Obstacle avoidance method and device, computer equipment and storage medium

Abstract

The invention discloses an obstacle avoidance method and device, computer equipment and a storage medium, and aims to solve the problem that reliable data is difficult to provide for obstacle avoidance of medium-and-high-speed unmanned ships when obstacle avoidance is carried out on an unmanned ship only through data acquired by load equipment arranged on the unmanned ship in the prior art. Therefore, the invention provides a novel obstacle avoidance method for solving the problem of poor accuracy and reliability of position and direction identification of the obstacle. According to the method, navigation data of target equipment and environment object data of each object in the surrounding environment of the target equipment are monitored through a target map obtained by fusing an electronic chart and an image collected by load equipment arranged on the unmanned ship; the problems of short identification distance, low response speed, relatively limited sensing information and the like caused by independent use of the load equipment and the electronic chart are solved through superposition of the load equipment and the electronic chart, reliable data support is provided for obstacle avoidance of the target equipment, and the navigation safety of the target equipment is improved.

Description

Technical Field

[0001] The present disclosure generally relates to the field of automated control, and in particular to an obstacle avoidance method, device, computer equipment, and storage medium. Background Art

[0002] Unmanned boats have the ability to navigate autonomously, detect and inspect, and perform dynamic tasks. They can provide strong assistance for large-scale, high-precision target monitoring at sea, and have the advantages of wide monitoring range, low cost, and no risk of casualties.

[0003] The core of autonomous control of unmanned boats is obstacle avoidance, that is, collecting the surrounding environment information of the unmanned boat based on the navigation radar, infrared thermal imager, millimeter wave / lidar, visual sensor and other equipment that perceive the target, so as to identify the location and direction of obstacles based on the surrounding environment information and avoid obstacles in real time. However, for the current environmental information collection equipment, on the one hand, there are problems of short recognition distance and slow response speed, and on the other hand, there is a problem of limited perception information, so it is difficult to provide reliable data for medium and high-speed unmanned boats to avoid obstacles, resulting in poor accuracy and reliability in identifying the location and direction of obstacles. Summary of the invention

[0004] In view of the above-mentioned defects or deficiencies in the prior art, it is desirable to provide an obstacle avoidance method, apparatus, computer equipment and storage medium with high accuracy and reliability in identifying the position and direction of obstacles.

[0005] A first aspect provides an obstacle avoidance method, the method comprising: Acquire first navigation data and environmental object data of the target device at the current moment based on a target map, wherein the target map is a map obtained by fusing an electronic nautical chart and an image collected by a radar on the target device; Performing collision risk assessment based on the first navigation data and the environmental object data by using a minimum distance method and a time arrival method to obtain a first result; If the first result is that there is a collision risk, an obstacle avoidance strategy is determined based on the first navigation data, the environmental object data and the wall collision rule library, and the navigation of the target device is controlled according to the obstacle avoidance strategy.

[0006] The obstacle avoidance method provided in the present application takes into account that the existing obstacle avoidance for unmanned boats is only performed through data collected by payload equipment installed on the unmanned boats, and it is difficult to provide reliable data for obstacle avoidance for medium and high-speed unmanned boats, resulting in poor accuracy and reliability in identifying the position and direction of obstacles. Therefore, the present application provides a new obstacle avoidance method. The method monitors the navigation data of the target device and the environmental object data of each object in the surrounding environment of the target device through a target map obtained by fusing an electronic nautical chart and images collected by a payload equipment installed on the unmanned boat. The superposition of the two makes up for the problems of short recognition distance, slow response speed, and limited perception information when the payload equipment and the electronic nautical chart are used separately, providing reliable data support for obstacle avoidance of the target device and improving the safety of navigation of the target device.

[0007] A second aspect provides an obstacle avoidance device, the device comprising: An acquisition module, used for acquiring first navigation data and environmental object data of a target device at a current moment based on a target map, wherein the target map is a map obtained by fusing an electronic nautical chart and an image collected by a radar on the target device; An evaluation module, configured to perform a collision risk evaluation based on the first navigation data and the environmental object data by using a minimum distance method and a time arrival method to obtain a first result; A determination module is used to determine an obstacle avoidance strategy based on the first navigation data, the environmental object data and the wall collision rule library when the first result is that there is a collision risk, and control the navigation of the target device according to the obstacle avoidance strategy.

[0008] A third aspect provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the method of the first aspect when executing the computer program.

[0009] A fourth aspect provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method of the first aspect when executed by a processor.

[0010] A fifth aspect provides a computer program product, comprising a computer program, which implements the method of the first aspect when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 An application scenario diagram of an obstacle avoidance method provided in this application; Figure 2 A flowchart of the steps of an obstacle avoidance method provided in this application; Figure 3 A flowchart of the steps of an obstacle avoidance method provided in this application; Figure 4 A flowchart of the steps of an obstacle avoidance method provided in this application; Figure 5 A flowchart of the steps of an obstacle avoidance method provided in this application; Figure 6 A flowchart of the steps of an obstacle avoidance method provided in this application; Figure 7 A flowchart of the steps of an obstacle avoidance method provided in this application; Figure 8 A flowchart of the steps of an obstacle avoidance method provided in this application; Fig. 9 A flowchart of the steps of an obstacle avoidance method provided in this application; Fig.10 A structural block diagram of an obstacle avoidance device provided in this application; Fig.11 A schematic diagram of the structure of a computer system of a target device provided in this application. DETAILED DESCRIPTION

[0012] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0013] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0014] Please refer to Figure 1 , Figure 1 This is an application scenario diagram of an obstacle avoidance method provided in the present application, and the application scenario diagram includes a target device 100 and a payload device 101 arranged on the target device. The target device 100 is, for example, an unmanned boat, and the payload device 101 is, for example, various sensor devices, radars, locators, depth sounders, etc. arranged on the unmanned boat. The target device 100 and the payload device 101 can communicate with each other. The target device 100 is provided with an electronic nautical chart and a map obtained by fusing the images collected by the payload device 101. During the driving process, the target device 100 can obtain its own navigation data and environmental object data of the surrounding environment in real time through the target map, and avoid obstacles based on the navigation data and environmental object data to ensure the safety of navigation.

[0015] Combine the following Figure 2The obstacle avoidance method provided in this application is exemplarily described. Figure 2 A flowchart of the steps of an obstacle avoidance method provided in this application, in which the method is applied to Figure 1 The method is described by taking the target device in as an example. The method includes the following steps: Step S20, obtaining navigation data and environmental object data of the target device based on a target map, wherein the target map is a map obtained by fusing an electronic nautical chart and an image collected by a payload device on the target device; Among them, electronic nautical charts refer to vector electronic nautical charts produced by national hydrographic agencies in accordance with the Transfer Standard for Digital Hydrographic Data (No. S-57) promulgated by the International Hydrographic Organization (IHO). Vector electronic nautical charts are databases that classify and store digital nautical chart information, and users can selectively query, display and use data. Electronic nautical charts are stored in the memory address of the target device.

[0016] The payload device on the target device is, for example, a radar installed on the target device. The radar emits electromagnetic waves around the target device to illuminate the environmental objects around the target device and receive their echoes, thereby obtaining information such as the distance from the environmental objects in the environment around the target device to the electromagnetic wave emission point, the distance change rate (radial velocity), azimuth, and altitude, so as to obtain data on the environmental objects around the target device and generate corresponding images. This is equivalent to a distribution map of each environmental object in the environment around the target device.

[0017] The target map is a map obtained by fusing the electronic chart and the images collected by the payload on the target device. The electronic chart can obtain global static information about the target device and its surroundings and information about moving vessels; the payload can capture images of the surrounding waters in real time, including information about local obstacles such as moving vessels, buoys, and islands. The fusion of the two can build a more comprehensive map. Compared with relying on a single data source, it can more accurately perceive the navigation environment around the target device and provide reliable data support for the subsequent determination of obstacle avoidance strategies.

[0018] The navigation data of the target device includes, for example, the position data, speed, heading angle, etc. of the target device. The environmental object data includes, for example, the position data, speed, heading angle, position data of buoys, position data and speed of obstacles in the environment around the target device.

[0019] In an optional embodiment, if Figure 3 As shown, Figure 3The steps for obtaining the target map provided for an exemplary embodiment of the present application are as follows: Step S301, collecting obstacle data within a preset range at different times through the payload device on the target device; The load device on the target device has a certain collection range, so the load device can only collect obstacle data within the preset range. The load device can collect obstacle data within the preset range in real time while the target device is constantly driving, so that collection results at different times can be obtained.

[0020] Obstacle data includes, for example, the distance and azimuth between the mobile ships, buoys, islands and the payload equipment within the detection range of the payload equipment.

[0021] Step S302, generating a plurality of first images based on obstacle data; The obstacle data is used to describe the position, posture, and relative position relationship of the obstacle with the target device. Therefore, after the obstacle data at different times are collected by the payload device, each obstacle can be labeled according to the obstacle data to obtain multiple first images. Each first image can carry a timestamp to facilitate subsequent sorting according to time to obtain a continuous and complete target map.

[0022] In an optional embodiment, if Figure 4 As shown, Figure 4 An optional method embodiment of generating multiple first images based on obstacle data provided by an exemplary embodiment of the present application includes the following steps: Step S401, performing coordinate system conversion on the polar coordinate data in the obstacle data to obtain a point set of each obstacle in a rectangular coordinate system; Step S402, determining the pixel brightness value of each obstacle in the image according to the payload equipment echo intensity data in the obstacle data; Step S403: Generate a plurality of first images according to the pixel brightness values ​​of each obstacle in the image at different times and the point sets of each obstacle in the rectangular coordinate system.

[0023] Among them, since the electronic chart uses a rectangular coordinate system to represent the location information of each chart element, and the radar uses polar coordinates to represent the location information of each obstacle. In order to facilitate the better fusion of the first image and the second image, we can first convert the data collected by the radar in the form of polar coordinates into a point set of each obstacle in the rectangular coordinate system, that is, to represent the polar coordinates by rectangular coordinates.

[0024] Exemplarily, the conversion formula is:

[0025] Among them, r is the distance data collected by the radar, is the azimuth data collected by the radar. x and y are the horizontal and vertical coordinates of the obstacle after conversion.

[0026] The data collected by the radar and represented in polar coordinate form are converted into rectangular coordinates corresponding to multiple obstacles after the above conversion.

[0027] Then the application can determine the size and resolution of the first image to be constructed based on the maximum detection distance and angular scanning range of the radar. The maximum detection distance of the radar determines the width and height of the first image. For example, if the maximum detection distance is 1000 meters, it corresponds to 1 meter / pixel, so the size of the image will be 1000x1000 pixels. The radar usually scans within a 360-degree range, so the width of the first image can be set to 360 pixels (one pixel per degree). The center point of the first image is usually set to the origin (0, 0), corresponding to the position of the radar, which is convenient for coordinate mapping later.

[0028] Since each obstacle corresponds to a pixel in the first image, the brightness value of the pixel can be set according to the radar echo intensity. The radar echo intensity is represented by a numerical value, a grayscale value ranging from 0 to 255.

[0029] After the data required for the first image is determined in the above manner, multiple first images can be generated according to the pixel brightness values ​​of each obstacle in the image at different times and the point sets of each obstacle in the rectangular coordinate system.

[0030] Step S303, reading the chart element information and attribute information of each chart element at different times from the electronic chart according to the time when the load equipment collects obstacle data; Among them, since it is necessary to subsequently fuse the first image generated by the obstacle data collected by the payload equipment and the second image generated by the electronic chart, it is necessary to collect the obstacle data and obtain the corresponding data from the electronic chart at the same time as much as possible. This can provide a basis for subsequent fusion and avoid the situation where the fusion of irrelevant images leads to inaccurate target maps.

[0031] Therefore, the present application can be to read the chart element information and attribute information of each chart element at the corresponding time from the electronic chart at each time when the payload device collects obstacle data, so as to generate a second image based on the above information. The first image is an image of a dynamic object, and the second image is an image of a static object. The fusion of the two can provide more comprehensive environmental information for the target device, so as to more accurately obtain the navigation data and environmental object data of the target device, and realize accurate obstacle avoidance.

[0032] For example, each chart element in an electronic chart includes, for example, a sounding point, a coastline, a depth contour, an obstacle, etc.; the chart element information of each chart element includes, for example, the coordinates of the sounding point, the coordinates of the coastline, the coordinates of the depth contour, the geometric shape of the obstacle, etc.; the attribute information of each chart element includes, for example, the sounding value, the coastline type, the depth value of the depth contour, the obstacle type, etc. These data can only be directly obtained through the electronic chart, and will not be elaborated here.

[0033] In yet another optional embodiment, Figure 5 As shown, Figure 5 An optional method embodiment of collecting obstacle data provided by an exemplary embodiment of the present application is to read chart element information and attribute information of each chart element from an electronic chart, and the method embodiment includes the following steps: Step S501, traversing the data files of the electronic nautical chart, parsing the header information of each data file to obtain different types of nautical chart elements; Step S502, determining the geometric shape information corresponding to each nautical chart element according to the element record in each data file; Step S503, parsing the attribute fields of the element records in each data file to obtain the attribute information of each nautical chart element.

[0034] Among them, the electronic nautical chart includes multiple data files, and each data file is set in the S-57 standard format. This standard defines the encoding, attributes and topological relationships of various navigation elements in the electronic nautical chart. Therefore, different types of chart elements are obtained by parsing each data file in the electronic nautical chart.

[0035] Electronic chart data files, usually with .000 extension. Usually, electronic chart data files can be opened through the corresponding S-57 data parsing library - GDAL library. And the file header information is parsed. By traversing and parsing the file header information of each data file, the record types representing different chart elements can be identified.

[0036] For example, the parsed SOUNDG record represents a sounding point; the SLCONS record represents a coastline; the DEPCNT record represents a depth contour; and the OBSTRN record represents an obstacle.

[0037] Then, the geometric shape information corresponding to each chart element is determined according to the element records in each data file, such as the coordinates of the bathymetric point, the coordinates of the coastline, the coordinates of the isobath, and the geometric shape of the obstacle.

[0038] After extracting the geometric shape information of various chart elements, the attribute fields in each element record are parsed to provide a richer description of the chart elements. For example, the VALSOU field of the SOUNDG record indicates the bathymetric value; the CATSLC field of the SLCONS record indicates the coastline type; the VALDCO field of the DEPCNT record indicates the depth value of the isobath; and the CATOBS field of the OBSTRN record indicates the obstacle type.

[0039] Step S304, generating a plurality of second images based on the chart element information and attribute information of each chart element; After obtaining the chart element information and attribute information of each chart element from the electronic chart based on the above method, a new map can be redrawn based on the information, and the chart element information and attribute information of each chart element are marked on the map. It should be noted here that since the chart element information and attribute information of each chart element need to be obtained at different times, it is necessary to generate second images at different times to obtain multiple second images.

[0040] For example, each second image may carry a timestamp, so as to facilitate subsequent sorting according to time to obtain a continuous and complete target map.

[0041] In yet another optional embodiment, Figure 6 As shown, Figure 6 An optional method embodiment of generating multiple second images provided by an exemplary embodiment of the present application includes the following steps: Step S601, determining the spatial topological relationship between the nautical chart elements according to the geometric shape information of the nautical chart elements and the attribute information of the nautical chart elements; Step S602: generating a plurality of second images according to geometric shape information of each nautical chart element at different times, attribute information of each nautical chart element and spatial topological relationship between each nautical chart element.

[0042] Among them, after extracting the geometric shape information and attribute information of each chart element from the electronic chart based on the above steps, the spatial relationship between them is analyzed to establish a topological relationship. Exemplarily, the topological relationship includes: adjacent SLCONS records can be connected to form a complete coastline; DEPCNT records can form a complete isobath network; OBSTRN records and SOUNDG records can be associated to describe the water depth information around obstacles.

[0043] Finally, the second image is obtained by integrating the geometric shape information of each chart element, the attribute information of each chart element and the spatial topological relationship between each chart element. Each element on the second image can represent the spatial distribution, attribute characteristics and mutual relationship of various chart elements in the chart, providing basic data support for subsequent image fusion and construction of target maps.

[0044] Step S305, fusing the plurality of first images and the plurality of second images respectively according to the time sequence of generation to obtain a plurality of fused images; Among them, after obtaining multiple first images and multiple second images according to the above method, the present application can perform corresponding fusion according to the timestamps on the first images and the second images, that is, fuse the first images and the second images with the same timestamp, so as to avoid fusing two unrelated images.

[0045] The fusion may be to take the union of each element in the first image and the second image, that is, to retain the same elements in the first image and the second image, while retaining the elements in the first image that are different from the second image, and the elements in the second image that are different from the first image.

[0046] The fusion may also be based on the first image, removing elements in the second image that are similar to elements in the first image, and only retaining the unremoved elements in the first image and the second image. It is understandable that the fused image may still carry the corresponding timestamp.

[0047] In yet another optional embodiment, Figure 7 As shown, Figure 7 An optional method embodiment of obtaining multiple fused images provided by an exemplary embodiment of the present application includes the following steps: Step S701, obtaining a first coordinate of a first feature object in a first image, and a second coordinate of a second feature object in a second image; Step S702, calculating a target distance between a first feature object and a second feature object based on the first coordinate and the second coordinate; Step S703, if the target distance is less than the predetermined distance, retain the first feature object and other feature objects in the second image except the second feature object, and generate a fused image based on the data of the first feature object and the other feature objects, where the other feature objects are feature objects whose target distance with the corresponding feature object is greater than or equal to the predetermined distance.

[0048] The first feature object is a dynamic object extracted from the first image, and the first feature object includes multiple first feature objects, all of which are extracted from the first image. Since the first image includes the coordinates of each object, when extracting multiple first feature objects in the first image, the first coordinates corresponding to the first feature object can be directly obtained.

[0049] The second feature object is a dynamic object extracted from the second image. The second feature object includes multiple objects, all of which are extracted from the second image. Since the second image includes the coordinates of each object, when extracting multiple second feature objects in the second image, the second coordinates corresponding to the second feature object can be directly obtained.

[0050] The present application can perform distance calculation on each first feature object extracted from the first image and multiple second feature objects extracted from the second image in sequence; and can also perform distance calculation on the first feature object and the second feature object within a distance range to determine whether the first feature object and the second feature object are the same object.

[0051] The predetermined distance may be a value determined based on experiments, historical data, experience, etc. The predetermined distance is used as a basis for judging whether two characteristic objects on different images are the same object. The predetermined distance is, for example, 10 centimeters. If the distance between the two characteristic objects is less than 10 centimeters, they are considered to be the same object.

[0052] In addition, because radar data is usually real-time and can reflect the current state of dynamic targets, the present application preferably uses the coordinates of the feature object extracted from the first image as the final target position representation of the feature object, and simultaneously retains the first feature object and other feature objects in the second image except the second feature object.

[0053] For example, if the coordinates of the first feature object are , the coordinates of the second feature object are , substitute the coordinates of the two into the following distance formula to calculate the distance d between the first feature object and the second feature object.

[0054]

[0055] If d is less than 10 cm, it is determined that the first feature object and the second feature object are the same object. In this case, the application only needs to retain the data of one feature object. The coordinates of the first feature object are retained as described above. , the coordinates of the second feature object delete.

[0056] In addition, if d is greater than or equal to 10 centimeters, it is determined that the first feature object and the second feature object are not the same object, and the present application needs to retain the data of the first feature object and the second feature object.

[0057] By traversing all first feature objects in the first image and all second feature objects in the second image, and calculating the distance, the information that needs to be retained is finally obtained. It can be understood that since the first image and the second image include multiple images, multiple first images and multiple second images are fused correspondingly according to the timestamps to obtain multiple fused images.

[0058] Step S306: Arrange the multiple fused images in the order of their generation time to obtain a target map.

[0059] Among them, after the first image and the second image are fused based on the timestamp through any of the above-mentioned methods, multiple fused images corresponding to different moments can be obtained. The present application can be to arrange multiple fused images in the order of generation time to obtain a target map, then the target map is a continuously changing image.

[0060] Step S30, performing collision risk assessment based on the navigation data and the environmental object data by using a minimum distance method and a time arrival method to obtain a first result; Among them, the present application determines whether there is a collision risk between the target device and the environmental object based on the distance between the target device and the environmental object, and how long it takes for the target device to reach the environmental object.

[0061] In an optional embodiment, if Figure 8 As shown, Figure 8 An optional method embodiment for performing collision risk assessment for an exemplary embodiment of the present application includes the following steps: Step S801, calculating relative position information of the target device and surrounding obstacles according to the first position information and the second position information; The first location information is the coordinates of the target device at the current moment, which can be obtained through a location sensor, GPS, etc. The location information of the target device is different at different moments, and only the first location information at the current moment is used for exemplary description.

[0062] The second position information is the coordinates of any surrounding obstacles in the surrounding environment of the target device, and can be acquired by a payload device (such as a radar) disposed on the target device.

[0063] Exemplarily, the first location information is ; The second location information is , the relative position information of the two can be calculated by the following formula, where d iIt is the relative position information of the target device and surrounding obstacles.

[0064]

[0065] Step S802, determining a first sub-collision risk result according to a comparison result of the relative position information and the first safety threshold; The first safety threshold may be a standard determined based on experiments, experience, timely data, etc., and used as a criterion for evaluating whether there is a collision risk between the target device and surrounding obstacles in the surrounding environment.

[0066] After the relative position information is obtained through the above calculation, the relative position information can be compared with the first safety threshold to obtain a comparison result, and the first sub-collision risk result of the two can be determined based on the comparison result. That is, one of the first results, indicating that the present application determines whether there is a collision risk between the target device and the surrounding obstacles from different directions, which can improve the accuracy of determining whether there is a collision risk between the two.

[0067] Optionally, if the relative position information is less than a first safety threshold, determining the first sub-collision risk result is that there is a collision risk between the target device and surrounding obstacles; If the relative position information is greater than or equal to the first safety threshold, it is determined that the first sub-collision risk result is that there is no collision risk between the target device and the surrounding obstacles.

[0068] Step S803, calculating the relative speed between the target device and the surrounding obstacles according to the first navigation speed and the second navigation speed; The first navigation speed is the current speed of the target device, which can be obtained through the speed measurement device on it; the second navigation speed is the speed of the surrounding obstacles. Of course, some stationary surrounding obstacles do not have the second navigation speed, and only some moving ships have the second navigation speed. If some surrounding obstacles are stationary, the collision risk can only be determined based on the relative position information.

[0069] Exemplarily, the present application may calculate the relative speed of the two according to the following formula:

[0070] Where ti is the relative speed, are the two velocity components of the first sailing speed, are the two velocity components of the second cruising speed.

[0071] Step S804, determining a second sub-collision risk result according to a comparison result between the relative speed and the second safety threshold; The second safety threshold may be a standard determined based on experiments, experience, timely data, etc., and used as a criterion for evaluating whether there is a collision risk between the target device and surrounding obstacles in the surrounding environment.

[0072] After the relative speed is obtained through the above calculation, the relative speed may be compared with the second safety threshold to obtain a comparison result, and a second sub-collision risk result of the two may be determined according to the comparison result, that is, another result of the first result.

[0073] Optionally, if the relative speed is less than a second safety threshold, determining the second sub-collision risk result is that there is a collision risk between the target device and surrounding obstacles; If the relative speed is greater than or equal to the second safety threshold, the second sub-collision risk result is determined as no collision risk between the target device and the surrounding obstacles.

[0074] Step S805: if at least one of the first sub-collision risk result and the second sub-collision risk result indicates that there is a collision risk, then determining that the first result indicates that there is a collision risk; Step S806: If both the first sub-collision risk result and the second sub-collision risk result indicate that there is no collision risk, then determining that the first result indicates that there is no collision risk.

[0075] Among them, the present application may be that as long as one of the two sub-results of the first result indicates that there is a collision risk, the first result is determined to be that there is a collision risk; conversely, only when both of the two sub-results do not indicate that there is a collision risk, the first result is determined to be that there is no collision risk.

[0076] Step S40: If the first result is that there is a collision risk, an obstacle avoidance strategy is determined based on the navigation data, the environmental object data and the wall collision rule library, and the navigation of the target device is controlled according to the obstacle avoidance strategy.

[0077] Among them, the present application is based on the above-mentioned method of determining whether there is a collision risk between the target device and the surrounding obstacles. After obtaining the collision risk assessment result, it can be understood that obstacle avoidance is only required when there is a collision risk between the two. If there is no collision risk, obstacle avoidance is not required, and driving can continue according to the original route and the original driving parameters.

[0078] In another optional embodiment, the present application also determines a risk index between the target device and the surrounding obstacles based on the first safety threshold, the second safety threshold, the relative position information, the relative speed, the first weight and the second weight.

[0079] Exemplarily, the risk index is determined by the following formula:

[0080] Where C is the risk index, is the weight coefficient, reflecting the importance of collision distance and time; D is the first safety threshold; T is the second safety threshold.

[0081] Next, the application may determine the obstacle avoidance strategy according to the following steps: Fig. 9 As shown, Step S901, calculating a first heading angle of surrounding obstacles according to the first position information and the second position information; Among them, the application can be to calculate the first heading angle according to the following formula:

[0082] Step S902, obtaining a second heading angle of the target device at the current moment in the first navigation data; The second heading angle of the target device at the current moment may be acquired by an angle measuring instrument or other device provided on the target device.

[0083] Step S903, determining the adjusted heading angle of the target device according to the difference between the first heading angle and the second heading angle, and obtaining a first sub-strategy; The present application may calculate the difference between the first heading angle and the second heading angle according to the following formula, and the difference is the adjustment amount for the second heading angle. If the adjustment amount is negative, the second heading angle may be reduced, and if the adjustment amount is positive, the second heading angle may be increased.

[0084]

[0085] In addition, after calculating the difference, the present application may also normalize the difference to keep it within the range of [-180 degrees, 180 degrees].

[0086] Step S904, determining the adjustment speed of the target device according to the risk index to obtain a second sub-strategy; in,

[0087] -V1, -V2, -V3 represent the maximum deceleration amplitude, the medium deceleration amplitude, and the minimum deceleration amplitude, respectively, which depends on the design and operating specifications of the target equipment.

[0088] When the distance is far and there is no risk, you can choose to speed up;

[0089] V1, V2, and V3 represent the maximum speed-up range, the medium speed-up range, and the minimum speed-up range, respectively, which also depends on the design and operating specifications of the target equipment.

[0090] It is understandable that if there is no risk, then you can just maintain the current speed and continue driving.

[0091] Step S905: Use the first sub-strategy and the second sub-strategy as obstacle avoidance strategies.

[0092] Among them, this application starts from the heading angle and speed to clarify the obstacle avoidance strategy for the target device, making the obstacle avoidance more effective.

[0093] After obtaining the obstacle avoidance strategy, the target device may generate control instructions for the object, and control the target device to navigate by adjusting the heading angle and adjusting the speed through the control instructions.

[0094] In yet another optional embodiment, when the target device is under the control of the control instruction, the navigation data of the target device at the next moment is determined according to the parameters of the target device and updated.

[0095] Among them, since the target device avoids obstacles according to the obstacle avoidance strategy, it cannot navigate according to the predetermined navigation data until the next moment. Therefore, when the target device avoids obstacles, it is necessary to determine the navigation data of the target device at the next moment according to the parameters of the target device and update it, so that the target device can generate real-time navigation data for easy query.

[0096] Exemplarily, the present application determines the navigation data of the target device at the next moment according to the following formula: 1. Update the position based on the target device’s navigation speed and heading:

[0097] 2. Heading update:

[0098] 3. Speed ​​update:

[0099] The obstacle avoidance method provided in the present application takes into account that the existing obstacle avoidance for unmanned boats is only performed through data collected by payload equipment installed on the unmanned boats, and it is difficult to provide reliable data for obstacle avoidance for medium and high-speed unmanned boats, resulting in poor accuracy and reliability in identifying the position and direction of obstacles. Therefore, the present application provides a new obstacle avoidance method. The method monitors the navigation data of the target device and the environmental object data of each object in the surrounding environment of the target device through a target map obtained by fusing an electronic nautical chart and images collected by a payload equipment installed on the unmanned boat. The superposition of the two makes up for the problems of short recognition distance, slow response speed, and limited perception information when the payload equipment and the electronic nautical chart are used separately, providing reliable data support for obstacle avoidance of the target device and improving the safety of navigation of the target device.

[0100] It should be noted that although the operations of the method of the present invention are described in a particular order in the accompanying drawings, this does not require or imply that the operations must be performed in the particular order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted in the flowchart can be performed in a different order. For example, ... Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps. For example, . . .

[0101] Further references Fig.10 , which shows an exemplary structural block diagram of an apparatus 1000 for performing obstacle avoidance according to an embodiment of the present application, wherein the apparatus 1000 includes an acquisition module 1001, an evaluation module 1002 and a determination module 1003.

[0102] An acquisition module 1001 is used to acquire the navigation data and environmental object data of the target device at the current moment based on a target map. The target map is a map obtained by fusing an electronic nautical chart and an image collected by a payload device on the target device; An evaluation module 1002 is used to perform a collision risk evaluation based on the navigation data and the environmental object data by using a minimum distance method and a time arrival method to obtain a first result; The determination module 1003 is used to determine an obstacle avoidance strategy based on the navigation data, the environmental object data and the wall collision rule library when the first result is that there is a collision risk, and control the navigation of the target device according to the obstacle avoidance strategy.

[0103] It should be understood that the units or modules described in the apparatus 1000 are similar to those described in the reference Figure 2 The various steps in the described method correspond to each other. Therefore, the operations and features described above for the method are also applicable to the device 1000 and the units contained therein, and will not be repeated here. The device 1000 can be pre-implemented in a browser or other security application of an electronic device, or loaded into the browser or its security application of an electronic device by downloading or the like. The corresponding units in the device 1000 can cooperate with the units in the electronic device to implement the solution of the embodiment of the present application.

[0104] Reference below Fig.11 , which shows a computer device suitable for implementing an embodiment of the present application, the computer device includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement Figure 2-9 Any method step.

[0105] Reference below Fig.11 , which shows a schematic diagram of the structure of a computer system 1100 suitable for implementing a computer device of an embodiment of the present application.

[0106] like Fig.11 As shown, the computer system 1100 includes a central processing unit (CPU) 1101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage portion 1108 into a random access memory (RAM) 1103. In the RAM 1103, various programs and data required for the operation of the system 1100 are also stored. The CPU 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0107] The following components are connected to the I / O interface 1105: an input section 1106 including a keyboard, a mouse, etc.; an output section 1107 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN card, a modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to the I / O interface 1105 as needed. A removable medium 1111, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1110 as needed, so that a computer program read therefrom is installed into the storage section 1108 as needed.

[0108] In particular, according to the embodiments of the present disclosure, the above reference Figure 2-9 The described processes may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising a computer program for executing Figure 2-9 In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 1109 and / or installed from the removable medium 1111.

[0109] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a different order from the order marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0110] The units or modules involved in the embodiments described in the present application may be implemented by software or hardware. The units or modules described may also be arranged in a processor, for example, may be described as: a processor includes an XX unit, a YY unit, and a ZZ unit. The names of these units or modules do not, in some cases, constitute a limitation on the unit or module itself, for example, the XX unit may also be described as a "unit for XX".

[0111] As another aspect, the present application further provides a computer-readable storage medium, which may be a computer-readable storage medium included in the device described in the above embodiment; or a computer-readable storage medium that exists independently and is not assembled into the device. The computer-readable storage medium stores one or more programs, and the programs are used by one or more processors to execute the formula input method described in the present application.

[0112] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the present application.

Claims

1. An obstacle avoidance method, characterized in that: The method comprises: Acquiring navigation data of the target device and environmental object data based on a target map, wherein the target map is a map obtained by fusing an electronic nautical chart and an image collected by a payload device on the target device; Performing collision risk assessment based on the navigation data and the environmental object data by using a minimum distance method and a time arrival method to obtain a first result; If the first result is that there is a collision risk, an obstacle avoidance strategy is determined based on the navigation data, the environmental object data and the wall collision rule library, and the navigation of the target device is controlled according to the obstacle avoidance strategy.

2. The obstacle avoidance method according to claim 1, characterized in that: The method further comprises the step of obtaining the target map: Collect obstacle data within a preset range at different times through the payload device on the target device; generating a plurality of first images based on the obstacle data; Reading the chart element information and attribute information of each chart element at different times from the electronic chart according to the time when the load equipment collects the obstacle data; generating a plurality of second images based on the chart element information and attribute information of each of the chart elements; fusing the plurality of first images and the plurality of second images respectively according to a time sequence of generation to obtain a plurality of fused images; Arrange the multiple fused images in the order of their generation time to obtain the target map.

3. The obstacle avoidance method according to claim 2, characterized in that: The generating a plurality of first images based on the obstacle data comprises: Performing coordinate system conversion on the polar coordinate data in the obstacle data to obtain a point set of each obstacle in a rectangular coordinate system; Determine the pixel brightness value of each obstacle in the image according to the payload equipment echo intensity data in the obstacle data; The multiple first images are generated according to the pixel brightness values ​​of each obstacle in the image at different moments and the point sets of each obstacle in a rectangular coordinate system.

4. The obstacle avoidance method according to claim 2, characterized in that: The chart element information includes chart elements and geometric shape information corresponding to the chart elements. The chart element information and attribute information of each chart element are read from the electronic chart according to the time when the load equipment collects the obstacle data, including: Traversing the data files of the electronic nautical chart, parsing the header information of each data file to obtain different types of nautical chart elements; Determine the geometric shape information corresponding to each of the nautical chart elements according to the element records in each of the data files; The attribute fields of the element records in each of the data files are parsed to obtain the attribute information of each of the nautical chart elements.

5. The obstacle avoidance method according to claim 4, characterized in that: The generating of a plurality of second images based on the nautical chart element information and attribute information of each of the nautical chart elements comprises: Determining the spatial topological relationship between the nautical chart elements according to the geometric shape information of the nautical chart elements and the attribute information of the nautical chart elements; The plurality of second images are generated according to geometric shape information of each of the nautical chart elements at different times, attribute information of each of the nautical chart elements, and spatial topological relationships between each of the nautical chart elements.

6. The obstacle avoidance method according to claim 2, characterized in that: The step of fusing the plurality of first images and the plurality of second images respectively according to the time sequence of generation to obtain a plurality of fused images comprises: Acquire a first coordinate of a first feature object in the first image, and a second coordinate of a second feature object in the second image; Calculate a target distance between the first feature object and the second feature object based on the first coordinate and the second coordinate; If the target distance is less than a predetermined distance, the first feature object and other feature objects in the second image except the second feature object are retained, and the fused image is generated according to the data of the first feature object and the other feature objects, wherein the other feature objects are feature objects whose target distance with the corresponding feature object is greater than or equal to a predetermined distance.

7. The method according to claim 1, characterized in that The navigation data includes first position information and a first navigation speed of the target device at a current moment, the environmental object data includes second position information and a second navigation speed of obstacles around the target device, and the collision risk assessment is performed based on the navigation data and the environmental object data by using a minimum distance method and a time arrival method to obtain a first result, including: Calculating relative position information of the target device and the surrounding obstacles according to the first position information and the second position information; Determining a first sub-collision risk result according to a comparison result of the relative position information and a first safety threshold; Calculating a relative speed between the target device and the surrounding obstacles according to the first navigation speed and the second navigation speed; Determining a second sub-collision risk result according to a comparison result between the relative speed and the second safety threshold; If only one of the first sub-collision risk result and the second sub-collision risk result indicates that there is a collision risk, determining that the first result indicates that there is a collision risk; If both the first sub-collision risk result and the second sub-collision risk result indicate that there is no collision risk, then the first result is determined to be that there is no collision risk.

8. The method according to claim 7, characterized in that The determining a first sub-collision risk result according to a comparison result of the relative position information and the first safety threshold comprises: If the relative position information is less than a first safety threshold, determining the first sub-collision risk result is that there is a collision risk between the target device and the surrounding obstacles; If the relative position information is greater than or equal to the first safety threshold, it is determined that the first sub-collision risk result is that there is no collision risk between the target device and the surrounding obstacles.

9. The method according to claim 7, characterized in that: Determining a second sub-collision risk result according to a comparison result between the relative speed and the second safety threshold includes: If the relative speed is less than a second safety threshold, determining the second sub-collision risk result as a collision risk between the target device and the surrounding obstacles; If the relative speed is greater than or equal to the second safety threshold, the second sub-collision risk result is determined to be that there is no collision risk between the target device and the surrounding obstacles.

10. The method according to claim 7, characterized in that The method further comprises: A risk index between the target device and the surrounding obstacles is determined according to the first safety threshold, the second safety threshold, the relative position information, the relative speed, the first weight and the second weight.

11. The method according to claim 10, characterized in that The determining of the obstacle avoidance strategy based on the first navigation data, the environmental object data and the wall collision rule library includes: Calculate a first heading angle of the surrounding obstacles according to the first position information and the second position information; Acquire a second heading angle of the target device at a current moment in the first navigation data; Determine the adjusted heading angle of the target device according to the difference between the first heading angle and the second heading angle, and obtain a first sub-strategy; Determine the adjustment speed of the target device according to the risk index to obtain a second sub-strategy; The first sub-strategy and the first sub-strategy are used as the obstacle avoidance strategy.

12. The method according to claim 11, characterized in that The step of controlling the target device to navigate according to the obstacle avoidance strategy includes: A control instruction is generated according to the first sub-strategy and the first sub-strategy, so as to control the target device to navigate according to the adjusted heading angle and the adjusted speed through the control instruction.

13. The method according to claim 12, characterized in that The method further comprises: When the target device is under the control of the control instruction, the navigation data of the target device at the next moment is determined according to the parameters of the target device and updated.

14. An obstacle avoidance device, characterized in that: The device comprises: An acquisition module, used to acquire navigation data and environmental object data of a target device at a current moment based on a target map, wherein the target map is a map obtained by fusing an electronic nautical chart and an image collected by a payload device on the target device; An evaluation module, configured to perform a collision risk evaluation based on the navigation data and the environmental object data by using a minimum distance method and a time arrival method to obtain a first result; A determination module is used to determine an obstacle avoidance strategy based on the navigation data, the environmental object data and the wall collision rule library when the first result is that there is a collision risk, and control the navigation of the target device according to the obstacle avoidance strategy.

15. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 13 are implemented.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 13 are implemented.

17. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 13 are implemented.

Images