle avoidance path in real time. Therefore, the flight safety, practicability and universality of the unmanned aerial vehicle in the construction site airspace environment can be improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of unmanned aerial vehicle flight control, and specifically relates to an unmanned aerial vehicle flight control intelligent obstacle avoidance method, device, system, equipment, medium and product. Background Art

[0002] An unmanned aerial vehicle, or "drone," is an unmanned aircraft controlled by a radio remote control device and a self-contained program control device, or operated completely or intermittently autonomously by an onboard computer; compared with manned aircraft, drones are often better suited to tasks that are too "dull, dirty or dangerous."

[0003] UAV flight control intelligent obstacle avoidance technology has been widely used in many flight scenarios in life, such as aerial documentary, GIS (Geographic Information System or Geo-Information system) point cloud modeling and ultra-wide-angle monitoring, etc. It can help drones actively avoid large buildings or special-shaped obstacles during flight, and can also help drones perform tasks safely and smoothly to ensure flight safety.

[0004] Drones are also used in construction sites, but existing drone flight control and obstacle avoidance solutions cannot adapt to the airspace environment of construction sites. For example, it is difficult to identify relatively small obstacles (such as cables, thin columns and steel bars) and small and medium-sized moving objects (such as crane arms and lifting platforms) and other unique objects on construction sites, which will lead to ineffective avoidance and affect safe flight. Therefore, how to provide a new drone flight control and obstacle avoidance solution suitable for the airspace environment of construction sites to efficiently, intelligently and accurately avoid unique objects on construction sites in order to improve the flight safety of drones is a topic that technicians in this field urgently need to study. Summary of the invention

[0005] The purpose of the present invention is to provide a method, device, system, computer equipment, computer-readable storage medium and computer program product for intelligent obstacle avoidance of unmanned aerial vehicle flight control, so as to solve the problem that the existing intelligent obstacle avoidance schemes for unmanned aerial vehicle flight control cannot adapt to the airspace environment at the construction site, which may lead to the inability to effectively avoid unique objects at the construction site and affect safe flight.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, a method for intelligent obstacle avoidance of a UAV flight control is provided, comprising:

[0008] Acquire video data acquired by an airborne camera from the surrounding environment of the UAV in real time, ranging data acquired by an airborne ranging device from the surrounding environment of the UAV in real time, and positioning data acquired by an airborne positioning device in real time, wherein the airborne camera, the airborne ranging device, and the airborne positioning device are respectively fixedly installed on the target UAV;

[0009] Performing real-time obstacle detection processing on the video data using a deep learning algorithm to obtain a real-time obstacle detection result, wherein the obstacle detection result indicates the presence of at least one obstacle;

[0010] For each obstacle in the at least one obstacle, according to the ranging data and the positioning data, a corresponding position, moving speed and moving trajectory are obtained by real-time analysis;

[0011] According to the positioning data and the real-time positions, moving speeds and moving trajectories of the various obstacles, an optimal obstacle avoidance path of the target UAV is calculated in real time using an obstacle avoidance path planning algorithm;

[0012] The target UAV is controlled in real time to perform a walking operation on the optimal obstacle avoidance path.

[0013] Based on the above invention content, a new solution for UAV flight control and obstacle avoidance suitable for the airspace environment of a construction site is provided, that is, firstly, video data obtained by real-time acquisition of the surrounding environment of the UAV by an airborne camera, ranging data obtained by real-time acquisition of the surrounding environment of the UAV by an airborne ranging device, and positioning data obtained by real-time positioning by an airborne positioning device are obtained, and then a deep learning algorithm is used to perform real-time processing of obstacle detection on the video data to obtain a real-time obstacle detection result, and for each detected obstacle, according to the ranging data and the positioning data, the corresponding position, moving speed and moving trajectory are analyzed in real time, and then according to the positioning data and the real-time position, moving speed and moving trajectory of each obstacle, an obstacle avoidance path planning algorithm is used to calculate in real time the optimal obstacle avoidance path of the target UAV, and finally the target UAV is controlled in real time to perform walking operations on the optimal obstacle avoidance path, so that unique objects at the construction site such as cables, thin columns, steel bars, crane arms, lifting platforms and / or buildings can be avoided efficiently, intelligently and accurately, thereby improving the flight safety, practicality and extensiveness of the UAV in the airspace environment of the construction site, and facilitating practical application and promotion.

[0014] In a possible design, according to the positioning data and the real-time positions, moving speeds and moving trajectories of the various obstacles, an optimal obstacle avoidance path of the target UAV is calculated in real time using an obstacle avoidance path planning algorithm, including:

[0015] Acquire air temperature and humidity data, air pressure data and / or wind speed data collected in real time by an airborne environment monitoring sensor, wherein the airborne environment monitoring sensor is also fixedly mounted on the target UAV;

[0016] According to the positioning data and the real-time positions, moving speeds and moving trajectories of the various obstacles, and in combination with the air temperature and humidity data, air pressure data and / or wind speed data, an obstacle avoidance path planning algorithm is used to calculate in real time the optimal obstacle avoidance path of the target UAV.

[0017] In one possible design, the airborne ranging equipment includes a laser radar and / or an ultrasonic ranging sensor.

[0018] In one possible design, the airborne positioning device includes a GPS / BD satellite positioning module and / or an IMU-based inertial navigation module.

[0019] In one possible design, the deep learning algorithm uses the YOLO V5 target detection algorithm, and the at least one obstacle includes cables, thin columns, steel bars, crane arms, lifting platforms and / or buildings.

[0020] In a second aspect, a UAV flight control intelligent obstacle avoidance device is provided, comprising a multi-source data acquisition unit, an obstacle detection processing unit, an obstacle positioning processing unit, an obstacle avoidance path calculation unit and a UAV real-time control unit;

[0021] The multi-source data acquisition unit is used to acquire video data acquired by an airborne camera from the surrounding environment of the UAV in real time, ranging data acquired by an airborne ranging device from the surrounding environment of the UAV in real time, and positioning data acquired by an airborne positioning device in real time, wherein the airborne camera, the airborne ranging device, and the airborne positioning device are respectively fixedly installed on the target UAV;

[0022] The obstacle detection processing unit is communicatively connected to the multi-source data acquisition unit, and is used to perform real-time obstacle detection processing on the video data using a deep learning algorithm to obtain a real-time obstacle detection result, wherein the obstacle detection result indicates the existence of at least one obstacle;

[0023] The obstacle positioning processing unit is communicatively connected to the multi-source data acquisition unit and the obstacle detection processing unit, and is used to analyze in real time, according to the ranging data and the positioning data, each obstacle in the at least one obstacle to obtain a corresponding position, moving speed and moving trajectory;

[0024] The obstacle avoidance path calculation unit is communicatively connected to the multi-source data acquisition unit and the obstacle positioning processing unit, and is used to calculate the optimal obstacle avoidance path of the target UAV in real time by using an obstacle avoidance path planning algorithm according to the positioning data and the real-time positions, moving speeds and moving trajectories of the various obstacles;

[0025] The UAV real-time control unit is communicatively connected to the obstacle avoidance path calculation unit and is used for controlling the target UAV in real time to perform a walking operation on the optimal obstacle avoidance path.

[0026] In a third aspect, the present invention provides a UAV flight control intelligent obstacle avoidance system, comprising an airborne camera, an airborne ranging device, an airborne positioning device, a control device, and a target UAV, wherein the airborne camera, the airborne ranging device, and the airborne positioning device are respectively fixedly mounted on the target UAV;

[0027] The onboard camera is communicatively connected to the control device and is used to collect video data of the surrounding environment of the drone in real time and transmit the collected results to the control device in real time;

[0028] The airborne distance measuring device is communicatively connected to the control device, and is used to collect distance measuring data of the surrounding environment of the UAV in real time, and transmit the collected results to the control device in real time;

[0029] The airborne positioning device is communicatively connected to the control device, and is used for real-time positioning to obtain positioning data, and transmits the positioning result to the control device in real time;

[0030] The control device is communicatively connected to the target UAV, and is used to execute the UAV flight control intelligent obstacle avoidance method as described in the first aspect or any possible design of the first aspect;

[0031] The target UAV is used to receive and execute control instructions from the control device.

[0032] In a fourth aspect, the present invention provides a control device, comprising a storage module, a processing module and a transceiver module which are communicatively connected in sequence, wherein the storage module is used to store a computer program, the transceiver module is used to send and receive messages, and the processing module is used to read the computer program to execute the intelligent obstacle avoidance method for unmanned aerial vehicle flight control as described in the first aspect or any possible design of the first aspect.

[0033] In a fifth aspect, the present invention provides a computer-readable storage medium having instructions stored thereon. When the instructions are executed on a computer, the intelligent obstacle avoidance method for unmanned aerial vehicle flight control as described in the first aspect or any possible design of the first aspect is executed.

[0034] In a sixth aspect, the present invention provides a computer program product, including a computer program or instructions, which, when executed by a computer, implements the intelligent obstacle avoidance method for unmanned aerial vehicle flight control as described in the first aspect or any possible design of the first aspect.

[0035] Beneficial effects of the above scheme:

[0036] (1) The present invention creatively provides a new solution for UAV flight control and obstacle avoidance in the airspace environment of a construction site, namely, firstly obtaining video data acquired by an onboard camera of the UAV's surrounding environment in real time, ranging data acquired by an onboard ranging device of the UAV's surrounding environment in real time, and positioning data acquired by an onboard positioning device in real time, then using a deep learning algorithm to perform real-time obstacle detection and processing on the video data to obtain real-time obstacle detection results, and for each detected obstacle, according to the ranging data and the positioning data, real-time analysis is performed to obtain the corresponding position, moving speed and moving trajectory, and then, according to the positioning data and the real-time position, moving speed and moving trajectory of each obstacle, an obstacle avoidance path planning algorithm is used to calculate in real time the optimal obstacle avoidance path of the target UAV, and finally, the target UAV is controlled in real time to perform walking operations on the optimal obstacle avoidance path, so that the target UAV can efficiently, intelligently and accurately avoid construction site-specific objects such as cables, thin columns, steel bars, crane arms, lifting platforms and / or buildings, thereby improving the flight safety, practicality and extensiveness of the UAV in the airspace environment of the construction site, and facilitating practical application and promotion. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 A flow chart of the intelligent obstacle avoidance method for UAV flight control provided in an embodiment of the present application.

[0039] Figure 2 A schematic diagram of the structure of the intelligent obstacle avoidance device for UAV flight control provided in an embodiment of the present application.

[0040] Figure 3 A schematic diagram of the structure of the UAV flight control intelligent obstacle avoidance system provided in an embodiment of the present application.

[0041] Figure 4 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structures of the drawings is only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can be obtained based on these embodiments without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0043] It should be understood that although the terms first and second, etc. may be used herein to describe various objects, these objects should not be limited by these terms. These terms are only used to distinguish one object from another object. For example, a first object can be referred to as a second object, and similarly, a second object can be referred to as a first object without departing from the scope of the exemplary embodiments of the present invention.

[0044] It should be understood that the term "and / or" that may appear in this document is merely a description of the association relationship between associated objects, indicating that there may be three relationships. For example, A and / or B can indicate three situations: A exists alone, B exists alone, or A and B exist at the same time. For another example, A, B and / or C can indicate the existence of any one of A, B and C or any combination of them. The term " / and" that may appear in this document describes another type of association object relationship, indicating that there may be two relationships. For example, A / and B can indicate two situations: A exists alone or A and B exist at the same time. In addition, the character " / " that may appear in this document generally indicates that the previous and next associated objects are in an "or" relationship.

[0045] Example

[0046] like Figure 1 As shown, the UAV flight control intelligent obstacle avoidance method provided in the first aspect of this embodiment can be, but is not limited to, executed by a control device having certain computing resources and communicating with an airborne camera, an airborne ranging device, an airborne positioning device, and a target UAV, for example, by a UAV ground control platform server arranged at a construction site. The UAV flight control intelligent obstacle avoidance method includes, but is not limited to, the following steps S1 to S5.

[0047] S1. Obtain video data collected in real time by an airborne camera on the surrounding environment of the UAV, ranging data collected in real time by an airborne ranging device on the surrounding environment of the UAV, and positioning data obtained by real-time positioning by an airborne positioning device, wherein the airborne camera, the airborne ranging device and the airborne positioning device are respectively fixedly installed on the target UAV.

[0048] In the step S1, the airborne camera can be implemented by using existing high-definition camera products. The airborne distance measuring device can specifically include, but is not limited to, laser radar and / or ultrasonic distance measuring sensors, etc., which can measure the shape and three-dimensional distance of objects in the surrounding environment of the drone based on existing laser distance measuring technology or ultrasonic distance measuring technology, so the distance measuring data can be routinely collected. The airborne positioning device can specifically include, but is not limited to, a GPS (Global Positioning System) / BDS (Beidou Navigation Satellite System) satellite positioning module and / or an inertial navigation module based on IMU (Inertial Measurement Unit), wherein the former can obtain the positioning data of the target drone such as the position, speed and direction based on the existing satellite positioning technology, and the latter will specifically include a three-axis accelerometer, a three-axis gyroscope, a three-axis magnetometer and a barometer, etc., and through the joint work of these four sensors, provide the target drone and accurate positioning data such as the position, speed, direction and attitude, etc., so the positioning data can be obtained by conventional positioning. In addition, the specific methods of collecting and transmitting the video data, transmitting the ranging data, and transmitting the positioning data to the local control device are existing technical means.

[0049] S2. Use a deep learning algorithm to perform real-time obstacle detection processing on the video data to obtain a real-time obstacle detection result, wherein the obstacle detection result indicates the existence of at least one obstacle.

[0050] In step S2, the deep learning algorithm is an important branch of artificial intelligence algorithm, which uses neural networks and large-scale data to simulate the learning and reasoning process of the human brain, thereby achieving autonomous learning and decision-making. It has been widely used in technical fields such as image recognition, speech recognition, and natural language processing. As one of the deep learning algorithms, the target detection algorithm is an existing artificial intelligence recognition algorithm used to identify objects in a picture and mark the location of the objects. Specifically, it may include but is not limited to Faster R-CNN (Faster Regions with Convolutional Neural Networks features, a target detection algorithm proposed by He Kaiming et al. in 2015. The algorithm won multiple first places in the 2015 ILSVRV and COCO competitions) target detection algorithm, SSD (Single Shot MultiBox Detector, a target detection algorithm proposed by Wei Liu at ECCV 2016, which is one of the main popular detection frameworks) target detection algorithm or YOLO (You only look once, currently the latest version has been developed to V5, and is also widely used in the industry. Its basic principle is: first, the input image is divided into 7×7 grids, and 2 borders are predicted for each grid. Then, the target windows with relatively low probability are removed according to the threshold, and finally, the redundant windows are removed by border merging to obtain the detection result) target detection algorithm. Since the imaging results of different obstacles are different, it is possible to detect whether there is an obstacle mark frame in the video frame image of the video data based on an existing deep learning algorithm (i.e., as the obstacle detection result, each obstacle mark frame represents an obstacle); for example, the deep learning algorithm may be, but is not limited to, a YOLO V5 target detection algorithm. In addition, since the environment is an airspace environment at a construction site, the at least one obstacle includes, but is not limited to, objects unique to the construction site, such as cables, thin columns, steel bars, crane arms, lifting platforms, and / or buildings.

[0051] S3. For each obstacle in the at least one obstacle, obtain the corresponding position, moving speed and moving trajectory through real-time analysis based on the ranging data and the positioning data.

[0052] In step S3, since each obstacle detected has a three-dimensional coordinate and a viewing angle range in the camera coordinate system with the position of the airborne camera as the origin of the coordinate system, and the ranging data contains the results of measuring the three-dimensional distance from the airborne ranging device to the objects in the surrounding environment of the drone in each viewing angle direction, therefore, under the premise that the airborne camera, the airborne ranging device, the airborne positioning device and the target drone are regarded as a whole, for each obstacle, the three-dimensional distance from the target drone to the corresponding obstacle can be determined from the ranging data based on the corresponding viewing angle range, and the corresponding positioning data such as the position, moving speed and moving trajectory can be obtained according to the three-dimensional distance and the positioning data, combined with conventional conversion based on geometric knowledge.

[0053] S4. Based on the positioning data and the real-time positions, moving speeds and moving trajectories of the various obstacles, an obstacle avoidance path planning algorithm is used to calculate in real time the optimal obstacle avoidance path of the target UAV.

[0054] In step S4, the obstacle avoidance path planning algorithm can be obtained by conventionally modifying the existing sweeping robot obstacle avoidance algorithm. In addition, considering that factors such as air temperature and humidity, air pressure and wind force will also affect the flight of the drone, specifically, according to the positioning data and the real-time positions of the various obstacles, the moving speed and the moving trajectory, the obstacle avoidance path planning algorithm is used to calculate in real time the optimal obstacle avoidance path of the target drone, including but not limited to the following steps: first, obtain the air temperature and humidity data, air pressure data and / or wind force data collected in real time by the airborne environmental monitoring sensor, wherein the airborne environmental monitoring sensor is also fixedly installed on the target drone; then, according to the positioning data and the real-time positions of the various obstacles, the moving speed and the moving trajectory, and in combination with the air temperature and humidity data, air pressure data and / or wind force data, the obstacle avoidance path planning algorithm is used to calculate in real time the optimal obstacle avoidance path of the target drone.

[0055] S5. Control the target UAV in real time to perform walking operations on the optimal obstacle avoidance path.

[0056] In step S5, the specific control method may include but is not limited to sending an ascending command, a descending command, a forward command, a backward command, a left turn command or a right turn command to the target UAV, so that the target UAV executes these commands to achieve walking operation on the optimal obstacle avoidance path.

[0057] Therefore, based on the UAV flight control intelligent obstacle avoidance method described in the aforementioned steps S1 to S5, a new UAV flight control obstacle avoidance solution suitable for the airspace environment of the construction site is provided, that is, firstly, video data obtained by real-time acquisition of the UAV surrounding environment by the airborne camera, ranging data obtained by real-time acquisition of the UAV surrounding environment by the airborne ranging device, and positioning data obtained by real-time positioning by the airborne positioning device are obtained, and then the video data is processed in real time by a deep learning algorithm for obstacle detection to obtain a real-time obstacle detection result, and for each detected obstacle, the corresponding position, moving speed and moving trajectory are analyzed in real time according to the ranging data and the positioning data, and then the optimal obstacle avoidance path of the target UAV is calculated in real time according to the positioning data and the real-time position, moving speed and moving trajectory of each obstacle by using an obstacle avoidance path planning algorithm, and finally the target UAV is controlled in real time to perform walking operations on the optimal obstacle avoidance path, so that unique objects at the construction site such as cables, thin columns, steel bars, crane arms, lifting platforms and / or buildings can be avoided efficiently, intelligently and accurately, and the flight safety, practicality and extensiveness of the UAV in the airspace environment of the construction site are improved, which is convenient for practical application and promotion.

[0058] like Figure 2 As shown, the second aspect of this embodiment provides a virtual device for implementing the intelligent obstacle avoidance method for UAV flight control described in the first aspect, comprising a multi-source data acquisition unit, an obstacle detection processing unit, an obstacle positioning processing unit, an obstacle avoidance path calculation unit and a UAV real-time control unit;

[0059] The multi-source data acquisition unit is used to acquire video data acquired by an airborne camera from the surrounding environment of the UAV in real time, ranging data acquired by an airborne ranging device from the surrounding environment of the UAV in real time, and positioning data acquired by an airborne positioning device in real time, wherein the airborne camera, the airborne ranging device, and the airborne positioning device are respectively fixedly installed on the target UAV;

[0060] The obstacle detection processing unit is communicatively connected to the multi-source data acquisition unit, and is used to perform real-time obstacle detection processing on the video data using a deep learning algorithm to obtain a real-time obstacle detection result, wherein the obstacle detection result indicates the existence of at least one obstacle;

[0061] The obstacle positioning processing unit is communicatively connected to the multi-source data acquisition unit and the obstacle detection processing unit, and is used to analyze in real time, according to the ranging data and the positioning data, each obstacle in the at least one obstacle to obtain a corresponding position, moving speed and moving trajectory;

[0062] The obstacle avoidance path calculation unit is communicatively connected to the multi-source data acquisition unit and the obstacle positioning processing unit, and is used to calculate the optimal obstacle avoidance path of the target UAV in real time by using an obstacle avoidance path planning algorithm according to the positioning data and the real-time positions, moving speeds and moving trajectories of the various obstacles;

[0063] The UAV real-time control unit is communicatively connected to the obstacle avoidance path calculation unit and is used for controlling the target UAV in real time to perform a walking operation on the optimal obstacle avoidance path.

[0064] The working process, working details and technical effects of the aforementioned device provided in the second aspect of this embodiment can be found in the UAV flight control intelligent obstacle avoidance method described in the first aspect, and will not be repeated here.

[0065] like Figure 3 As shown, the third aspect of this embodiment provides a physical system for implementing the intelligent obstacle avoidance method for UAV flight control described in the first aspect, comprising an airborne camera, an airborne ranging device, an airborne positioning device, a control device, and a target UAV, wherein the airborne camera, the airborne ranging device, and the airborne positioning device are respectively fixedly mounted on the target UAV;

[0066] The onboard camera is communicatively connected to the control device and is used to collect video data of the surrounding environment of the drone in real time and transmit the collected results to the control device in real time;

[0067] The airborne distance measuring device is communicatively connected to the control device, and is used to collect distance measuring data of the surrounding environment of the UAV in real time, and transmit the collected results to the control device in real time;

[0068] The airborne positioning device is communicatively connected to the control device, and is used for real-time positioning to obtain positioning data, and transmits the positioning result to the control device in real time;

[0069] The control device is communicatively connected to the target UAV and is used to execute the UAV flight control intelligent obstacle avoidance method as described in the first aspect;

[0070] The target UAV is used to receive and execute control instructions from the control device.

[0071] The working process, working details and technical effects of the aforementioned system provided in the third aspect of this embodiment can be found in the UAV flight control intelligent obstacle avoidance method described in the first aspect, and will not be repeated here.

[0072] like Figure 4As shown, the fourth aspect of this embodiment provides a control device for executing the intelligent obstacle avoidance method for unmanned aerial vehicle flight control as described in the first aspect, including a storage module, a processing module and a transceiver module that are sequentially connected in communication, wherein the storage module is used to store a computer program, the transceiver module is used to send and receive messages, and the processing module is used to read the computer program to execute the intelligent obstacle avoidance method for unmanned aerial vehicle flight control as described in the first aspect. For example, the storage module may include, but is not limited to, a random access memory (Random-Access Memory, RAM), a read-only memory (Read-Only Memory, ROM), a flash memory (Flash Memory), a first-in-first-out memory (First Input First Output, FIFO) and / or a first-in-last-out memory (First Input Last Output, FILO), etc.; the processing module may include, but is not limited to, a microprocessor of the STM32F105 series. In addition, the control device may also include, but is not limited to, a power module, a display screen and other necessary components.

[0073] The working process, working details and technical effects of the aforementioned control device provided in the fourth aspect of this embodiment can be found in the UAV flight control intelligent obstacle avoidance method described in the first aspect, and will not be repeated here.

[0074] The fifth aspect of this embodiment provides a computer-readable storage medium storing instructions including the intelligent obstacle avoidance method for unmanned aerial vehicle flight control as described in the first aspect, that is, the computer-readable storage medium stores instructions, and when the instructions are executed on a computer, the intelligent obstacle avoidance method for unmanned aerial vehicle flight control as described in the first aspect is executed. The computer-readable storage medium refers to a carrier for storing data, which may include but is not limited to computer-readable storage media such as floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or memory sticks, and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0075] The working process, working details and technical effects of the aforementioned computer-readable storage medium provided in the fifth aspect of this embodiment can be referred to the intelligent obstacle avoidance method for UAV flight control as described in the first aspect, and will not be repeated here.

[0076] A sixth aspect of this embodiment provides a computer program product, including a computer program or an instruction, which, when executed by a computer, implements the intelligent obstacle avoidance method for UAV flight control as described in the first aspect. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0077] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent obstacle avoidance method for UAV flight control, characterized in that: include: Acquire video data acquired by an airborne camera from the surrounding environment of the UAV in real time, ranging data acquired by an airborne ranging device from the surrounding environment of the UAV in real time, and positioning data acquired by an airborne positioning device in real time, wherein the airborne camera, the airborne ranging device, and the airborne positioning device are respectively fixedly installed on the target UAV; Performing real-time obstacle detection processing on the video data using a deep learning algorithm to obtain a real-time obstacle detection result, wherein the obstacle detection result indicates the presence of at least one obstacle; For each obstacle in the at least one obstacle, according to the ranging data and the positioning data, a corresponding position, moving speed and moving trajectory are obtained by real-time analysis; According to the positioning data and the real-time positions, moving speeds and moving trajectories of the various obstacles, an optimal obstacle avoidance path of the target UAV is calculated in real time using an obstacle avoidance path planning algorithm; The target UAV is controlled in real time to perform a walking operation on the optimal obstacle avoidance path.

2. The intelligent obstacle avoidance method for UAV flight control according to claim 1, characterized in that: According to the positioning data and the real-time positions, moving speeds and moving trajectories of the various obstacles, an optimal obstacle avoidance path of the target UAV is calculated in real time using an obstacle avoidance path planning algorithm, including: Acquire air temperature and humidity data, air pressure data and / or wind speed data collected in real time by an airborne environment monitoring sensor, wherein the airborne environment monitoring sensor is also fixedly mounted on the target UAV; According to the positioning data and the real-time positions, moving speeds and moving trajectories of the various obstacles, and in combination with the air temperature and humidity data, air pressure data and / or wind speed data, an obstacle avoidance path planning algorithm is used to calculate in real time the optimal obstacle avoidance path of the target UAV.

3. The intelligent obstacle avoidance method for UAV flight control according to claim 1, characterized in that: The airborne distance measuring equipment includes a laser radar and / or an ultrasonic distance measuring sensor.

4. The intelligent obstacle avoidance method for UAV flight control according to claim 1, characterized in that: The airborne positioning device includes a GPS / BD satellite positioning module and / or an IMU-based inertial navigation module.

5. The intelligent obstacle avoidance method for UAV flight control according to claim 1, characterized in that: The deep learning algorithm adopts the YOLO V5 target detection algorithm, and the at least one obstacle includes cables, thin columns, steel bars, crane arms, lifting platforms and / or buildings.

6. An intelligent obstacle avoidance device for UAV flight control, characterized in that: It includes a multi-source data acquisition unit, an obstacle detection processing unit, an obstacle positioning processing unit, an obstacle avoidance path calculation unit and a UAV real-time control unit; The multi-source data acquisition unit is used to acquire video data acquired by an airborne camera from the surrounding environment of the UAV in real time, ranging data acquired by an airborne ranging device from the surrounding environment of the UAV in real time, and positioning data acquired by an airborne positioning device in real time, wherein the airborne camera, the airborne ranging device, and the airborne positioning device are respectively fixedly installed on the target UAV; The obstacle detection processing unit is communicatively connected to the multi-source data acquisition unit, and is used to perform real-time obstacle detection processing on the video data using a deep learning algorithm to obtain a real-time obstacle detection result, wherein the obstacle detection result indicates the existence of at least one obstacle; The obstacle positioning processing unit is communicatively connected to the multi-source data acquisition unit and the obstacle detection processing unit, and is used to analyze in real time, according to the ranging data and the positioning data, each obstacle in the at least one obstacle to obtain a corresponding position, moving speed and moving trajectory; The obstacle avoidance path calculation unit is communicatively connected to the multi-source data acquisition unit and the obstacle positioning processing unit, and is used to calculate the optimal obstacle avoidance path of the target UAV in real time by using an obstacle avoidance path planning algorithm according to the positioning data and the real-time positions, moving speeds and moving trajectories of the various obstacles; The UAV real-time control unit is communicatively connected to the obstacle avoidance path calculation unit and is used for controlling the target UAV in real time to perform a walking operation on the optimal obstacle avoidance path.

7. An intelligent obstacle avoidance system for UAV flight control, characterized in that: It includes an airborne camera, an airborne distance measuring device, an airborne positioning device, a control device and a target UAV, wherein the airborne camera, the airborne distance measuring device and the airborne positioning device are respectively fixedly installed on the target UAV; The onboard camera is communicatively connected to the control device and is used to collect video data of the surrounding environment of the drone in real time and transmit the collected results to the control device in real time; The airborne distance measuring device is communicatively connected to the control device, and is used to collect distance measuring data of the surrounding environment of the UAV in real time, and transmit the collected results to the control device in real time; The airborne positioning device is communicatively connected to the control device, and is used for real-time positioning to obtain positioning data, and transmit the positioning result to the control device in real time; The control device is communicatively connected to the target UAV and is used to execute the UAV flight control intelligent obstacle avoidance method according to any one of claims 1 to 5; The target UAV is used to receive and execute control instructions from the control device.

8. A control device, characterized in that: The method comprises a storage module, a processing module and a transceiver module which are sequentially communicatively connected, wherein the storage module is used to store a computer program, the transceiver module is used to send and receive messages, and the processing module is used to read the computer program to execute the intelligent obstacle avoidance method for UAV flight control as described in any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed on the computer, the intelligent obstacle avoidance method for UAV flight control as described in any one of claims 1 to 5 is executed.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or the instruction is executed by a computer, the intelligent obstacle avoidance method for UAV flight control is implemented as described in any one of claims 1 to 5.

Images