Unmanned ship mapping method, unmanned ship and computer readable storage medium

Abstract

The application is suitable for the technical field of unmanned ship, and provides an unmanned ship mapping method, an unmanned ship and a computer readable storage medium, which comprises the following steps: in the process of unmanned ship sailing, a plurality of first position points in a target environment where the unmanned ship is located are acquired by a monocular vision device of the unmanned ship; for any one of the first position points, a bearing angle sequence of the unmanned ship relative to the first position point is acquired by the monocular vision device; positioning information of the first position point is calculated according to the bearing angle sequence; and a map of the target environment is generated according to the positioning information of each first position point in the target environment. Through the above method, the problem that the unmanned ship cannot accurately map due to limited load can be solved.

Description

Technical Field

[0001] This application belongs to the field of unmanned surface vessel (USV) technology, and particularly relates to an unmanned surface vessel mapping method, an unmanned surface vessel, and a computer-readable storage medium. Background Technology

[0002] Unmanned surface vessels (USVs) are an important type of unmanned maritime platform with broad application prospects in areas such as river inspection, hydrological monitoring, and waterway surveying. Considering that inland waterways are typically narrow, have rugged shorelines, and complex environments, traditional large-scale marine mapping methods are difficult to apply. Therefore, USV mapping has become an important technology for environmental mapping.

[0003] Currently, unmanned surface vessels (USVs) typically employ multi-sensor fusion mapping or achieve high-precision mapping by carrying high-precision sensing equipment. However, for some complex aquatic environments, only small USVs can navigate. The limited payload capacity of small USVs restricts their ability to carry a large amount of hardware, posing a significant challenge to their environmental perception and autonomous mapping capabilities. Summary of the Invention

[0004] This application provides an unmanned surface vessel (USV) mapping method, an USV, and a computer-readable storage medium, which can solve the problem of inaccurate mapping due to the limited payload of the USV.

[0005] In a first aspect, embodiments of this application provide an unmanned surface vessel mapping method, including: During the navigation of the unmanned vessel, multiple first location points in the target environment where the unmanned vessel is located are acquired by the monocular vision device of the unmanned vessel. For any first location point, the azimuth angle sequence of the unmanned vessel relative to the first location point is obtained through the monocular vision device; wherein, the azimuth angle sequence includes multiple second location points along the unmanned vessel's navigation path and the azimuth angles corresponding to each of the multiple second location points, and the azimuth angle corresponding to each second location point is the azimuth angle of the first location point relative to the second location point. The positioning information of the first location point is calculated based on the azimuth sequence; A map of the target environment is generated based on the location information of each of the first location points in the target environment.

[0006] In this embodiment, multiple location points along the unmanned surface vessel's (USV) path are used as known baselines. The azimuth angles between each location point and feature points in the navigation environment, acquired by a monocular vision device, are combined to locate the feature points in the navigation environment. Mapping is then performed based on the location information of these feature points. This method allows for navigation environment mapping using only a monocular vision device, eliminating the need for high-cost sensing equipment such as binocular vision acquisition devices or lidar, thus reducing the USV's hardware load and cost. Furthermore, locating feature points based on the relative azimuth angles between multiple USV path points and feature points reduces calculation errors caused by single outliers, improving mapping accuracy. This method balances hardware cost and mapping accuracy, effectively addressing the problem of limited payload capacity preventing high-precision mapping, especially for small USVs.

[0007] In one possible implementation of the first aspect, calculating the positioning information of the first location point based on the azimuth sequence includes: Multiple predicted positions of the first position point are calculated based on the azimuth sequence; The positioning information of the first location point is determined based on multiple predicted locations of the first location point.

[0008] In this embodiment, multiple predicted positions are generated by azimuth sequence, and then the final positioning information of the first position point is determined by combining the results. This can effectively filter measurement noise and abnormal points, and improve positioning accuracy and stability.

[0009] In one possible implementation of the first aspect, calculating multiple predicted positions of the first location point based on the azimuth sequence includes: The second position points in the azimuth sequence are combined in pairs to obtain multiple position groups; A predicted position of the first position point is calculated based on the azimuth angles corresponding to the two second position points in each position group.

[0010] In the above method, predicted positions are generated by combining multiple known observation locations (second location points) in pairs. This fully utilizes all azimuth observation data to form sufficient and redundant candidate locations, facilitating the subsequent screening of abnormal error points and effectively improving the accuracy and anti-interference stability of the final positioning result. Furthermore, compared to time-series prediction methods, the method described in the above embodiment of this application arranges as many spatial combinations as possible, breaking time-series limitations and more realistically reflecting the spatial characteristics between location points, thereby improving positioning accuracy.

[0011] In one possible implementation of the first aspect, determining the positioning information of the first location point based on multiple predicted locations of the first location point includes: Calculate the confidence level corresponding to each predicted position based on the two second position points in each position group; The positioning information of the first location point is determined based on the confidence level of each of the multiple predicted locations.

[0012] In the above method, the credibility of each predicted location is first quantified based on geometric parameters, and then all predicted points are merged based on the credibility. This can distinguish the positioning reliability of different predicted locations, suppress the interference of points with poor geometric configuration and large errors on the final positioning result, and help improve positioning accuracy and stability.

[0013] In one possible implementation of the first aspect, calculating the confidence level corresponding to each predicted position based on the two first position points in each position group includes: The first score is calculated based on the length of the line connecting two of the second position points in the position group; The second score is calculated based on the intersection angle formed by the lines connecting each of the two second position points in the position group to the predicted position corresponding to the position group. The confidence level of the predicted location corresponding to the location group is calculated based on the first score and the second score.

[0014] In the above method, the baseline length and the intersection angle of the two location points are combined to score and calculate the credibility of the two core geometric dimensions of triangulation positioning. This comprehensively evaluates the geometric configuration of each predicted location, and the credibility quantification results are more in line with the actual positioning error level, effectively improving the accuracy of anomaly point identification and weighted fusion.

[0015] In one possible implementation of the first aspect, determining the positioning information of the first location point based on the confidence level corresponding to each of the plurality of predicted locations includes: Calculate the sum of the confidence levels corresponding to each of the multiple predicted locations to obtain the first data; Calculate the ratio of the confidence level corresponding to each predicted location to the first data to obtain the second data; Using the confidence level corresponding to each of the multiple predicted locations as weights, the second data corresponding to each of the multiple predicted locations are weighted and summed to obtain the positioning information of the first location point.

[0016] In the above method, the weights of each predicted position are obtained by confidence normalization and then the coordinates are weighted and fused. This allows the predicted points with better geometric configurations and higher confidence to dominate the final positioning result, weakening the influence of inferior points with large errors, and effectively improving positioning accuracy and trajectory smoothness.

[0017] In one possible implementation of the first aspect, the method further includes: For each of the first location points, if the number of predicted locations corresponding to the first location point reaches a preset value, then the first N predicted locations among the multiple predicted locations corresponding to the first location point are retained in descending order of confidence.

[0018] Understandably, as the unmanned vessel continues to navigate, the amount of data in the azimuth sequence for the same initial location point increases. By employing the method described above, when the number of predicted locations is sufficient, only the top N high-quality locations are retained in descending order of confidence, eliminating a large number of low-confidence outlier coordinates. This significantly reduces the computational load of subsequent weighted fusion and minimizes the interference of erroneous locations on the final positioning result.

[0019] Secondly, embodiments of this application provide an unmanned vessel, including: A monocular vision device is used to acquire images of the target environment in which the unmanned vessel is located; The processor is configured as follows: During the navigation of the unmanned vessel, multiple first location points in the target environment where the unmanned vessel is located are acquired by the monocular vision device of the unmanned vessel. For any first position point, the azimuth angle sequence of the unmanned vessel relative to the first position point is obtained through the monocular vision device; wherein, the azimuth angle sequence includes multiple second position points passed by the unmanned vessel during navigation and the azimuth angles corresponding to each of the multiple second position points, and the azimuth angle corresponding to each second position point is the azimuth angle of the first position point relative to the second position point. The positioning information of the first location point is calculated based on the azimuth sequence; A map of the target environment is generated based on the location information of each of the first location points in the target environment.

[0020] Thirdly, embodiments of this application provide a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the unmanned vessel mapping method as described in any one of the first aspects above.

[0021] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the unmanned vessel mapping method as described in any one of the first aspects above.

[0022] Fifthly, embodiments of this application provide a computer program product that, when run on a terminal device, causes the terminal device to execute the unmanned vessel mapping method described in any of the first aspects above.

[0023] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a schematic flowchart of the unmanned vessel mapping method provided in the embodiments of this application; Figure 2 This is a schematic diagram of the unmanned vessel's waypoints provided in the embodiments of this application; Figure 3 This is a schematic diagram of an unmanned vessel navigation scenario provided in an embodiment of this application; Figure 4 This is a schematic diagram of an unmanned vessel navigation scenario provided in another embodiment of this application; Figure 5 This is a schematic diagram of an unmanned vessel navigation scenario provided in another embodiment of this application; Figure 6 This is a structural block diagram of the unmanned vessel mapping device provided in the embodiments of this application; Figure 7 This is a schematic diagram of the architecture of the unmanned vessel provided in the embodiments of this application. Detailed Implementation

[0026] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0027] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0028] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0029] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0030] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0031] References to "one embodiment" or "some embodiments" in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized.

[0032] Unmanned surface vessels (USVs) are an important type of unmanned maritime platform with broad application prospects in areas such as river inspection, hydrological monitoring, and waterway surveying. Considering that inland waterways are typically narrow, have rugged shorelines, and complex environments, traditional large-scale marine mapping methods are difficult to apply. Therefore, USV mapping has become an important technology for environmental mapping.

[0033] Currently, unmanned surface vessels (USVs) typically employ multi-sensor fusion mapping or achieve high-precision mapping by carrying high-precision sensing equipment. However, for some complex aquatic environments, only small USVs can navigate. The limited payload capacity of small USVs restricts their ability to carry a large amount of hardware, posing a significant challenge to their environmental perception and autonomous mapping capabilities.

[0034] Based on this, this application provides a mapping method for unmanned surface vessels (USVs). In this embodiment, multiple location points along the USV's navigation path are used as known baselines. The azimuth angles between each location point and feature points in the navigation environment, acquired by a monocular vision device, are combined to locate the feature points in the navigation environment. Mapping is then performed based on the location information of these feature points. In this way, mapping of the navigation environment can be achieved using only a monocular vision device. The USV does not need to be equipped with high-cost sensing devices such as binocular vision acquisition devices or lidar, reducing the hardware load and cost of the USV. Furthermore, locating feature points based on the relative azimuth angles between multiple transit points and feature points reduces calculation errors caused by single outliers, thus improving mapping accuracy. This method balances hardware cost and mapping accuracy, effectively solving the problem of high-precision mapping due to payload limitations, especially for small USVs.

[0035] See Figure 1 This is a flowchart illustrating the unmanned vessel mapping method provided in this application embodiment. It is intended as an example and not a limitation. The method may include steps S101-S104, which are described in detail below.

[0036] S101, during the unmanned vessel's navigation, acquire multiple first position points in the target environment where the unmanned vessel is located, collected by the unmanned vessel's monocular vision device.

[0037] The first location point can be a location point with significant features in the target environment. It is understood that multiple first location points can be marked on the target environment.

[0038] In one implementation, image recognition is performed on the image acquired by the monocular vision device to obtain feature points in the image, and these feature points are recorded as the first position point.

[0039] Optionally, multiple initial location points can be located during a single voyage of the unmanned vessel.

[0040] Optionally, only one initial location point can be located during each voyage of the unmanned vessel, and multiple different initial location points can be located through multiple voyages of the unmanned vessel in the target environment.

[0041] Optionally, the positioning information of the same initial location point can be updated through multiple voyages of the unmanned vessel in the target environment.

[0042] It is understandable that the multiple first location points in S101 could be collected by the unmanned vessel during a single voyage or by the unmanned vessel during multiple voyages.

[0043] S102, for any first position point, obtain the azimuth sequence of the unmanned vessel relative to the first position point through a monocular vision device.

[0044] The azimuth sequence includes multiple second position points along the unmanned vessel's navigation path and the azimuth angles corresponding to each of the multiple second position points. The azimuth angle corresponding to each second position point is the azimuth angle of the first position point relative to the second position point.

[0045] For example, see Figure 2 This is a schematic diagram of the unmanned vessel's waypoints provided in an embodiment of this application. It is intended as an example and not a limitation. Figure 2 As shown, point A is the first position point. Points Pi and Pi+1 are the second position points passed by the unmanned vessel during its first voyage, where point Pi corresponds to time ti and point Pi+1 corresponds to time ti+1. Points Pj and Pj+1 are the second position points passed by the unmanned vessel during its second voyage, where point Pj corresponds to time tj and point Pj+1 corresponds to time tj+1. The azimuth angles of the first position point A relative to points Pi, Pi+1, Pj, and Pj+1 are recorded. The resulting azimuth angle sequence includes (Pi, θi), (Pi+1, θi+1), (Pj, θj), and (Pj+1, θj+1), where Pi represents the position of point Pi and θi represents the azimuth angle of point A relative to point Pi.

[0046] Optionally, multiple secondary location points can be acquired during a single voyage of the unmanned vessel.

[0047] Optionally, only one second location point can be located during each voyage of the unmanned vessel, and multiple different second location points can be obtained through multiple voyages of the unmanned vessel in the target environment.

[0048] It is understandable that the azimuth sequence in S102 may include the second position point obtained by the unmanned vessel during one voyage, or it may include the second position point obtained by the unmanned vessel during multiple voyages.

[0049] Optionally, the azimuth angle can be the angle between the line connecting the first and second location points and the longitude. Alternatively, the azimuth angle can be the angle between the line connecting the first and second location points and the latitude.

[0050] It should be noted that the definition rules for azimuth angles recorded in the azimuth angle sequence are consistent. For example, for all second position points, the angle between the line connecting the first and second position points and the longitude is recorded as the azimuth angle. Alternatively, for all second position points, the angle between the line connecting the first and second position points and the latitude is recorded as the azimuth angle.

[0051] In one implementation, the second position point can be recorded at a fixed frequency during the unmanned vessel's navigation.

[0052] S103, calculate the positioning information of the first position point based on the azimuth sequence.

[0053] In some possible implementations, S103 includes: determining a first straight line corresponding to each second position point based on each second position point and its corresponding azimuth angle in the azimuth angle sequence, wherein the first straight line is a straight line passing through the first position point and the second position point; fitting the first straight lines corresponding to multiple second position points to determine the intersection position of multiple first straight lines, and recording the intersection position as the positioning information of the first position.

[0054] In some embodiments of this application, S103 includes: Multiple predicted positions of the first position point are calculated based on the azimuth sequence; The positioning information of the first location point is determined based on multiple predicted locations of the first location point.

[0055] In this embodiment, multiple predicted positions are generated by azimuth sequence, and then the final positioning information of the first position point is determined by combining the results. This can effectively filter measurement noise and abnormal points, and improve positioning accuracy and stability.

[0056] In some possible implementations, the steps for calculating the predicted position may include: filtering out outliers in the azimuth sequence to obtain a filtered azimuth sequence; and calculating multiple predicted positions of the first position point based on the filtered azimuth sequence.

[0057] In some possible implementations, the steps for calculating the predicted location may include: The azimuth sequence is segmented according to the acquisition time sequence to obtain multiple subsequences; each subsequence corresponds to a time period; the predicted position for the corresponding time period is generated iteratively by segmenting the subsequences; the multiple predicted positions generated continuously in the time sequence are iteratively smoothed to obtain multiple processed predicted positions; the final positioning information of the first position point is determined based on the multiple processed predicted positions.

[0058] The above implementation method is equivalent to predicting the position information of the first position point according to the time sequence.

[0059] In some embodiments of this application, the calculation steps for the predicted location include: By pairwise combining the second position points in the azimuth sequence, multiple position groups are obtained; Calculate a predicted position for the first position point based on the azimuth angles corresponding to the two second position points in each position group.

[0060] For example, if the azimuth sequence includes three second position points P1, P2 and P3, then by combining them in pairs, we can obtain three position groups, namely P1P2, P2P3 and P1P3.

[0061] Optionally, for each location group, the predicted position of the first location point can be calculated using a triangulation algorithm.

[0062] In the above method, predicted positions are generated by combining multiple known observation locations (second location points) in pairs. This fully utilizes all azimuth observation data to form sufficient and redundant candidate locations, facilitating the subsequent screening of abnormal error points and effectively improving the accuracy and anti-interference stability of the final positioning result. Furthermore, compared to time-series prediction methods, the method described in the above embodiment of this application arranges as many spatial combinations as possible, breaking time-series limitations and more realistically reflecting the spatial characteristics between location points, thereby improving positioning accuracy.

[0063] In some implementations, the steps for determining the location information of the first location point include S201-S202, which are described in detail below.

[0064] S201, calculate the confidence level corresponding to each predicted position based on the two second position points in each position group.

[0065] In some possible implementations, S201 includes: calculating the difference in azimuth angles between the two second position points in each position group to obtain the azimuth angle difference value; obtaining the preset weight corresponding to the preset data range to which the azimuth angle difference value belongs to obtain the confidence level corresponding to each position group.

[0066] In some embodiments of this application, S201 includes: The first score is calculated based on the length of the line connecting two second location points in the location group; The second score is calculated based on the intersection angle formed by the lines connecting the two second position points in the position group to the predicted position corresponding to the position group. The confidence level of the predicted location corresponding to the location group is calculated based on the first score and the second score.

[0067] In the above method, the baseline length and the intersection angle of the two location points are combined to score and calculate the credibility of the two core geometric dimensions of triangulation positioning. This comprehensively evaluates the geometric configuration of each predicted location, and the credibility quantification results are more in line with the actual positioning error level, effectively improving the accuracy of anomaly point identification and weighted fusion.

[0068] Optionally, the first score can be calculated using the following formula: ; in, It received the highest rating; For preset reference values, such as =10 (meters); L is the length of the line connecting the two second position points in the position group.

[0069] In the above-mentioned first scoring method, the piecewise linear formula can concisely and efficiently quantify the impact of the baseline length of the two base stations on the positioning reliability. The score is capped after the baseline length meets the standard. It not only distinguishes the difference between poor positioning accuracy of short baseline and stable and reliable positioning of long baseline, but also avoids the problem of unlimited score amplification caused by excessively long baseline. The calculation is small and the threshold is controllable, which makes it easy to quickly complete the prediction location reliability scoring.

[0070] Optional, according to the formula Calculate the second score. Among them, This is the intersection angle formed by the lines connecting each of the two second position points in the position group to their corresponding predicted positions in the position group. It can be understood that when... hour, (Maximum); when When approaching 0 degrees or approaching 180 degrees, Approaching 0.

[0071] Optionally, the first and second scores corresponding to each location group can be added together to obtain the confidence level of the predicted location corresponding to that location group.

[0072] In some implementations of this application, a low-score-sensitive nonlinear fusion calculation can be performed on the first and second scores corresponding to each location group to obtain the confidence level of the predicted position corresponding to each location group. The low-score-sensitive nonlinear fusion calculation can significantly suppress the confidence level when either the first or second score is small.

[0073] Optional, according to the formula A low-score-sensitive nonlinear fusion calculation is performed on the first and second scores. Here, K represents the confidence level. This indicates a rounding up operation, where H is a preset value.

[0074] Understandably, the first score is equivalent to considering the baseline length, and the second score is equivalent to considering the intersection angle. Calculated using this formula, K only approaches the preset value when both the baseline length and the intersection angle are ideal; if any condition in either the baseline length or the intersection angle deteriorates, the reliability drops rapidly.

[0075] By employing the above method, low-score sensitive nonlinear fusion processing is used to process the two scores. If either the baseline or intersection angle dimension index is poor, the overall credibility will be significantly reduced. This accurately filters out inferior prediction points that are only qualified in one dimension or have defects in geometric configuration, thereby improving the rigor of credibility evaluation.

[0076] S202, determine the location information of the first location point based on the confidence level of each of the multiple predicted locations.

[0077] In steps S201-S202, the credibility of each predicted location is first quantified based on geometric parameters, and then all predicted points are merged based on the credibility. This can distinguish the positioning reliability of different predicted locations, suppress the interference of points with poor geometric configuration and large errors on the final positioning result, and help improve positioning accuracy and stability.

[0078] Optionally, S202 includes: using confidence as a weight for the predicted location, performing a weighted summation of multiple predicted locations to obtain the positioning information of the first location point.

[0079] In some implementations of this application, S202 includes: The sum of the confidence levels corresponding to each of the multiple predicted locations is calculated to obtain the first data. Calculate the ratio of the confidence level corresponding to each predicted location to the first data to obtain the second data; Using the confidence level of each of the multiple predicted locations as weights, the second data corresponding to each of the multiple predicted locations are weighted and summed to obtain the location information of the first location point.

[0080] For example, according to the formula Calculate the positioning information of the first location point. Where A represents the positioning information of the first location point; This is the first data; For the i-th predicted position Corresponding credibility; This is the second data point.

[0081] In the above method, the weights of each predicted position are obtained by confidence normalization and then the coordinates are weighted and fused. This allows the predicted points with better geometric configurations and higher confidence to dominate the final positioning result, weakening the influence of inferior points with large errors, and effectively improving positioning accuracy and trajectory smoothness.

[0082] S104, Generate a map of the target environment based on the positioning information of each first location point in the target environment.

[0083] Optionally, for multiple first location points in the target environment, a map of the target environment is generated for each first location point according to the geospatial order of their respective location information.

[0084] In some embodiments, the method further includes: For each first position point, if the number of predicted positions corresponding to the first position point reaches a preset value, then the first N predicted positions among the multiple predicted positions corresponding to the first position point are retained in descending order of confidence.

[0085] Understandably, as the unmanned vessel continues to navigate, the amount of data in the azimuth sequence for the same initial location point increases. By employing the method described above, when the number of predicted locations is sufficient, only the top N high-quality locations are retained in descending order of confidence, eliminating a large number of low-confidence outlier coordinates. This significantly reduces the computational load of subsequent weighted fusion and minimizes the interference of erroneous locations on the final positioning result.

[0086] See one example. Figure 3 This is a schematic diagram of an unmanned vessel navigation scenario provided in an embodiment of this application. Figure 3 As shown, A1 to An are the first position points, and P1 to Pj are the second position points. Taking the i-th first position point Ai as an example, its corresponding azimuth sequence can include the azimuths corresponding to the four second position points P1, P2, P3, and Pj. Figure 1 The method in this embodiment calculates the positioning information of Ai based on the azimuth sequence corresponding to Ai.

[0087] Understandably, at each second location point, the unmanned surface vessel (USV) can simultaneously record the azimuth angles of multiple first locations relative to the current second location point. This allows for parallel calculation of the positioning information of multiple first locations, improving mapping efficiency. For example, at the second location point P1, simultaneously recording the azimuth angles of A1, A2, A3, and A4 relative to P1 generates four azimuth angle sequences (the azimuth angle sequences corresponding to A1-A4). At the second location point P2, simultaneously recording the azimuth angles of A3, A4, A5, Ai, Ai+1, An-1, and An-3 relative to P1 generates seven azimuth angle sequences (the azimuth angle sequences corresponding to A3-A5, Ai, Ai+1, An-3, and An-1).

[0088] See another example. Figure 4 This is a schematic diagram of an unmanned vessel navigation scenario provided in another embodiment of this application. For example... Figure 4 As shown, A1 to A3 and Ai are the first position points, and P1 to Pj are the second position points. Taking the i-th first position point Ai as an example, its corresponding azimuth sequence can include the azimuths corresponding to the four second position points P1, P2, P3, and Pj. Figure 1 The method in this embodiment calculates the positioning information of Ai based on the azimuth sequence corresponding to Ai.

[0089] See another example. Figure 5 This is a schematic diagram of an unmanned vessel navigation scenario provided in another embodiment of this application. For example... Figure 5As shown, A1 to A3 and Ai are the first position points, and P1 to Pj are the second position points. Taking the i-th first position point Ai as an example, its corresponding azimuth sequence can include the azimuths corresponding to the four second position points P1, P2, P3, and Pj. Figure 1 The method in this embodiment calculates the positioning information of Ai based on the azimuth sequence corresponding to Ai.

[0090] from Figures 3 to 5 The unmanned vessel navigation scenario shown demonstrates its ability to navigate complex aquatic environments, such as... Figure 3 Narrow, winding waterways, such as Figure 4 The winding shoreline of the lake, such as Figure 5 By analyzing the curved shoreline of the islands, characteristic points at the junctions of the water and shore can be identified as primary location points. After determining the location information of each primary location point, a boundary environment map of the complex waterway can be drawn based on this information.

[0091] In this embodiment, multiple location points along the unmanned surface vessel's (USV) path are used as known baselines. The azimuth angles between each location point and feature points in the navigation environment, acquired by a monocular vision device, are combined to locate the feature points in the navigation environment. Mapping is then performed based on the location information of these feature points. This method allows for navigation environment mapping using only a monocular vision device, eliminating the need for high-cost sensing equipment such as binocular vision acquisition devices or lidar, thus reducing the USV's hardware load and cost. Furthermore, locating feature points based on the relative azimuth angles between multiple USV path points and feature points reduces calculation errors caused by single outliers, improving mapping accuracy. This method balances hardware cost and mapping accuracy, effectively addressing the problem of limited payload capacity preventing high-precision mapping, especially for small USVs.

[0092] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0093] Corresponding to the unmanned vessel mapping method described in the above embodiments, Figure 6 This is a structural block diagram of the unmanned vessel mapping device provided in the embodiments of this application. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0094] Reference Figure 6 The device 6 includes: The acquisition unit 61 is used to acquire multiple first position points in the target environment where the unmanned vessel is located, collected by the monocular vision device of the unmanned vessel during the navigation of the unmanned vessel.

[0095] The acquisition unit 62 is used to acquire, for any one of the first position points, the azimuth angle sequence of the unmanned vessel relative to the first position point through the monocular vision device; wherein, the azimuth angle sequence includes multiple second position points along the unmanned vessel's navigation path and the azimuth angles corresponding to each of the multiple second position points, and the azimuth angle corresponding to each second position point is the azimuth angle of the first position point relative to the second position point.

[0096] The positioning unit 63 is used to calculate the positioning information of the first position point based on the azimuth sequence.

[0097] Mapping unit 64 is used to generate a map of the target environment based on the positioning information of each of the first location points in the target environment.

[0098] Optionally, the positioning unit 63 is also used for: Multiple predicted positions of the first position point are calculated based on the azimuth sequence; The positioning information of the first location point is determined based on multiple predicted locations of the first location point.

[0099] Optionally, the positioning unit 63 is also used for: The second position points in the azimuth sequence are combined in pairs to obtain multiple position groups; A predicted position of the first position point is calculated based on the azimuth angles corresponding to the two second position points in each position group.

[0100] Optionally, the positioning unit 63 is also used for: Calculate the confidence level corresponding to each predicted position based on the two second position points in each position group; The location information of the first location is determined based on the confidence level of each of the multiple predicted locations.

[0101] Optionally, the positioning unit 63 is also used for: The first score is calculated based on the length of the line connecting two of the second position points in the position group; The second score is calculated based on the intersection angle formed by the lines connecting each of the two second position points in the position group to the predicted position corresponding to the position group. The confidence level of the predicted location corresponding to the location group is calculated based on the first score and the second score.

[0102] Optionally, the positioning unit 63 is also used for: Calculate the sum of the confidence levels corresponding to each of the multiple predicted locations to obtain the first data; Calculate the ratio of the confidence level corresponding to each predicted location to the first data to obtain the second data; Using the confidence level corresponding to each of the multiple predicted locations as weights, the second data corresponding to each of the multiple predicted locations are weighted and summed to obtain the positioning information of the first location point.

[0103] Optionally, the positioning unit 63 is also used for: For each of the first location points, if the number of predicted locations corresponding to the first location point reaches a preset value, then the first N predicted locations among the multiple predicted locations corresponding to the first location point are retained in descending order of confidence.

[0104] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0105] in addition, Figure 6 The unmanned surface vessel mapping device shown can be a software unit, a hardware unit, or a combination of software and hardware built into an existing terminal device, or it can be integrated into the terminal device as an independent component, or it can exist as an independent terminal device.

[0106] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0107] See Figure 7 This is a schematic diagram of the architecture of the unmanned vessel provided in an embodiment of this application. It is intended as an example and not a limitation. Figure 7 As shown, the unmanned surface vessel may include a monocular vision device 71 and a processor 72. The monocular vision device 71 can interact with the processor 72 to exchange data.

[0108] The monocular vision device 71 is used to acquire images of the target environment in which the unmanned vessel is located. Optionally, the monocular vision device 71 can be a monocular camera.

[0109] The processor 72 can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0110] The processor 72 is configured to: During the unmanned surface vessel's (USV) navigation, multiple first location points in the target environment where the USV is located are acquired by the USV's monocular vision device. For any given first location point, the azimuth sequence of the USV relative to the first location point is acquired through the monocular vision device. The azimuth sequence includes multiple second location points along the USV's navigation path and the azimuth angles corresponding to each of the second location points. The azimuth angle corresponding to each second location point is the azimuth angle of the first location point relative to the second location point. The positioning information of the first location points is calculated based on the azimuth sequence. A map of the target environment is generated based on the positioning information of each first location point in the target environment.

[0111] In some embodiments, the unmanned surface vessel (USV) may further include a memory. The memory may store a computer program that can run on a processor 72, which, when executed, implements the steps described in any of the various USV mapping method embodiments above.

[0112] Optionally, the memory may also store the first position point acquired by the monocular vision device 71 and the azimuth sequence of the unmanned vessel.

[0113] Optionally, the memory may also store multiple predicted locations obtained during the execution of the unmanned vessel mapping method, as well as the confidence level corresponding to each predicted location.

[0114] In some embodiments, the memory can be an internal storage unit of the unmanned surface vessel (USV), such as its hard drive or RAM. In other embodiments, the memory can be an external storage device, such as a plug-in hard drive, smart media card (SMC), secure digital card (SD), or flash card. Furthermore, the memory can include both internal and external storage units. The memory is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory can also be used to temporarily store data that has been output or will be output.

[0115] In some embodiments, the unmanned vessel may further include a positioning device for acquiring the unmanned vessel's location information.

[0116] Understandable. Figure 7 This is merely an example of an unmanned vessel and does not constitute a limitation on unmanned vessels. It may include more or fewer components than shown in the illustration, or a combination of certain components, or different components, such as input / output devices, network access devices, etc.

[0117] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the steps in the above-described method embodiments.

[0118] This application provides a computer program product that, when run on a terminal device, enables the terminal device to implement the steps described in the various method embodiments.

[0119] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a device / terminal equipment, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0120] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0121] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0122] In the embodiments provided in this application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0123] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0124] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for mapping unmanned surface vessels, characterized in that, include: During the navigation of the unmanned vessel, multiple first location points in the target environment where the unmanned vessel is located are acquired by the monocular vision device of the unmanned vessel. For any first location point, the azimuth angle sequence of the unmanned vessel relative to the first location point is obtained through the monocular vision device; wherein, the azimuth angle sequence includes multiple second location points along the unmanned vessel's navigation path and the azimuth angles corresponding to each of the multiple second location points, and the azimuth angle corresponding to each second location point is the azimuth angle of the first location point relative to the second location point. The positioning information of the first location point is calculated based on the azimuth sequence; A map of the target environment is generated based on the location information of each of the first location points in the target environment.

2. The unmanned surface vessel mapping method as described in claim 1, characterized in that, The step of calculating the positioning information of the first location point based on the azimuth sequence includes: Multiple predicted positions of the first position point are calculated based on the azimuth sequence; The positioning information of the first location point is determined based on multiple predicted locations of the first location point.

3. The unmanned surface vessel mapping method as described in claim 2, characterized in that, The step of calculating multiple predicted positions of the first position point based on the azimuth sequence includes: The second position points in the azimuth sequence are combined in pairs to obtain multiple position groups; A predicted position of the first position point is calculated based on the azimuth angles corresponding to the two second position points in each position group.

4. The unmanned surface vessel mapping method as described in claim 3, characterized in that, The step of determining the positioning information of the first location point based on multiple predicted locations of the first location point includes: Calculate the confidence level corresponding to each predicted position based on the two second position points in each position group; The positioning information of the first location point is determined based on the confidence level of each of the multiple predicted locations.

5. The unmanned surface vessel mapping method as described in claim 4, characterized in that, The step of calculating the confidence level corresponding to each predicted position based on the two second position points in each position group includes: The first score is calculated based on the length of the line connecting two of the second position points in the position group; The second score is calculated based on the intersection angle formed by the lines connecting each of the two second position points in the position group to the predicted position corresponding to the position group. The confidence level of the predicted location corresponding to the location group is calculated based on the first score and the second score.

6. The unmanned surface vessel mapping method as described in claim 4, characterized in that, The step of determining the location information of the first location based on the confidence level corresponding to each of the plurality of predicted locations includes: Calculate the sum of the confidence levels corresponding to each of the multiple predicted locations to obtain the first data; Calculate the ratio of the confidence level corresponding to each predicted location to the first data to obtain the second data; Using the confidence level corresponding to each of the multiple predicted locations as weights, the second data corresponding to each of the multiple predicted locations are weighted and summed to obtain the positioning information of the first location point.

7. The unmanned surface vessel mapping method as described in any one of claims 4 to 6, characterized in that, The method further includes: For each of the first location points, if the number of predicted locations corresponding to the first location point reaches a preset value, then the first N predicted locations among the multiple predicted locations corresponding to the first location point are retained in descending order of confidence.

8. An unmanned surface vessel, characterized in that, include: A monocular vision device is used to acquire images of the target environment in which the unmanned vessel is located; The processor is configured as follows: During the navigation of the unmanned vessel, multiple first location points in the target environment where the unmanned vessel is located are acquired by the monocular vision device of the unmanned vessel. For any first location point, the azimuth angle sequence of the unmanned vessel relative to the first location point is obtained through the monocular vision device; wherein, the azimuth angle sequence includes multiple second location points along the unmanned vessel's navigation path and the azimuth angles corresponding to each of the multiple second location points, and the azimuth angle corresponding to each second location point is the azimuth angle of the first location point relative to the second location point. The positioning information of the first location point is calculated based on the azimuth sequence; A map of the target environment is generated based on the location information of each of the first location points in the target environment.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

Images