Unmanned aerial vehicle path planning method, device and equipment and storage medium

Abstract

The invention relates to the technical field of unmanned aerial vehicles, and discloses an unmanned aerial vehicle path planning method, device and equipment and a storage medium, and the method comprises the steps: responding to a received inspection task, and obtaining an inspection map corresponding to the inspection task; based on the inspection map, generating a first planned path through a path planning algorithm, and controlling the unmanned aerial vehicle to inspect according to the first planned path; in the inspection process, dynamic obstacle information on the first planned path is obtained; based on the dynamic obstacle information, obtaining a predicted motion track of the dynamic obstacle; generating an obstacle avoidance strategy based on the predicted motion track of the dynamic obstacle; and controlling the unmanned aerial vehicle to inspect according to the first planned path and the obstacle avoidance strategy. The unmanned aerial vehicle can be ensured to accurately plan the flight path in real time in a complex flight environment, and dynamic obstacles can be effectively avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and particularly to a method, device, equipment and storage medium for path planning of unmanned aerial vehicles. Background Art

[0002] With the development of unmanned aerial vehicle technology, path planning and dynamic obstacle avoidance have become important issues for the autonomous flight of unmanned aerial vehicles. Existing path planning methods are mainly based on static maps, ignoring the influence of real-time dynamic obstacles. The obstacle avoidance algorithms usually target environments where the positions of obstacles change less, and are not sensitive enough to the real-time response of dynamic obstacles, which easily leads to inaccurate path planning results or collisions.

[0003] Therefore, in a complex flight environment, how to ensure that the unmanned aerial vehicle can plan the flight path in real time and accurately, and effectively avoid dynamic obstacles is an urgent problem to be solved in the current unmanned aerial vehicle field. Summary of the Invention

[0004] In view of this, the present application provides a method, device, equipment and storage medium for path planning of unmanned aerial vehicles, which can ensure that the unmanned aerial vehicle can plan the flight path in real time and accurately, and effectively avoid dynamic obstacles in a complex flight environment. The technical solution is as follows.

[0005] In a first aspect, the present invention provides a method for path planning of an unmanned aerial vehicle, the method comprising:

[0006] Responding to the received inspection task, and obtaining the inspection map corresponding to the inspection task;

[0007] Based on the inspection map, generating a first planned path through a path planning algorithm, and controlling the unmanned aerial vehicle to perform inspection according to the first planned path;

[0008] During the inspection process, obtaining the dynamic obstacle information on the first planned path;

[0009] Based on the dynamic obstacle information, obtaining the predicted motion trajectory of the dynamic obstacle;

[0010] Based on the predicted motion trajectory of the dynamic obstacle, generating an obstacle avoidance strategy;

[0011] Controlling the unmanned aerial vehicle to perform inspection according to the first planned path and the obstacle avoidance strategy.

[0012] In an optional implementation manner, the generating a first planned path through a path planning algorithm based on the inspection map includes: generating the first planned path between the starting point and the ending point of the inspection map through a path planning algorithm based on the inspection points indicated by the inspection task; the inspection points are the position points that the unmanned aerial vehicle needs to pass through when performing the inspection task.

[0013] In an alternative embodiment, the dynamic obstacle information includes the position, moving speed, and moving direction of the dynamic obstacle.

[0014] In an alternative embodiment, obtaining the predicted motion trajectory of the dynamic obstacle based on the dynamic obstacle information includes: obtaining the predicted motion trajectory of the dynamic obstacle through a trained neural network model based on the position, moving speed, and moving direction of the dynamic obstacle.

[0015] In an alternative embodiment, generating an obstacle avoidance strategy based on the predicted motion trajectory of the dynamic obstacle includes: generating an obstacle avoidance strategy through a dynamic window algorithm according to the predicted motion trajectory of the dynamic obstacle; the obstacle avoidance strategy includes: when the distance between the drone and the dynamic obstacle is less than a first distance, controlling the drone to change the moving direction, moving speed, and moving acceleration so that the drone avoids the dynamic obstacle.

[0016] A method for path planning of a drone provided by the present invention has the following advantages.

[0017] The UAV path planning method of the present invention, when the UAV receives an inspection task, obtains the corresponding inspection map according to the inspection task, and the inspection map is a static two-dimensional or three-dimensional map. Subsequently, according to the starting point, ending point of the inspection task and the inspection points that the inspection task needs to pass through, an initial planned path from the starting point to the ending point is generated on the inspection map. Since the path planning is only based on the static map at this time, it is necessary to adjust the initial planned path according to the actual environmental impact factors during the inspection process. These environmental impact factors may be various static and dynamic obstacles on the inspection path. After generating the initial planned path, the UAV is controlled to execute the inspection task according to this initial planned path. During the inspection process, it is necessary to detect the obstacle information on the inspection path, especially the dynamic obstacle information, which can be detected by a radar or a depth camera, and adjust the detection frequency according to the settings and the actual environmental conditions. After detecting the information of the dynamic obstacle, according to the position, moving speed and moving direction of the dynamic obstacle in the information, the predicted movement trajectory of the dynamic obstacle is obtained through a trained neural network model. An obstacle avoidance strategy is formulated according to the predicted movement trajectory to avoid collision with the dynamic obstacle. The obstacle avoidance strategy can be adjusted as needed. For example, when the distance between the UAV and the dynamic obstacle is less than the set distance, the UAV is controlled to change the moving direction, moving speed and moving acceleration so that the UAV avoids the dynamic obstacle. After the obstacle avoidance strategy is generated, the inspection path of the UAV can be adjusted in real time based on the initial planned path and the obstacle avoidance strategy, so as to control the UAV to complete the inspection task. The UAV path planning method of the present invention can ensure that the UAV can plan the flight path in real time and accurately in a complex flight environment, effectively avoid dynamic obstacles, and ensure that the UAV can complete the flight task smoothly and safely.

[0018] In a second aspect, the present invention provides a UAV path planning device, which includes:

[0019] An acquisition module, configured to obtain the inspection map corresponding to the inspection task in response to the received inspection task;

[0020] A path generation module, configured to generate a first planned path through a path planning algorithm based on the inspection map, and control the UAV to perform inspection according to the first planned path;

[0021] A dynamic obstacle detection module, configured to obtain the dynamic obstacle information on the first planned path during the inspection process;

[0022] A prediction module, configured to obtain the predicted movement trajectory of the dynamic obstacle based on the dynamic obstacle information;

[0023] A strategy generation module, configured to generate an obstacle avoidance strategy based on the predicted movement trajectory of the dynamic obstacle;

[0024] A control module, configured to control the drone to perform inspection according to the first planned path and the obstacle avoidance strategy.

[0025] In an alternative embodiment, the path generation module is specifically configured to:

[0026] Based on the inspection points indicated by the inspection task, generate the first planned path between the starting point and the ending point of the inspection map through a path planning algorithm; the inspection points are the position points that the drone needs to pass through when performing the inspection task.

[0027] In an alternative embodiment, the prediction module is specifically configured to:

[0028] Based on the position, moving speed, and moving direction of the dynamic obstacle, obtain the predicted motion trajectory of the dynamic obstacle through a trained neural network model.

[0029] In an alternative embodiment, the strategy generation module is specifically configured to: according to the predicted motion trajectory of the dynamic obstacle, generate an obstacle avoidance strategy through a dynamic window algorithm; the obstacle avoidance strategy includes: when the distance between the drone and the dynamic obstacle is less than a first distance, control the drone to change the moving direction, moving speed, and moving acceleration so that the drone avoids the dynamic obstacle.

[0030] In a third aspect, the present invention provides a computer device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the drone path planning method according to the first aspect or any corresponding embodiment thereof.

[0031] In a fourth aspect, the present invention provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to cause a computer to execute the drone path planning method according to the first aspect or any corresponding embodiment thereof.

[0032] In a fifth aspect, the present invention provides a computer program product, including computer instructions, and the computer instructions are used to cause a computer to execute the drone path planning method according to the first aspect or any corresponding embodiment thereof. Description of the Drawings

[0033] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0034] Figure 1 It is a schematic flowchart of a method for UAV path planning shown according to an exemplary embodiment.

[0035] Figure 2 It is a schematic diagram of the system architecture of a UAV path planning system based on ROS2 shown according to an exemplary embodiment.

[0036] Figure 3 It is a schematic diagram of the structure of a UAV path planning device provided by an embodiment of the present application.

[0037] Figure 4 It is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention. Detailed implementation manners

[0038] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Apparently, the described embodiments are some but not all of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0039] It should be understood that the "indication" mentioned in the embodiments of the present application may be a direct indication, an indirect indication, or a representation of an associated relationship. For example, A indicates B, which may mean that A directly indicates B. For example, B can be obtained through A; it may also mean that A indirectly indicates B. For example, A indicates C, and B can be obtained through C; it may also mean that there is an associated relationship between A and B.

[0040] In the description of the embodiments of the present application, the term "corresponding" may represent a direct or indirect corresponding relationship between two parties, may also represent an associated relationship between two parties, or may be a relationship such as indication and being indicated, configuration and being configured, etc.

[0041] In the embodiments of the present application, "predefined" can be implemented by pre-saving corresponding codes, tables, or other means that can be used to indicate relevant information in a device (for example, including a terminal device and a network device). The present application does not limit its specific implementation manner.

[0042] As an important product of modern technology, UAVs play an increasingly important role in multiple fields such as search and rescue, monitoring and surveillance, and logistics transportation with their efficient and flexible characteristics. With the development of UAV technology, path planning and dynamic obstacle avoidance have become one of the core technologies for autonomous flight of UAVs.

[0043] In a complex flight environment, how to ensure that the drone can plan the flight path in real time and accurately, and effectively avoid dynamic obstacles is a challenge that needs to be solved urgently in the current drone field. The existing path planning methods are mainly based on static maps, ignoring the influence of real-time dynamic obstacles. The obstacle avoidance algorithms usually target environments where the positions of obstacles change less, and are not sensitive enough to the real-time response of dynamic obstacles, which easily leads to inaccurate path planning results or collisions.

[0044] To solve the limitations of the existing drone path planning solutions, the embodiments of the present invention provide a drone path planning method, which can ensure that the drone can plan the flight path in real time and accurately in a complex flight environment, and effectively avoid dynamic obstacles, ensuring that the drone can complete the flight mission smoothly and safely.

[0045] The method flow of the drone path planning method in this embodiment is as Figure 1 shown and includes the following steps.

[0046] S101. In response to the received inspection task, obtain the inspection map corresponding to the inspection task.

[0047] Specifically, in step S101, the inspection task points to the inspection map of a certain area, which includes the inspection area, the inspection starting point, the inspection ending point, and the inspection intermediate points. These inspection intermediate points are the position points that the drone must pass through when performing the inspection task. The inspection Figure 1 map is generally a static two-dimensional or three-dimensional map for initial path planning.

[0048] S102. Based on the inspection map, generate the first planned path through the path planning algorithm, and control the drone to perform the inspection according to the first planned path.

[0049] Specifically, in step S102, according to the inspection area, the inspection starting point, the inspection ending point, and the inspection intermediate points of the inspection map, generate the initial planned path, that is, the above-mentioned first planned path. The path planning algorithm here can adopt the A* algorithm, the RRT algorithm (Rapidly Exploring Random Tree), etc.

[0050] S103. During the inspection process, obtain the dynamic obstacle information on the first planned path.

[0051] Optionally, in step S103, to obtain the obstacle information on the path, generally, it can be through the radar, camera, sensor, etc. on the drone. The dynamic obstacle information includes the position information, moving speed, moving direction, etc. of the dynamic obstacle.

[0052] S104. Based on the dynamic obstacle information, obtain the predicted motion trajectory of the dynamic obstacle.

[0053] Optionally, according to the position information, moving speed, and moving direction of the dynamic obstacle, use a pre-trained neural network model to predict the trajectory of the dynamic obstacle and obtain the predicted motion trajectory of the dynamic obstacle.

[0054] S105. Generate an obstacle avoidance strategy based on the predicted motion trajectory of the dynamic obstacle.

[0055] Specifically, in the above steps, an obstacle avoidance strategy is generated by the dynamic window method. The obstacle avoidance strategy is: when the distance between the UAV and the dynamic obstacle is less than the first distance, control the UAV to change the moving direction, moving speed, and moving acceleration so that the UAV avoids the dynamic obstacle.

[0056] S106. Control the UAV to perform inspection according to the first planned path and the obstacle avoidance strategy.

[0057] Specifically, in the above steps, control the UAV to execute the inspection flight task according to the generated initial planned path, and avoid the dynamic obstacles on the path through the obstacle avoidance strategy during the inspection, so as to ensure that the UAV completes the inspection task.

[0058] In summary, for the UAV path planning method provided in the embodiments of the present invention, when the UAV receives an inspection task, it obtains the corresponding inspection map according to the inspection task, and the inspection map is a static two-dimensional or three-dimensional map. Subsequently, according to the starting point, ending point of the inspection task and the inspection points that the inspection task needs to pass through, an initial planned path from the starting point to the ending point is generated on the inspection map. Since the path planning is only based on the static map at this time, it is necessary to adjust the initial planned path according to the actual environmental impact factors during the inspection process. These environmental impact factors may be various static and dynamic obstacles on the inspection path. After generating the initial planned path, the UAV is controlled to execute the inspection task according to this initial planned path. During the inspection process, it is necessary to detect the obstacle information on the inspection path, especially the dynamic obstacle information, which can be detected by a radar or a depth camera, and adjust the detection frequency according to the settings and the actual environmental conditions. After detecting the information of the dynamic obstacle, according to the position, moving speed and moving direction of the dynamic obstacle in the information, the predicted movement trajectory of the dynamic obstacle is obtained through a trained neural network model. An obstacle avoidance strategy is formulated according to the predicted movement trajectory to avoid collision with the dynamic obstacle. The obstacle avoidance strategy can be adjusted as needed. For example, when the distance between the UAV and the dynamic obstacle is less than the set distance, the UAV is controlled to change its moving direction, moving speed and moving acceleration so that the UAV can avoid the dynamic obstacle. After the obstacle avoidance strategy is generated, the inspection path of the UAV can be adjusted in real time based on the initial planned path and the obstacle avoidance strategy, so as to control the UAV to complete the inspection task. The UAV path planning method of the present invention can ensure that the UAV can plan the flight path in real time and accurately and effectively avoid dynamic obstacles in a complex flight environment, ensuring that the UAV can complete the flight task smoothly and safely.

[0059] Based on the UAV path planning algorithm in the above embodiment, a UAV path planning system based on ROS2 is constructed.

[0060] ROS2 (Robot Operating System 2), as a highly integrated distributed robot operating system, provides a flexible real-time communication mechanism and powerful computing resources, and is an ideal platform for developing a UAV path planning and dynamic obstacle avoidance system. ROS2 is an open-source operating system that provides various functions for robots, such as hardware abstraction, device drivers, function libraries, visualization tools, message communication, and software package management. It supports multiple programming languages, such as C++ and Python, and provides rich tools and libraries, enabling developers to more conveniently build complex robot systems.

[0061] ROS2 is a powerful general-purpose robotics library that can be used with PX4 (an open-source flight control system) to create powerful drone applications. ROS2 enables deep integration with PX4 and can directly read and write to the internal uORB topics in PX4 at high speeds. Communication between ROS2 and PX4 uses middleware that implements the XRCE-DDS protocol. This middleware exposes PX4 uORB messages as ROS2 messages and types, effectively allowing direct access to PX4 from the ROS2 workflow and nodes. The middleware uses uORB message definitions to generate code for serializing and deserializing messages to and from PX4. These same message definitions are used in ROS2 applications to allow for message interpretation.

[0062] ROS2 supports a distributed architecture, allowing nodes to run on multiple physical machines and communicate over a network, thus supporting more complex and large-scale robotic systems. It also introduces real-time communication mechanisms such as Data Distribution Service (DDS) to support strict real-time requirements, which are applicable to fields such as autonomous driving and industrial automation. ROS2 can run on multiple operating systems such as Linux, Windows, and macOS, greatly improving cross-platform compatibility and providing support for multiple programming languages, including C++ and Python. Developers can choose the appropriate programming language for development according to their preferences and requirements. ROS2 introduces DDS security extensions to support encrypted communication and access control, enhancing system security. Its architecture is more modular, facilitating customization and extension. In addition, the design of ROS2 takes into account the needs of multi-robot collaboration, making it easier to build distributed robotic systems.

[0063] The communication methods of ROS2 are the most core concepts of ROS, and the essence of the ROS system lies in the communication architecture it provides. The main communication methods of ROS2 include the following: Topic: An asynchronous communication method that allows one or more nodes to publish messages to a topic, while one or more nodes can subscribe to this topic to receive messages. Service: A synchronous communication method that allows nodes to communicate through requests and responses. Parameter Server: Used to store and retrieve global parameters, and nodes can read or modify these parameters. Actionlib: Used to handle tasks that require long-term running, providing a mechanism to cancel tasks or query task status.

[0064] The architecture of the drone path planning system based on ROS2 provided in this example is as Figure 2As shown in the figure, it includes a sensor data acquisition module, an environment perception and map construction module, a global path planning module, a dynamic obstacle detection and tracking module, a local obstacle avoidance and path adjustment module, a control and execution module, and a ROS2 communication module. It combines real-time map update, dynamic obstacle detection and avoidance strategies, and intelligent path planning, and can effectively cope with obstacles in a dynamic environment and provide an efficient and accurate robot navigation path.

[0065] The sensor data acquisition module collects sensor data of the environment around the UAV in real time through lidar, IMU (Inertial Measurement Unit), or camera, including but not limited to lidar data, camera image data, inertial navigation data, etc., and publishes this data to the corresponding topic through the message mechanism of ROS2.

[0066] The environment perception and map construction module constructs a detection map through SLAM (Simultaneous Localization and Mapping) and detects obstacle information.

[0067] The global path planning module is used to plan the global path according to the path planning algorithm, that is, the initial path planning. Specifically, it subscribes to the sensor data topic published by the environment perception module, and according to the collected environment information, uses a suitable path planning algorithm (A* algorithm, RRT algorithm, etc.) to generate the optimal or sub-optimal path from the starting point to the ending point, and publishes the planned path information to the corresponding topic through the message mechanism of ROS2.

[0068] The dynamic obstacle detection and tracking module is used to detect and track dynamic obstacles and obtain the moving speed and moving direction of the dynamic obstacles.

[0069] The local obstacle avoidance and path adjustment module is used to subscribe to the topics published by the environment perception module and the path planning module. According to the real-time collected obstacle information and the planned path information, it uses an improved obstacle avoidance algorithm (dynamic window method, artificial potential field method) to generate an obstacle avoidance path, and sends the obstacle avoidance instruction to the control module of the UAV through the message mechanism of ROS2.

[0070] The control and execution module is used to receive the obstacle avoidance instruction sent by the dynamic obstacle avoidance module, generate a control instruction according to the current state and target position of the UAV, and send it to the execution mechanism of the UAV to realize the autonomous flight and obstacle avoidance of the UAV.

[0071] The ROS2 communication module is used for information transfer between various modules and calls the corresponding modules according to requirements.

[0072] The above-mentioned modules cooperate with each other to implement functions such as real-time map update, dynamic obstacle detection and avoidance strategy, and intelligent path planning, which can effectively handle obstacles in a dynamic environment and provide an efficient and accurate robot navigation path. Specifically, first, the A* algorithm is used to calculate the optimal path in the static map. Then, the real-time map update module updates the current environmental state according to the data input by the sensors. In a real-time environment, an improved D* algorithm is adopted for dynamic path adjustment. This algorithm can quickly recalculate the path according to the position changes of real-time obstacles, reducing the computational complexity of replanning. Based on the Dynamic Window Approach (DWA), the possible motion trajectories are evaluated by calculating the current speed, acceleration of the UAV, and the positions of obstacles in the environment. According to the speeds and positions of dynamic obstacles, the algorithm can select a safe path within a short time to avoid areas where collisions are about to occur. At the same time, combined with the multi-threading and real-time processing capabilities of ROS2, it is ensured that the obstacle avoidance operation can be executed in real time without having a negative impact on the performance of the UAV. The obstacle information of the surrounding environment is obtained in real time through the sensor module (LiDAR or depth camera). The sensor data is published through the topic mechanism of ROS2, and the path planning and obstacle avoidance algorithms update the environmental model based on this real-time data. The environmental perception module combines SLAM (Simultaneous Localization and Mapping) technology, which can not only obtain obstacle information but also update the map in real time to optimize the path planning accuracy. Through the control interface of ROS2, the path planning and obstacle avoidance modules output the target position information and speed commands, and the control module adjusts the control signals according to the motion state of the robot to ensure that the robot travels stably on the path and can execute obstacle avoidance actions according to the obstacle avoidance strategy. For example, in a tunnel environment, the UAV needs to carry out handling tasks through complex and narrow channels. The real-time map update module can dynamically construct an obstacle model through sensor data and combine the improved D* algorithm to correct the path in real time. The obstacle avoidance module effectively avoids dynamically moving obstacles, ensuring that the UAV can complete the task smoothly and safely.

[0073] The UAV path planning system based on ROS2 in this example first calculates the optimal path using a path planning algorithm in a static map. Then, the real-time map update module updates the current environmental state according to the data input by the sensors. In the real-time environment, an improved dynamic window algorithm is used for dynamic path adjustment. This algorithm can quickly recalculate the path according to the position changes of real-time obstacles, reducing the computational amount of replanning. According to the speed, direction, and position of dynamic obstacles, a safe path can be selected within a short time to avoid areas where collisions are about to occur. At the same time, combined with the multi-threading and real-time processing capabilities of ROS2, it is ensured that the obstacle avoidance operation can be executed in real time without having a negative impact on the performance of the UAV. By combining real-time map update and the D* algorithm, it is possible to handle dynamically changing obstacles in a complex environment and correct the planned path in real time. Using the distributed architecture and real-time support of ROS2, efficient path planning and dynamic obstacle avoidance are achieved, and multi-threading cooperation is carried out in complex tasks. The dynamic window method is improved using ROS2 multi-threading and implementation processing capabilities, combined with sensor data, which can respond to the movement of obstacles in real time and select a safe path for avoidance. Based on the ROS2 system architecture, the deficiencies of traditional path planning and obstacle avoidance methods in a dynamic environment are effectively solved. This method can not only respond to environmental changes in real time but also provide efficient and safe path planning and obstacle avoidance strategies in complex tasks.

[0074] In an embodiment of the present application, a UAV path planning device is also provided. This device is used to implement the above-mentioned embodiments and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0075] An embodiment of the present application provides a UAV path planning device. Figure 3 FIG. is a schematic structural diagram of a UAV path planning device provided by an embodiment of the present application. The device includes:

[0076] An acquisition module 301, configured to obtain a patrol map corresponding to the received patrol task in response to the received patrol task;

[0077] A path generation module 302, configured to generate a first planned path based on the patrol map through a path planning algorithm, and control the UAV to perform patrol according to the first planned path;

[0078] A dynamic obstacle detection module 303, configured to obtain dynamic obstacle information on the first planned path during the patrol process;

[0079] The prediction module 304 is configured to obtain the predicted motion trajectory of the dynamic obstacle based on the dynamic obstacle information;

[0080] The strategy generation module 305 is configured to generate an obstacle avoidance strategy based on the predicted motion trajectory of the dynamic obstacle;

[0081] The control module 306 is configured to control the drone to perform inspection according to the first planned path and the obstacle avoidance strategy.

[0082] In an alternative embodiment, the path generation module 302 is specifically configured to:

[0083] Generate the first planned path between the start point and the end point of the inspection map through a path planning algorithm based on the inspection points indicated by the inspection task; the inspection points are the position points that the drone needs to pass through when performing the inspection task.

[0084] In an alternative embodiment, the prediction module 304 is specifically configured to:

[0085] Obtain the predicted motion trajectory of the dynamic obstacle through a trained neural network model based on the position, moving speed, and moving direction of the dynamic obstacle.

[0086] In an alternative embodiment, the strategy generation module 305 is specifically configured to: generate an obstacle avoidance strategy through a dynamic window algorithm according to the predicted motion trajectory of the dynamic obstacle; the obstacle avoidance strategy includes: when the distance between the drone and the dynamic obstacle is less than the first distance, controlling the drone to change the moving direction, moving speed, and moving acceleration so that the drone avoids the dynamic obstacle.

[0087] The further function descriptions of the above-mentioned various modules and units are the same as those in the corresponding foregoing embodiments, and will not be elaborated herein.

[0088] The drone path planning device in this embodiment is presented in the form of functional units. Here, the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0089] This embodiment of the present invention further provides a computer device having the above Figure 3 shown drone path planning device.

[0090] Please refer to Figure 4 , Figure 4 which is a schematic structural diagram of a computer device provided by an alternative embodiment of the present invention, as shown in Figure 4As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting the components, including a high-speed interface and a low-speed interface. Each component communicates with each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphical information in a graphical user interface on an external input / output device (such as a display device coupled to the interface). In some alternative embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a set of blade servers, or a multi-processor system). Figure 4 In the figure, a single processor 10 is taken as an example.

[0091] The processor 10 can be a central processing unit, a network processor, or a combination thereof. Among them, the processor 10 can further include a hardware chip. The above-mentioned hardware chip can be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The above-mentioned programmable logic device can be a complex programmable logic device, a field programmable gate array, a generic array logic, or any combination thereof.

[0092] Among them, the memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the methods shown in the above embodiments.

[0093] The memory 20 can include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the computer device. In addition, the memory 20 can include high-speed random access memory and can also include non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 can optionally include a memory remotely set relative to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the above-mentioned network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0094] The memory 20 can include volatile memory, such as random access memory; the memory can also include non-volatile memory, such as flash memory, a hard disk, or a solid-state drive; the memory 20 can also include a combination of the above types of memory.

[0095] The computer device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30, and the output device 40 may be connected through a bus or other means. Figure 4 Taking connection through a bus as an example.

[0096] Embodiments of the present invention further provide a computer-readable storage medium. The method according to the embodiments of the present invention can be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented as computer code that is originally stored in a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored as such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disc, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.

[0097] A part of the present invention can be applied as a computer program product. For example, computer program instructions, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should be able to understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0098] Although the embodiments of the present invention are described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for UAV path planning, characterized in that: The method comprises: In response to the received inspection task, obtaining an inspection map corresponding to the inspection task; Based on the inspection map, a first planned path is generated by a path planning algorithm, and the UAV is controlled to perform inspection along the first planned path; During the inspection process, obtaining dynamic obstacle information on the first planned path; Based on the dynamic obstacle information, a predicted motion trajectory of the dynamic obstacle is obtained; generating an obstacle avoidance strategy based on the predicted motion trajectory of the dynamic obstacle; The drone is controlled to perform inspection according to the first planned path and obstacle avoidance strategy.

2. The method according to claim 1, characterized in that The step of generating a first planned path based on the inspection map by using a path planning algorithm includes: Based on the inspection points indicated by the inspection task, the first planned path is generated between the starting point and the end point of the inspection map through a path planning algorithm; the inspection points are the location points that the drone needs to pass through to perform the inspection task.

3. The method according to claim 1, characterized in that The dynamic obstacle information includes the position, moving speed and moving direction of the dynamic obstacle.

4. The method according to claim 3, characterized in that The obtaining, based on the dynamic obstacle information, a predicted motion trajectory of the dynamic obstacle includes: Based on the position, moving speed and moving direction of the dynamic obstacle, the predicted motion trajectory of the dynamic obstacle is obtained through the trained neural network model.

5. The method according to claim 1, characterized in that The generating of the obstacle avoidance strategy based on the predicted motion trajectory of the dynamic obstacle comprises: generating an obstacle avoidance strategy through a dynamic window algorithm according to the predicted motion trajectory of the dynamic obstacle; The obstacle avoidance strategy includes: when the distance between the drone and the dynamic obstacle is less than a first distance, controlling the drone to change the moving direction, moving speed and moving acceleration so that the drone avoids the dynamic obstacle.

6. A drone path planning device, characterized in that: The device comprises: An acquisition module, configured to, in response to a received inspection task, acquire an inspection map corresponding to the inspection task; A path generation module, used to generate a first planned path based on the inspection map through a path planning algorithm, and control the UAV to perform inspection along the first planned path; A dynamic obstacle detection module, used to obtain dynamic obstacle information on the first planned path during the inspection process; A prediction module, used to obtain a predicted motion trajectory of a dynamic obstacle based on the dynamic obstacle information; A strategy generation module, used to generate an obstacle avoidance strategy based on the predicted motion trajectory of the dynamic obstacle; A control module is used to control the UAV to perform inspection according to the first planned path and obstacle avoidance strategy.

7. The device according to claim 6, characterized in that The path generation module is specifically used for: Based on the inspection points indicated by the inspection task, the first planned path is generated between the starting point and the end point of the inspection map through a path planning algorithm; the inspection points are the location points that the drone needs to pass through to perform the inspection task.

8. The device according to claim 6, characterized in that The prediction module is specifically used for: Based on the position, moving speed and moving direction of the dynamic obstacle, the predicted motion trajectory of the dynamic obstacle is obtained through the trained neural network model.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the UAV path planning method according to any one of claims 1 to 5 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the drone path planning method according to any one of claims 1 to 5.

Images