Unmanned vehicle control method and device
By combining laser ranging and Beidou differential positioning, and image recognition technology, the problem of positioning accuracy of drones and unmanned ships in rainy and foggy weather is solved, and high-precision docking of unmanned vehicles under different weather conditions is achieved. control.
Patent Information
- Application Number
- CN202411185879.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-12-06
AI Technical Summary
During the autonomous return process, drones and unmanned ships need to land at smart airports and smart docks with high accuracy, but face the problems of high position accuracy requirements and weather changes affecting positioning accuracy, especially in rainy and foggy weather, it is difficult to ensure accurate docking.
Using a combination of laser ranging and Beidou differential positioning, laser ranging is used to determine the target position when meeting preset weather conditions, and when not meeting the conditions, the target position is determined through image recognition, and the unmanned load is controlled based on the corrected driving route. With docking.
It improves the positioning accuracy and control accuracy of unmanned vehicles in different weather environments, avoids the impact of the weather environment on positioning, and ensures the reliability of safe return and charging.
Smart Images

Figure CN119088010A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of automated control technology, and in particular to a control method and device for an unmanned vehicle. Background Art
[0002] After completing their missions, drones and unmanned ships / boats need to autonomously return to smart airports and smart docks for charging. The process of controlling the landing and return of unmanned vehicles requires high positioning accuracy, and small errors may cause collisions, damage, or safety risks to the drones. In addition, the weather at sea is changeable, especially in rainy and foggy weather, which will affect the positioning accuracy of unmanned vehicles and thus affect the accuracy of their control.
[0003] Therefore, how to ensure that it can accurately land at the smart airport and enter the smart dock in the state of autonomous return is a technical difficulty that needs to be solved. Summary of the invention
[0004] This application proposes a control method and device for an unmanned vehicle. The specific scheme is as follows:
[0005] In one aspect, an embodiment of the present application provides a method for controlling an unmanned vehicle, including:
[0006] During the process of the target object returning based on the driving route, it is determined in real time whether the target object is within the laser ranging range of the stop point;
[0007] When the target object is within the laser ranging range of the stop point and the weather environment at the stop point meets the preset conditions, the target position of the target object is determined by using the laser ranging method based on the coordinates of the stop point;
[0008] When the target object is within the laser ranging range of the stop point and the weather environment at the stop point does not meet the preset conditions, multiple images of the target object are collected to determine the target position of the target object based on the reference position corresponding to each image;
[0009] The driving route is corrected based on the target position to control the target object to stop at the stop point based on the corrected driving route.
[0010] In a possible implementation of an embodiment of an aspect of the present application, a target position of a target object is determined by using a laser ranging method based on the coordinates of a stop point, including:
[0011] The target position of the target object is determined based on the first coordinate determined by laser ranging and the second coordinate determined by Beidou differential positioning.
[0012] In a possible implementation of an embodiment of an aspect of the present application, determining a target position of a target object based on a reference position corresponding to each image includes:
[0013] Recognize each image separately and determine the reference position of the target object corresponding to each image;
[0014] Each reference position is fused to determine the target position of the target object.
[0015] In a possible implementation of an embodiment of one aspect of the present application, it also includes:
[0016] Obtain the third coordinate of the target object based on Beidou differential positioning;
[0017] The driving route is determined based on the third coordinate and the stop point planning, so as to control the return of the target object based on the driving route.
[0018] Another aspect of the present application provides a control device for an unmanned vehicle, including:
[0019] A positioning module, used to determine in real time whether the target object is within the laser ranging range of the stop point during the process of the target object returning based on the driving route;
[0020] A first determination module is used to determine the target position of the target object by using a laser ranging method based on the coordinates of the stop point when the target object is within the laser ranging range of the stop point and the weather environment of the stop point meets the preset conditions;
[0021] A second determination module is used to collect multiple images of the target object when the target object is within the laser ranging range of the stop point and the weather environment of the stop point does not meet the preset conditions, so as to determine the target position of the target object based on the reference position corresponding to each image;
[0022] The control module is used to correct the driving route based on the target position, so as to control the target object to stop at the stop point based on the corrected driving route.
[0023] In a possible implementation of an embodiment of an aspect of the present application, the first determining module is configured to:
[0024] The target position of the target object is determined based on the first coordinate determined by laser ranging and the second coordinate determined by Beidou differential positioning.
[0025] In a possible implementation of an embodiment of an aspect of the present application, the second determining module is configured to:
[0026] Recognize each image separately and determine the reference position of the target object corresponding to each image;
[0027] Each reference position is fused to determine the target position of the target object.
[0028] In a possible implementation of an embodiment of the first aspect of the present application, the control module is further configured to:
[0029] Obtain the third coordinate of the target object based on Beidou differential positioning;
[0030] The driving route is determined based on the third coordinate and the stop point planning, so as to control the return of the target object based on the driving route.
[0031] Another aspect of the present application provides a computer device, including a processor and a memory;
[0032] The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the method as described in the above embodiment.
[0033] Another aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the program implements the method of the above embodiment when executed by a processor.
[0034] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:
[0036] Figure 1 A schematic diagram of a flow chart of a control method for an unmanned vehicle provided in an embodiment of the present application;
[0037] Figure 2 A schematic flow chart of another unmanned vehicle control method provided in an embodiment of the present application;
[0038] Figure 3 A schematic diagram of the structure of a control device for an unmanned vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION
[0039] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.
[0040] The control method of the unmanned vehicle according to an embodiment of the present application is described below with reference to the accompanying drawings.
[0041] Figure 1 A flowchart of a control method for an unmanned vehicle provided in an embodiment of the present application.
[0042] The control method of the unmanned vehicle of the embodiment of the present application is executed by the control device of the unmanned vehicle (hereinafter referred to as the control device) provided by the embodiment of the present application. The control method of the unmanned vehicle can be configured in a computer device to improve the accuracy of the control of the unmanned vehicle.
[0043] like Figure 1 As shown, the control method of the unmanned vehicle includes:
[0044] Step 101 , during the process of the target object returning based on the driving route, it is determined in real time whether the target object is within the laser ranging range of the stop point.
[0045] The target objects are unmanned vehicles (also known as unmanned vehicles) such as drones, unmanned ships, and unmanned boats that need to go to the docking point. Laser ranging tools are installed at the docking point.
[0046] In the present application, the driving route can be pre-planned and set in the system. Afterwards, the control device controls the movement of the target object based on the driving route until it stops at the stop point.
[0047] During the movement of the target object, the current position of the target object can be obtained in real time through Beidou differential positioning technology. After that, the distance from the current position of the target object to the stop point is determined. When the distance is less than the preset laser ranging distance of the stop point, it can be determined that the target object is within the laser ranging range of the stop point.
[0048] Step 102, when the target object is within the laser ranging range of the stop point and the weather environment of the stop point meets the preset conditions, the target position of the target object is determined by using the laser ranging method based on the coordinates of the stop point.
[0049] Among them, the preset condition may be that the current rainfall is less than a preset threshold and / or the visibility is greater than a preset threshold. In rainy and foggy weather, water droplets suspended in the air will scatter the laser, and part of the laser energy will be scattered instead of being directly reflected back to the sensor, resulting in a weakening of the received echo signal intensity and inaccurate laser ranging. Therefore, when the target object is within the laser ranging range of the stop point and the weather environment of the stop point meets the preset conditions, the effect of rainy and foggy weather on the laser ranging is small, so the target position of the target object can be determined by the laser ranging method based on the coordinates of the stop point. This improves the reliability and accuracy of determining the target position.
[0050] In this application, the first coordinate of the target object can be measured by laser ranging method based on the coordinates of the stop point, and the first coordinate can be directly determined as the target position. Alternatively, the target position of the target object can be determined based on the first coordinate determined by laser ranging and the second coordinate determined by Beidou differential positioning. The method is as follows:
[0051] Lat=ω1Lat1+ω2Lat2
[0052] Lon=ω1Lon1+ω2Lon2
[0053] Elev=ω1Elev1+ω2Elev2
[0054] Among them, Lat1, Lon1, and Elev1 are the longitude, latitude, and elevation of the first coordinate respectively; Lat2, Lon2, and Elev2 are the longitude, latitude, and elevation of the second coordinate respectively; Lat, Lon, and Elev are the longitude, latitude, and elevation (i.e., the target position) after the fusion of the first and second coordinates respectively; ω1 and ω2 are the weights of the first and second coordinates respectively, and the weights are derived from a large amount of test data. 1+ ω2=1.
[0055] Optionally, the process of determining the first coordinate of the target object based on laser ranging is as follows:
[0056] The distance d, azimuth angle information θ and pitch angle θ from the target object are obtained through laser ranging. h , based on the latitude and longitude coordinates of the stop point (Lat A ,Lon A ) and Elev A Calculate the first coordinate (Lat1, Lon1) and elevation Elev1 of the target object.
[0057]
[0058] Elev1=Elev A +sin(θ h )
[0059] Where R is the radius of the Earth (approximately 6371 kilometers).
[0060] Step 103, when the target object is within the laser ranging range of the stop point and the weather environment of the stop point does not meet the preset conditions, multiple images of the target object are collected to determine the target position of the target object based on the reference position corresponding to each image.
[0061] The weather environment at the stop point does not meet the preset conditions, that is, the current rainfall is greater than a preset threshold and / or the visibility is less than a preset threshold.
[0062] In this application, when the target object is within the laser ranging range of the stop point and the weather environment of the stop point does not meet the preset conditions, rainy and foggy weather has a greater impact on the laser ranging, but does not affect the monitoring of the target object through visual technology. Therefore, according to the second coordinate of the target object determined based on the current Beidou differential positioning, the image monitoring device is controlled to rotate to capture multiple images containing the target object, and the target position of the target object is determined based on the reference position corresponding to each image. Thereby improving the reliability and accuracy of determining the target position.
[0063] In the present application, a recognition model can be pre-trained, and then each image and the angle at which the image monitoring device rotates when taking each image are sent to the recognition model, and the recognition model can output the reference position corresponding to each image. After determining the reference position corresponding to each image, the reference position can be fitted to determine the trajectory type of the motion trajectory of the target object. Among them, the trajectory type includes simple harmonic motion, non-simple harmonic motion, etc. In the case where the trajectory type of the motion trajectory is non-simple harmonic motion, it means that the direction of the airflow is fixed, such as linear motion or arbitrary curve motion. At this time, the reference position corresponding to the last acquired image can be determined as the target position. In the case where the trajectory type of the motion trajectory is simple harmonic motion, each reference position can be fused to determine the target position of the target object. For example, the average of the reference positions of the last acquired multiple images is determined as the target position.
[0064] Optionally, the reference position may be fused with a second coordinate determined based on Beidou differential positioning to determine the target position of the target object.
[0065] The process of training and acquiring the recognition model is as follows: a training data set is obtained, wherein the training data set contains multiple images acquired by monitoring the target object, the rotation angle of the monitoring device when taking each image, and the annotated coordinates corresponding to each image. Afterwards, each image and its corresponding rotation angle are input into the initial recognition model to obtain the predicted position output by the initial recognition model. Then, according to the difference between the predicted position and its corresponding annotated coordinates, a loss value is determined to correct the initial prediction model according to the loss value until the final recognition model is obtained.
[0066] Step 104, correcting the driving route based on the target position, so as to control the target object to stop at the stop point based on the corrected driving route.
[0067] In the present application, after the driving route is corrected based on the target position, the posture and direction of the target object are adjusted based on the corrected driving route, and the target object is controlled to stop at the stop point.
[0068] In addition, since the target object is constantly moving, a fixed time interval may be set or the correction process of step 102 to step 103 may be cyclically executed when the target object reaches a specific distance, so as to ensure the accuracy of the position of the target object.
[0069] In the present application, in the process of the target object returning based on the driving route, it is determined in real time whether the target object is within the laser ranging range of the stop point. After that, when the target object is within the laser ranging range of the stop point and the weather environment of the stop point meets the preset conditions, the target position of the target object is determined by the laser ranging method based on the coordinates of the stop point. When the target object is within the laser ranging range of the stop point and the weather environment of the stop point does not meet the preset conditions, multiple images of the target object are collected to determine the target position of the target object based on the reference position corresponding to each image. Then, the driving route is corrected based on the target position to control the target object to stop at the stop point based on the corrected driving route. Thus, under different weather environment conditions, different positioning methods are used to determine the target position of the target object, avoiding the influence of the weather environment on the positioning accuracy, thereby improving the positioning accuracy, and further improving the accuracy of unmanned vehicle control.
[0070] like Figure 2 As shown, the control method of the unmanned vehicle includes:
[0071] Step 201, obtaining the third coordinate of the target object operation based on Beidou differential positioning.
[0072] In this application, when operating on a target object, when a situation arises where it is necessary to return home (for example, resources (such as electricity) are about to run out, the marine environment does not meet operating conditions, etc.), the third coordinate of the target object can be acquired based on Beidou differential positioning.
[0073] Step 202, determining a driving route based on the third coordinate and the stop point planning, so as to control the target object to return based on the driving route.
[0074] In this application, any path planning algorithm can be used to determine the driving route based on the third coordinate and the stop point planning. In addition, ocean current data (such as offshore wind speed, wind direction, wave height, water flow direction and speed, etc.) can also be obtained.
[0075] Based on the offshore wind speed, wind direction, wave height, water flow direction and speed, the return route of the unmanned ship is generated to avoid the influence of adverse weather areas. In addition, it is also possible to consider introducing obstacle avoidance logic to avoid conflicts with other ships and obstacles. The objective function is defined in combination with ocean current data, which is a cost function, in which unfavorable conditions have a higher weight. Then, a search algorithm is used to find the driving path that minimizes the cost function. The automatic identification system (AIS) can also be used to track the position of other ships to avoid collisions with other ships. Sensors on the ship can also be used to detect unknown obstacles. Once an obstacle is detected, preset rules or more complex machine learning models are used to decide how to avoid the obstacle. This ensures the safety of the movement of the target object.
[0076] Step 203 , during the process of the target object returning based on the driving route, it is determined in real time whether the target object is within the laser ranging range of the stop point.
[0077] Step 204 , when the target object is within the laser ranging range of the stop point and the weather environment of the stop point meets the preset conditions, the target position of the target object is determined by using the laser ranging method based on the coordinates of the stop point.
[0078] Step 205 , when the target object is within the laser ranging range of the stop point and the weather environment of the stop point does not meet the preset conditions, multiple images of the target object are collected to determine the target position of the target object based on the reference position corresponding to each image.
[0079] Step 206, correcting the driving route based on the target position, so as to control the target object to stop at the stop point based on the corrected driving route.
[0080] In the present application, the specific implementation process of steps 203 to 206 can be found in the detailed description of any embodiment of the present application and will not be repeated here.
[0081] In the present application, the third coordinate of the target object operation is obtained based on Beidou differential positioning, and the driving route is determined based on the third coordinate and the stop point planning, so as to control the target object to return based on the driving route. Afterwards, in the process of the target object returning based on the driving route, it is determined in real time whether the target object is within the laser ranging range of the stop point. When the target object is within the laser ranging range of the stop point and the weather environment of the stop point meets the preset conditions, the target position of the target object is determined based on the coordinates of the stop point by using the laser ranging method, and when the target object is within the laser ranging range of the stop point and the weather environment of the stop point does not meet the preset conditions, multiple images of the target object are collected to determine the target position of the target object based on the reference position corresponding to each image, and then the driving route is corrected based on the target position to control the target object to stop at the stop point based on the corrected driving route. Thus, under different weather environment conditions, different positioning methods are used to determine the target position of the target object, avoiding the influence of the weather environment on the positioning accuracy, thereby improving the positioning accuracy, and further improving the accuracy of the unmanned vehicle control.
[0082] In order to implement the above embodiment, the embodiment of the present application also proposes a control device for an unmanned vehicle. Figure 3 A schematic diagram of the structure of a control device for an unmanned vehicle provided in an embodiment of the present application.
[0083] like Figure 3 As shown, the control device 300 of the unmanned vehicle includes:
[0084] The positioning module 310 is used to determine in real time whether the target object is within the laser ranging range of the stop point during the process of the target object returning based on the driving route;
[0085] A first determination module 320 is used to determine the target position of the target object by using a laser ranging method based on the coordinates of the stop point when the target object is within the laser ranging range of the stop point and the weather environment of the stop point meets the preset conditions;
[0086] A second determination module 330 is used to collect multiple images of the target object to determine the target position of the target object based on a reference position corresponding to each image when the target object is within the laser ranging range of the stop point and the weather environment of the stop point does not meet the preset conditions;
[0087] The control module 340 is used to correct the driving route based on the target position, so as to control the target object to stop at the stop point based on the corrected driving route.
[0088] In a possible implementation of another aspect of the present application, the first determining module 320 is configured to:
[0089] The target position of the target object is determined based on the first coordinate determined by laser ranging and the second coordinate determined by Beidou differential positioning.
[0090] In a possible implementation of another aspect of the present application, the second determining module 330 is configured to:
[0091] Recognize each image separately and determine the reference position of the target object corresponding to each image;
[0092] Each reference position is fused to determine the target position of the target object.
[0093] In a possible implementation of another aspect of the present application, the control module 340 is further configured to:
[0094] Obtain the third coordinate of the target object based on Beidou differential positioning;
[0095] The driving route is determined based on the third coordinate and the stop point planning, so as to control the return of the target object based on the driving route.
[0096] It should be noted that the above explanation of the embodiment of the control method for an unmanned vehicle is also applicable to the control device for the unmanned vehicle of this embodiment, so it will not be repeated here.
[0097] In the present application, in the process of the target object returning based on the driving route, it is determined in real time whether the target object is within the laser ranging range of the stop point. After that, when the target object is within the laser ranging range of the stop point and the weather environment of the stop point meets the preset conditions, the target position of the target object is determined by the laser ranging method based on the coordinates of the stop point. When the target object is within the laser ranging range of the stop point and the weather environment of the stop point does not meet the preset conditions, multiple images of the target object are collected to determine the target position of the target object based on the reference position corresponding to each image. Then, the driving route is corrected based on the target position to control the target object to stop at the stop point based on the corrected driving route. Thus, under different weather environment conditions, different positioning methods are used to determine the target position of the target object, avoiding the influence of the weather environment on the positioning accuracy, thereby improving the positioning accuracy, and further improving the accuracy of unmanned vehicle control.
[0098] In order to implement the above embodiment, the embodiment of the present application also proposes a computer device, including a processor and a memory;
[0099] The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the control method of the unmanned vehicle as described in the above embodiment.
[0100] In order to implement the above embodiments, the embodiments of the present application further propose a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the control method of the unmanned vehicle as in the above embodiments is implemented.
[0101] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.
Claims
1. A control method for an unmanned vehicle, characterized in that: include: During the process of the target object returning based on the driving route, determining in real time whether the target object is within the laser ranging range of the stop point; When the target object is within the laser ranging range of the stop point and the weather environment of the stop point meets the preset conditions, the target position of the target object is determined by using the laser ranging method based on the coordinates of the stop point; When the target object is within the laser ranging range of the stop point and the weather environment of the stop point does not meet the preset condition, collecting multiple images of the target object to determine the target position of the target object based on a reference position corresponding to each of the images; The driving route is corrected based on the target position, so as to control the target object to stop at the stop point based on the corrected driving route.
2. The method according to claim 1, characterized in that The method of determining the target position of the target object by using a laser ranging method based on the coordinates of the stop point includes: The target position of the target object is determined based on the first coordinate determined by laser ranging and the second coordinate determined by Beidou differential positioning.
3. The method according to claim 1, characterized in that The determining the target position of the target object based on the reference position corresponding to each of the images includes: Recognize each of the images respectively to determine the reference position of the target object corresponding to each of the images; Each of the reference positions is fused to determine the target position of the target object.
4. The method according to claim 1, characterized in that Also includes: Acquire the third coordinate of the target object operation based on Beidou differential positioning; The driving route is determined based on the third coordinate and the stop point planning, so as to control the target object to return based on the driving route.
5. A control device for an unmanned vehicle, characterized in that: include: A positioning module, used to determine in real time whether the target object is within the laser ranging range of the stop point during the process of the target object returning based on the driving route; A first determination module is used to determine the target position of the target object by using a laser ranging method based on the coordinates of the stop point when the target object is within the laser ranging range of the stop point and the weather environment of the stop point meets the preset conditions; A second determination module is used to collect multiple images of the target object when the target object is within the laser ranging range of the stop point and the weather environment of the stop point does not meet the preset condition, so as to determine the target position of the target object based on the reference position corresponding to each of the images; A control module is used to correct the driving route based on the target position, so as to control the target object to stop at the stop point based on the corrected driving route.
6. The device according to claim 5, characterized in that The first determining module is used to: The target position of the target object is determined based on the first coordinate determined by laser ranging and the second coordinate determined by Beidou differential positioning.
7. The device according to claim 5, characterized in that The second determining module is used to: Recognize each of the images respectively to determine the reference position of the target object corresponding to each of the images; Each of the reference positions is fused to determine the target position of the target object.
8. The device according to claim 5, characterized in that The control module is also used for: Acquire the third coordinate of the target object operation based on Beidou differential positioning; The driving route is determined based on the third coordinate and the stop point planning, so as to control the target object to return based on the driving route.
9. An electronic device, characterized in that: include: A processor, and a memory interacting with the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 4.
10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 4 when being executed by a processor.
