Cooperative obstacle avoidance sensing method and system for unmanned aerial vehicle and unmanned ship

Abstract

The invention relates to a cooperative obstacle avoidance sensing method and system for an unmanned aerial vehicle and an unmanned ship, and relates to the technical field of medical treatment, and the method comprises the steps: obtaining first sensing data of the unmanned aerial vehicle; acquiring second sensing data of the unmanned ship; determining obstacle avoidance information based on the first sensing data and the second sensing data; and generating an obstacle avoidance instruction according to the obstacle avoidance information. Through the combination of different source sensing data, the accuracy and reliability of obstacle avoidance of the unmanned ship are improved.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle technology, and in particular to a cooperative obstacle avoidance perception method, system, electronic equipment and non-transient computer-readable storage medium for unmanned aerial vehicles and unmanned boats. Background Art

[0002] UAVs and unmanned boats are key components of unmanned systems, with autonomous flight and navigation capabilities. They can carry various sensors and actuators, and communicate and transmit commands to ground control systems through wireless communications.

[0003] In the existing technology, obstacle detection and recognition technology usually extracts obstacle information from the sensor data of drones or unmanned boats, and then generates navigation paths and decisions based on the perceived obstacle information. However, this method has low obstacle perception accuracy, which brings hidden dangers to the navigation of unmanned boats. Summary of the invention

[0004] In view of the technical problems existing in the prior art, the present invention provides a collaborative obstacle avoidance perception method, system, electronic device and non-transitory computer-readable storage medium for a UAV and an unmanned boat.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: The present invention provides a collaborative obstacle avoidance perception method for a UAV and an unmanned boat, the method comprising: Obtain the first perception data of the drone; Obtaining the second perception data of the unmanned boat; Determining obstacle avoidance information based on the first perception data and the second perception data; An obstacle avoidance instruction is generated according to the obstacle avoidance information.

[0006] Optionally, the first perception data includes: image data and position data of any obstacle.

[0007] Optionally, the second perception data includes: image data and position data of any obstacle.

[0008] Optionally, determining obstacle avoidance information based on the first perception data and the second perception data includes: matching the first sensing data and the second sensing data to determine the same obstacle; fusing the image data of the same obstacle to obtain target image data; Fusion of the position data of the same obstacle to obtain target position data; Obstacle avoidance information is determined based on the target image data and the target position data.

[0009] Optionally, matching the first perception data and the second perception data to determine the same obstacle includes: Using an image matching algorithm, matching the image data of any obstacle in the first perception data with the image data of any obstacle in the second perception data to determine similar obstacles; Calculating the perceived distance according to the position data of the similar obstacles; Similar obstacles whose perception distance is less than a preset threshold are determined as the same obstacle; the same obstacle is composed of any obstacle in the first perception data and any obstacle in the second perception data.

[0010] Optionally, fusing the image data of the same obstacle to obtain target image data includes: An image fusion algorithm is used to fuse the image data of the same obstacle to obtain target image data.

[0011] Optionally, fusing the position data of the same obstacle to obtain target position data includes: The weighted average algorithm is used to fuse the position data of the same obstacle to obtain the target position data.

[0012] Optionally, determining obstacle avoidance information based on the target image data and the target position data includes: Create raster maps; Extracting image features from the target image data by using an edge detection algorithm; The grid map is updated according to the image features and the target position data, and the updated grid map is used as obstacle avoidance information.

[0013] Optionally, after generating the obstacle avoidance instruction, the method further includes: According to the obstacle avoidance instruction, the navigation route of the unmanned boat is replanned.

[0014] The present invention also provides a cooperative obstacle avoidance perception system for a UAV and an unmanned boat, the system comprising: A first data acquisition module, used to acquire first perception data of the drone; A second data acquisition module is used to acquire second perception data of the unmanned boat; a data analysis module, configured to determine obstacle avoidance information based on the first perception data and the second perception data; The instruction generation module is used to generate an obstacle avoidance instruction according to the obstacle avoidance information.

[0015] Optionally, the first perception data includes: image data and position data of any obstacle.

[0016] Optionally, the second perception data includes: image data and position data of any obstacle.

[0017] Optionally, the data analysis module is further used to: matching the first sensing data and the second sensing data to determine the same obstacle; fusing the image data of the same obstacle to obtain target image data; Fusion of the position data of the same obstacle to obtain target position data; Obstacle information is determined based on the target image data and the target position data.

[0018] Optionally, matching the first perception data and the second perception data to determine the same obstacle includes: Using an image matching algorithm, matching the image data of any obstacle in the first perception data with the image data of any obstacle in the second perception data to determine similar obstacles; Calculating the perceived distance according to the position data of the similar obstacles; Similar obstacles whose perception distance is less than a preset threshold are determined as the same obstacle; the same obstacle is composed of any obstacle in the first perception data and any obstacle in the second perception data.

[0019] Optionally, fusing the image data of the same obstacle to obtain target image data includes: An image fusion algorithm is used to fuse the image data of the same obstacle to obtain target image data.

[0020] Optionally, fusing the position data of the same obstacle to obtain target position data includes: The weighted average algorithm is used to fuse the position data of the same obstacle to obtain the target position data.

[0021] Optionally, determining obstacle avoidance information based on the target image data and the target position data includes: Create raster maps; Extracting image features from the target image data by using an edge detection algorithm; The grid map is updated according to the image features and the target position data, and the updated grid map is used as obstacle avoidance information.

[0022] Optionally, after generating the obstacle avoidance instruction, the method further includes: According to the obstacle avoidance instruction, the navigation route of the unmanned boat is replanned.

[0023] In addition, to achieve the above-mentioned purpose, the present invention also proposes an electronic device, including: a memory for storing a computer software program; a processor for reading and executing the computer software program, thereby realizing a collaborative obstacle avoidance perception method for a drone and an unmanned boat as described above.

[0024] In addition, to achieve the above-mentioned purpose, the present invention also proposes a non-transitory computer-readable storage medium, in which a computer software program is stored. When the computer software program is executed by a processor, it implements the collaborative obstacle avoidance perception method of a drone and an unmanned boat as described above.

[0025] The beneficial effects of the present invention are: (1) The present invention obtains first perception data of a drone; obtains second perception data of an unmanned boat; determines obstacle avoidance information based on the first perception data and the second perception data; and generates obstacle avoidance instructions according to the obstacle avoidance information. By obtaining and analyzing perception data from different sources and generating corresponding obstacle avoidance instructions, the accuracy and reliability of obstacle avoidance of the unmanned boat are improved, and the risk of collision with obstacles is reduced.

[0026] (2) The present invention takes into account the importance of obstacle images and positions to obstacle avoidance accuracy, matches the first perception data and the second perception data to determine the same obstacle; fuses the image data of the same obstacle to obtain target image data; fuses the position data of the same obstacle to obtain target position data; and determines obstacle avoidance information based on the target image data and the target position data. This improves the accuracy of obstacle recognition.

[0027] (3) The present invention adopts an image matching algorithm to match the image data of any obstacle in the first perception data with the image data of any obstacle in the second perception data to determine similar obstacles; calculate the perception distance according to the position data of the similar obstacles; determine similar obstacles whose perception distance is less than a preset threshold as the same obstacle; the same obstacle is composed of any obstacle in the first perception data and any obstacle in the second perception data. Based on this, more comprehensive and accurate obstacle information is provided, thereby improving the obstacle avoidance capability and safety of the unmanned boat or other equipment.

[0028] (4) The present invention creates a grid map of the current environment; extracts image features from the target image data through an edge detection algorithm; updates the grid map based on the image features and the target location data, and uses the updated grid map as obstacle avoidance information. This enables perception and avoidance of obstacles in the environment, providing safety for the navigation of the unmanned boat. By creating a grid map, extracting image features, and updating the grid map, environmental perception is enhanced, collision risks are avoided, and reliable obstacle avoidance guidance is provided for the device. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A scene diagram of a cooperative obstacle avoidance perception method for a UAV and an unmanned boat provided by the present invention; Figure 2 A flowchart of a collaborative obstacle avoidance perception method for a UAV and an unmanned boat provided by the present invention; Figure 3 A schematic diagram of the structure of a cooperative obstacle avoidance perception system for a UAV and an unmanned boat provided by the present invention; Figure 4 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention; Figure 5 A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0031] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0032] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0033] See also Figure 1 , Figure 1A scene diagram of a cooperative obstacle avoidance perception method for a UAV and an unmanned boat provided by the present invention. Figure 1 As shown, the terminal and the server are connected via a network, such as a wired or wireless network connection. The terminal may include but is not limited to portable terminals such as mobile phones and tablets installed with various network platform applications, as well as fixed terminals such as computers, query machines, and advertising machines. The server provides users with various business services, including service push servers, user recommendation servers, etc.

[0034] It should be noted that Figure 1 The scene diagram of a collaborative obstacle avoidance perception method for a UAV and an unmanned boat is only an example. The terminal, server, and application scenario described in the embodiment of the present invention are intended to more clearly illustrate the technical solution of the embodiment of the present invention, and do not generate limitations on the technical solution provided by the embodiment of the present invention. Ordinary technicians in this field can know that with the evolution of the system and the emergence of new business scenarios, the technical solution provided by the embodiment of the present invention is also applicable to similar technical problems.

[0035] Among them, the terminal can be used for: Obtain the first perception data of the drone; Obtaining the second perception data of the unmanned boat; Determining obstacle information based on the first perception data and the second perception data; An obstacle avoidance instruction is generated according to the obstacle information.

[0036] See also Figure 2 , provides a flow chart of a cooperative obstacle avoidance perception method of a UAV and an unmanned boat of the present invention, comprising the following steps: Step 201: Acquire first perception data of the drone.

[0037] The first perception data includes: image data and position data of any obstacle. Specifically, a perception system including sensors and devices is installed on the drone to obtain perception data of the surrounding environment. Data collection: Through the perception system, the drone collects perception data of the surrounding environment and the marine environment in real time. These data can be continuous data streams or discrete data points. Obstacle detection: The collected perception data is processed and analyzed, and obstacles in the surrounding environment are detected using corresponding algorithms and technologies. These obstacles can be other ships, buoys, reefs, shores, etc. Image data acquisition: If the perception system includes a camera or other visual sensors, the drone can obtain image data of the surrounding environment and the marine environment. These image data can provide detailed information such as the appearance, shape, size, etc. of the obstacle. Position data acquisition: In addition to the image data, the position data of the obstacle is also obtained by using the global positioning system (GPS) or other positioning technology, where the position data is the position coordinates of the center point of the obstacle in the geographic coordinate system. Data integration: The image data and the position data are integrated together to form a complete first perception data. Each obstacle is associated with its corresponding image data and position data.

[0038] Optionally, the sensor may include radar, laser scanner, infrared sensor and other equipment.

[0039] Step 202: Acquire second perception data of the unmanned boat.

[0040] The second perception data includes: image data and position data of any obstacle. Specifically, a perception system is installed on the unmanned boat, including a camera or other visual sensor, so as to capture image data of the surrounding environment and the marine environment. Image data acquisition: The image data around the unmanned boat is acquired in real time through a camera or other visual sensor. These image data can be a continuous video stream or a discrete image frame. Obstacle identification: The acquired image data is processed and analyzed, and obstacles in the image are identified using computer vision technology and deep learning algorithms. These obstacles can be other ships, buoys, reefs, shores, etc. Position data acquisition: In addition to image data, the position data of the obstacle is also acquired by using a global positioning system (GPS) or other positioning technology, where the position data is the position coordinates of the center point of the obstacle in the geographic coordinate system. Data integration: The image data and position data are integrated to form a complete second perception data. Each obstacle is associated with its corresponding image data and position data.

[0041] Step 203: Determine obstacle information based on the first perception data and the second perception data.

[0042] In one implementation, step 203 may specifically include the following steps: The first perception data and the second perception data are matched to determine the same obstacle.

[0043] Optionally, the step of “matching the first perception data and the second perception data to determine the same obstacle” may specifically include the following steps: An image matching algorithm is used to match the image data of any obstacle in the first perception data with the image data of any obstacle in the second perception data to determine similar obstacles.

[0044] Specifically, feature descriptors are extracted from the image data of each obstacle in the first perception data to construct a first feature descriptor sequence; feature descriptors are extracted from the image data of each obstacle in the second perception data to construct a second feature descriptor sequence. A feature matching algorithm is used to match the first feature descriptor sequence and the second feature descriptor sequence to find similar obstacles. For example, similar obstacles can be similar pairs {M1, N1} or similar groups {M1, N1, N2}, where M1 represents obstacles in the first perception data and N1, N2 represent obstacles in the second perception data.

[0045] Among them, algorithms such as SIFT (Scale-Inariant Feature Transform), SURF (Speeded UpRobust Features) or ORB (Oriented Fast and Rotated Brief) can be used to extract feature descriptors from image data, and the feature matching algorithm can be matching algorithms such as FLANN (Fast Library for Approximate NearestNeighbors) or RANSAC (RANSAC Random Sample Consensus), which are not specifically limited here.

[0046] The perceived distance is calculated according to the position data of the similar obstacles.

[0047] Specifically, since each obstacle in the first perception data is associated with its corresponding image data and position data, and each obstacle in the second perception data is associated with its corresponding image data and position data, for similar obstacles, their corresponding position data is obtained, and the perception distance is calculated based on the position data. If the similar obstacles are similar pairs {M1, N1}, the perception distance d0 between M1 and N1 is calculated.

[0048] Furthermore, if the similar obstacles are a similar group {M1, N1, N2}, the perceived distance d1 between M1 and N1 and the perceived distance d2 between M1 and N2 are calculated respectively. If d1>d2, d2 is used as the perceived distance calculated in the step “calculating the perceived distance according to the position data of the similar obstacles”, and M1 and N2 are correspondingly regarded as similar obstacles.

[0049] The perceived distance between similar obstacles may be calculated by Euclidean distance or other distance measurement methods, which are not specifically limited here.

[0050] Similar obstacles whose perception distance is less than a preset threshold are determined as the same obstacle; the same obstacle is composed of any obstacle in the first perception data and any obstacle in the second perception data.

[0051] Specifically, if the perception distance d0 of the similar pair {M1, N1} is greater than the preset threshold, it is considered that M1 and N1 do not belong to the same obstacle, and the perception data of the drone and the unmanned boat are abnormal; if the perception distance d0 of the similar pair {M1, N1} is less than the preset threshold, it is considered that M1 and N1 belong to the same obstacle.

[0052] It should be noted that the preset threshold can be set according to specific application scenarios and system requirements, and is not specifically limited here.

[0053] This provides more comprehensive and accurate obstacle information, thereby improving the obstacle avoidance capability and safety of unmanned boats or other equipment.

[0054] The image data of the same obstacle are fused to obtain target image data.

[0055] The image fusion algorithm may be used to fuse the image data of the same obstacle to obtain target image data, which represents the corrected image data of the obstacle.

[0056] Optionally, the step of "fusing the image data of the same obstacle to obtain the target image data" may specifically include the following steps: an image alignment step and an image fusion step. Specifically, since the first perception data and the second perception data come from different perspectives, the image data of the same obstacles M1 and N1 need to be aligned first. The image alignment can be achieved by an image registration algorithm, such as SIFT (Scale-Inariant Feature Transform), SURF (Speeded Up Robust Features) or RANSAC (RANSAC Random Sample Consensus), which is not specifically limited here.

[0057] Specifically, image fusion is to fuse the aligned image data at the pixel level, and fuse the pixel values ​​at the same position according to the selected fusion algorithm. The fusion algorithm can be a weighted average method (weighted average of image data of the same obstacle, and the weight can be assigned according to image quality, reliability or other factors), a maximum value method (pixel-by-pixel comparison of image data of the same obstacle, and the maximum value is selected as the pixel value of the target image), etc., which are not specifically limited here.

[0058] Therefore, by fusing the image data of the same obstacle, more complete and clearer target image data can be obtained, avoiding repeated recognition and misjudgment, and improving the accuracy of obstacle recognition.

[0059] The position data of the same obstacle are fused to obtain the target position data.

[0060] Specifically, the weighted average algorithm is used to fuse the position data of the same obstacle to obtain the target position data; that is, the position data of each same obstacle is weighted according to its weight; the weighted position data are averaged to obtain the target position data. The target position data represents the corrected position coordinates of the center point of the obstacle.

[0061] In order to fuse the location data of the same obstacle, it is necessary to first determine the weight of each location data, which can be assigned according to the reliability, accuracy or other factors of the corresponding perception data. For example, the weight can be determined based on the accuracy of the perception system of the drone and unmanned boat, the performance of the sensor, the data quality, etc.

[0062] In this way, errors and deviations between different position data are eliminated and the accuracy of obstacle location determination is improved. Accurate position data is very important for obstacle avoidance decisions and path planning.

[0063] Obstacle avoidance information is determined based on the target image data and the target position data.

[0064] Optionally, the step of “determining obstacle avoidance information based on the target image data and the target position data” may specifically include the following steps: Create a raster map.

[0065] Specifically, the environment where the drone and the unmanned boat are located is divided into a plurality of grid units, each of which is an area of ​​a fixed size. The grid size can be selected according to the application scenario and requirements, and can be a square or rectangle of a fixed size, which is not specifically limited here.

[0066] The image features in the target image data are extracted by an edge detection algorithm.

[0067] Among them, the Canny edge detection algorithm can be used to extract image features in the target image data; the Canny algorithm is a commonly used edge detection algorithm with good edge detection effect.

[0068] The grid map is updated according to the image features and the target position data, and the updated grid map is used as obstacle avoidance information.

[0069] Specifically, the target position data is converted into grid coordinates, the corresponding image features are projected onto the grid map, the grid cells where the obstacles are located are determined, and then the status of the corresponding grid cells in the grid map is updated. For example, a grid containing an obstacle is marked as an obstacle grid, and a grid without an obstacle is marked as a free grid.

[0070] This implementation enhances environmental perception, avoids collision risks, and provides reliable obstacle avoidance guidance for the device by creating a grid map, extracting image features, and updating the grid map.

[0071] Step 204: Generate an obstacle avoidance instruction according to the obstacle avoidance information.

[0072] Specifically, the obstacle avoidance action to be taken is determined according to the obstacle avoidance information, and the corresponding obstacle avoidance instruction is generated according to the determined obstacle avoidance action. The obstacle avoidance action can be generated according to predefined rules, path planning algorithms, machine learning models, etc.

[0073] Furthermore, after step 204 generates the obstacle avoidance instruction, the following steps are further included: Step 205: replan the navigation route of the unmanned boat according to the obstacle avoidance instruction.

[0074] Specifically, according to the generated obstacle avoidance instructions, the navigation route of the unmanned boat is replanned based on a classic path planning algorithm (such as the A algorithm) or a more advanced algorithm (such as the RRT algorithm).

[0075] Furthermore, the smoothness, safety and efficiency of the navigation route are considered, and the path is smoothed and adjusted to optimize the generated navigation route. The route optimization can be achieved by curve fitting, local path planning or other optimization techniques.

[0076] Furthermore, the optimized navigation route is applied to the control system of the unmanned boat so that it can navigate according to the route. According to the instructions of the navigation route, the speed, direction, heading and other parameters of the unmanned boat are adjusted to achieve obstacle avoidance and navigation.

[0077] Therefore, by acquiring and analyzing perception data from different sources, corresponding obstacle avoidance instructions are generated to improve the accuracy and reliability of the unmanned boat's obstacle avoidance and reduce the risk of collision with obstacles.

[0078] See also Figure 3 , Figure 3 A schematic diagram of the structure of a cooperative obstacle avoidance perception system for a UAV and an unmanned boat provided by the present invention.

[0079] like Figure 3 As shown, a cooperative obstacle avoidance perception system for a UAV and an unmanned boat proposed in an embodiment of the present invention includes: A first data acquisition module, used to acquire first perception data of the drone; A second data acquisition module is used to acquire second perception data of the unmanned boat; a data analysis module, configured to determine obstacle avoidance information based on the first perception data and the second perception data; The instruction generation module is used to generate an obstacle avoidance instruction according to the obstacle avoidance information.

[0080] Furthermore, the system also includes: The route planning module is used to re-plan the navigation route of the unmanned boat according to the obstacle avoidance instruction.

[0081] See also Figure 4 , Figure 4 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 4 As shown, an embodiment of the present invention provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, the following steps are implemented: Obtain the first perception data of the drone; Obtaining the second perception data of the unmanned boat; Determining obstacle avoidance information based on the first perception data and the second perception data; An obstacle avoidance instruction is generated according to the obstacle avoidance information.

[0082] See also Figure 5 , Figure 5 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 5 As shown, this embodiment provides a computer-readable storage medium 500, on which a computer program 411 is stored. When the computer program 411 is executed by a processor, the following steps are implemented: Obtain the first perception data of the drone; Obtaining the second perception data of the unmanned boat; Determining obstacle avoidance information based on the first perception data and the second perception data; An obstacle avoidance instruction is generated according to the obstacle avoidance information.

[0083] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0084] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0085] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0086] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0088] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0089] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A collaborative obstacle avoidance perception method for a UAV and an unmanned boat, characterized in that: The method comprises: Obtain the first perception data of the drone; Obtaining the second perception data of the unmanned boat; Determining obstacle avoidance information based on the first perception data and the second perception data; An obstacle avoidance instruction is generated according to the obstacle avoidance information.

2. The cooperative obstacle avoidance perception method of a UAV and an unmanned boat according to claim 1 is characterized in that: The first perception data includes: image data and position data of any obstacle.

3. The cooperative obstacle avoidance perception method of a UAV and an unmanned boat according to claim 2 is characterized in that: The second perception data includes: image data and position data of any obstacle.

4. The cooperative obstacle avoidance perception method of a UAV and an unmanned boat according to claim 3 is characterized in that: The determining obstacle avoidance information based on the first perception data and the second perception data includes: matching the first sensing data and the second sensing data to determine the same obstacle; fusing the image data of the same obstacle to obtain target image data; Fusion of the position data of the same obstacle to obtain target position data; Obstacle avoidance information is determined based on the target image data and the target position data.

5. The cooperative obstacle avoidance perception method of a UAV and an unmanned boat according to claim 4 is characterized in that: The matching the first perception data and the second perception data to determine the same obstacle includes: Using an image matching algorithm, matching the image data of any obstacle in the first perception data with the image data of any obstacle in the second perception data to determine similar obstacles; Calculating the perceived distance according to the position data of the similar obstacles; Similar obstacles whose perception distance is less than a preset threshold are determined as the same obstacle; the same obstacle is composed of any obstacle in the first perception data and any obstacle in the second perception data.

6. The cooperative obstacle avoidance perception method of a UAV and an unmanned boat according to claim 4 is characterized in that: The fusing the image data of the same obstacle to obtain the target image data includes: An image fusion algorithm is used to fuse the image data of the same obstacle to obtain target image data.

7. The cooperative obstacle avoidance perception method of a UAV and an unmanned boat according to claim 4 is characterized in that: The fusing the position data of the same obstacle to obtain the target position data includes: The weighted average algorithm is used to fuse the position data of the same obstacle to obtain the target position data.

8. The cooperative obstacle avoidance perception method for a UAV and an unmanned boat according to claim 4 is characterized in that: The determining obstacle avoidance information based on the target image data and the target position data includes: Create raster maps; Extracting image features from the target image data by using an edge detection algorithm; The grid map is updated according to the image features and the target position data, and the updated grid map is used as obstacle avoidance information.

9. The cooperative obstacle avoidance perception method of a UAV and an unmanned boat according to claim 8, characterized in that: After the obstacle avoidance instruction is generated, the method further includes: According to the obstacle avoidance instruction, the navigation route of the unmanned boat is replanned.

10. A cooperative obstacle avoidance perception system for unmanned aerial vehicles and unmanned boats, characterized in that: The system comprises: A first data acquisition module, used to acquire first perception data of the drone; A second data acquisition module is used to acquire second perception data of the unmanned boat; a data analysis module, configured to determine obstacle avoidance information based on the first perception data and the second perception data; The instruction generation module is used to generate an obstacle avoidance instruction according to the obstacle avoidance information.

Images