Methods for updating search strategy sets and methods for covering search clusters of autonomous vehicles

Abstract

This application provides a method for updating a search strategy set and a method for coverage search of an autonomous vehicle cluster. The method includes: determining the search perception range corresponding to the current location of the autonomous vehicles in the cluster; determining whether a subset of search strategies corresponding to the search perception range exists in the search strategy set; the subset of search strategies includes at least one search strategy; if a subset of search strategies exists, determining a matching search strategy from the subset and adjusting the matching search strategy to obtain candidate search strategies; and updating the search strategy set using the candidate search strategies. This method can improve the search efficiency of coverage search of an autonomous vehicle cluster.

Description

Technical Field

[0001] This application relates to the field of search operation technology, and in particular to a method and apparatus for updating a search strategy set, a method and apparatus for unmanned vehicle cluster coverage search, terminal equipment, unmanned surface vessel, and computer-readable storage medium. Background Technology

[0002] In recent years, the application of unmanned vehicles (UAVs) to search pre-defined areas for target finding or obstacle removal has become increasingly widespread. For example, swarms of unmanned surface vessels (USVs) can be used to conduct comprehensive searches of pre-defined waters, or swarms of drones can be used to patrol pre-defined areas. In practical applications, if precise map data of the pre-defined area is not available beforehand, current technical solutions generally involve setting a search strategy set based on historical search experience for the area. This set of search strategies includes the location of the target and / or the search path. When the UAV swarm needs to search the pre-defined area, the search strategy corresponding to each UAV in the swarm is determined from the set of search strategies. Each UAV then executes its corresponding search task according to its determined search strategy, thereby achieving comprehensive searching of the pre-defined area.

[0003] However, due to limited historical search experience, when a coverage search of a preset area is required, it cannot be guaranteed that the search strategy determined from the search strategy set can meet the required search coverage rate (e.g., achieving over 90% coverage within 5 minutes). In other words, to achieve the target search coverage rate, the number of searches by the autonomous vehicle cluster needs to be increased. Therefore, using the current technical solution for coverage search by the autonomous vehicle cluster results in low search efficiency.

[0004] Therefore, how to improve the search efficiency of unmanned vehicle clusters for coverage search is a technical problem that needs to be solved by those skilled in the art. Summary of the Invention

[0005] The purpose of this application is to provide a method and apparatus for updating a search strategy set, a method and apparatus for coverage search of an unmanned equipment cluster, a terminal device, an unmanned surface vessel, and a computer-readable storage medium, with the aim of improving the search efficiency of coverage search of an unmanned equipment cluster.

[0006] Firstly, this application provides a method for updating a search strategy set. The method includes:

[0007] Determine the search and perception range of the autonomous vehicles in the autonomous vehicle cluster at their current location;

[0008] Determine whether a subset of search strategies exists in the search strategy set that corresponds to the search perception range; the subset of search strategies includes at least one search strategy.

[0009] If the subset of search strategies does not exist in the search strategy set, then a candidate search strategy corresponding to the search awareness range is created;

[0010] The search strategy set is updated using the candidate search strategies.

[0011] In one embodiment, if the subset of search strategies does not exist in the search strategy set, a candidate search strategy corresponding to the search awareness range is created, and the process proceeds to the step of updating the search strategy set using the candidate search strategy.

[0012] In one embodiment, each search strategy in the search strategy set is provided with corresponding encoding information; determining whether a subset of search strategies in the search strategy set exists that corresponds to the search perception range includes:

[0013] Determine the coding information to be searched corresponding to the search perception range;

[0014] Based on the correspondence between the code information to be searched and each code information in the search strategy set, determine whether there exists a subset of search strategies in the search strategy set that corresponds to the code information to be searched.

[0015] In one embodiment, determining the search-to-be-searched encoding information corresponding to the search perception range includes:

[0016] Establish a grid map corresponding to the search and sensing range;

[0017] For each grid cell in the grid diagram, the encoding value of the grid cell is determined based on the actual region state corresponding to the grid cell; wherein, if the pheromone concentration of the actual region corresponding to the grid cell is greater than or equal to a preset concentration threshold, or if there is an obstacle in the actual region corresponding to the grid cell, the encoding value of the grid cell is determined to be a first preset value; otherwise, the encoding value of the grid cell is determined to be a second preset value.

[0018] The encoding information to be searched corresponding to the raster map is determined based on the encoding value corresponding to each of the raster units.

[0019] In one embodiment, determining a matching search strategy from the subset of search strategies and adjusting the matching search strategy to obtain candidate search strategies includes:

[0020] Determine the strategy score corresponding to each search strategy in the subset of search strategies, and determine the matching search strategy based on the highest strategy score among the strategy scores;

[0021] The matching search strategy is adjusted to obtain candidate search strategies.

[0022] In one embodiment, updating the search strategy set using the candidate search strategy includes:

[0023] Obtain the candidate strategy score of the candidate search strategy;

[0024] The search strategy set is updated according to the ranking relationship between the candidate strategy scores and the strategy scores corresponding to each search strategy in the search strategy subset.

[0025] In one embodiment, the method for updating a search strategy set further includes:

[0026] Determine the strategy similarity between each search strategy in the subset of search strategies and the candidate search strategies;

[0027] The search strategies corresponding to the similarity scores of the strategies that exceed the similarity threshold are identified as search strategies to be confirmed.

[0028] Correspondingly, updating the search strategy set based on the score ranking relationship between the candidate strategy scores and the strategy scores corresponding to each search strategy in the search strategy subset includes:

[0029] The search strategy set is updated according to the score ranking relationship between the candidate strategy scores and the search strategy to be confirmed.

[0030] In one embodiment, obtaining the candidate strategy score of the candidate search strategy includes:

[0031] The relative positions of the candidates to be searched are determined according to the candidate search strategy.

[0032] The absolute position of the candidate to be searched is determined based on the relative position of the candidate and the current position;

[0033] After the autonomous driving device performs a search task based on the candidate absolute position, the candidate strategy score of the candidate search strategy is determined according to the corresponding search coverage.

[0034] In one embodiment, the method for updating a search strategy set further includes:

[0035] If the real-time distance between any of the autonomous driving devices and any of the candidate absolute positions is less than or equal to a preset distance threshold, and / or the pheromone concentration corresponding to any of the candidate absolute positions exceeds a preset concentration threshold, then return to the step of determining the search and perception range of the autonomous driving devices in the autonomous driving device cluster at the current position.

[0036] Secondly, this application also provides another method for covering and searching a cluster of unmanned vehicles, applicable to any unmanned vehicle in a cluster of unmanned vehicles, the method comprising:

[0037] Obtain the real-time search and perception range of the unmanned vehicle at the target's real-time location;

[0038] The target search strategy corresponding to the real-time search perception range is determined from the search strategy set; the search strategy set is obtained using the search strategy set update method described above;

[0039] Control the unmanned vehicle to perform the search task according to the target search strategy.

[0040] Thirdly, this application also provides an apparatus for updating a search strategy set. The apparatus includes:

[0041] The range determination module is used to determine the search and perception range of the autonomous driving equipment at its current location;

[0042] The determination module is used to determine whether there exists a subset of search strategies in the search strategy set that corresponds to the search perception range; the subset of search strategies includes at least one search strategy.

[0043] The first execution module is configured to determine a matching search strategy from the search strategy subset if the search strategy subset exists in the search strategy set, and adjust the matching search strategy to obtain a candidate search strategy.

[0044] An update module is used to update the search strategy set using the candidate search strategies.

[0045] Fourthly, this application also provides another unmanned vehicle cluster coverage search device. The device includes:

[0046] The acquisition module is used to acquire the real-time search and perception range of the unmanned vehicle at the real-time location of the target;

[0047] A strategy determination module is used to determine a target search strategy corresponding to the real-time search perception range from a search strategy set; the search strategy set is obtained using the search strategy set update method described above.

[0048] The search module is used to control the unmanned vehicle to perform search tasks according to the target search strategy.

[0049] Fifthly, this application also provides a terminal device. The terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described above.

[0050] Sixthly, this application also provides an unmanned surface vessel (USV) comprising a USV body and a controller for performing the steps of the method as described in any of the preceding claims.

[0051] Seventhly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method described above.

[0052] This application provides a method for updating a search strategy set. After determining the search perception range corresponding to the current location of each autonomous vehicle in an autonomous vehicle cluster, and confirming the existence of a subset of search strategies corresponding to that range within the search strategy set, this method determines a matching search strategy from the subset. Candidate search strategies are then determined by adjusting the information of the matching search strategies, and the search strategy set is updated and expanded using these candidate strategies. Therefore, when an autonomous vehicle in the cluster determines a target search strategy from the search strategy set determined by the method according to this application, the probability that the determined target search strategy meets the coverage search requirements is higher. In other words, this method can improve the search efficiency of coverage searches performed by an autonomous vehicle cluster.

[0053] It is understood that the search strategy set update apparatus, unmanned vehicle cluster coverage search method and apparatus, terminal device, unmanned surface vessel and computer-readable storage medium provided in the embodiments of this application have the same beneficial effects as the search strategy set update method described above, and will not be repeated here. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0055] Figure 1 A flowchart illustrating a method for updating a search strategy set as provided in this application embodiment;

[0056] Figure 2 This application provides a schematic diagram illustrating a process for determining the coded information to be searched corresponding to the search sensing range, as provided in an embodiment of the present application.

[0057] Figure 3 A schematic diagram illustrating a search target location provided in an embodiment of this application;

[0058] Figure 4 A schematic diagram illustrating a method for calculating strategy similarity provided in an embodiment of this application;

[0059] Figure 5 A schematic diagram illustrating another method for updating a search strategy set provided in this application embodiment;

[0060] Figure 6 A flowchart illustrating a cluster coverage search method for unmanned vehicles provided in this application embodiment;

[0061] Figure 7 The diagram shown is a structural schematic of a search strategy set update device provided in an embodiment of this application;

[0062] Figure 8 The diagram shown is a structural schematic of an unmanned vehicle cluster coverage search device provided in an embodiment of this application;

[0063] Figure 9 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. Detailed Implementation

[0064] 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, devices, circuits, and methods are omitted so as not to obscure the description of this application with unnecessary detail.

[0065] 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.

[0066] 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.

[0067] 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]."

[0068] 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.

[0069] 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. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized. "A plurality" means "two or more."

[0070] This application provides a method for updating a search strategy set, which can be executed by the processor of a terminal device when running a corresponding computer program.

[0071] Figure 1 The flowchart illustrates a method for updating a search strategy set according to an embodiment of this application. For ease of explanation, only the parts relevant to this embodiment are shown. The method provided in this embodiment includes the following steps:

[0072] S110: Determine the search and perception range of the unmanned vehicles in the unmanned vehicle cluster at the current location.

[0073] The unmanned equipment cluster refers to a cluster composed of various unmanned equipment; unmanned equipment includes unmanned boats, drones, and automatic sweeping machines, etc. This embodiment does not limit the specific type of unmanned equipment.

[0074] The search and perception range refers to the area that an autonomous vehicle can cover during a search using pre-set detection devices. The search and perception range of an autonomous vehicle varies depending on its location.

[0075] Specifically, after identifying each autonomous vehicle in the autonomous vehicle cluster, the current location of each autonomous vehicle is obtained, and for each current location, the corresponding search and perception range is determined.

[0076] S120: Determine whether there exists a subset of search strategies in the search strategy set that corresponds to the search perception range; the subset of search strategies includes at least one search strategy.

[0077] The search strategy subset refers to a set of strategies corresponding to the search perception range, including at least one search strategy; the search strategy includes the search target location and / or search path, and the search target location refers to the specific location that the autonomous vehicle needs to drive to when performing the coverage search task; in actual operation, the search target location can also be represented by the search target.

[0078] It is understandable that the search strategy needs to be determined based on the search perception range, and the same search perception range can correspond to multiple different search strategies (such as the search target location). Therefore, after determining the search perception range corresponding to the current location, it is necessary to query whether there is a search strategy in the search strategy set that matches the search perception range. If there is at least one search strategy that matches the search perception range, then a subset of search strategies is determined based on at least one search strategy, indicating that there is a subset of search strategies in the search strategy set that corresponds to the search perception range. If there is no search strategy that matches the search perception range, then it means that there is no subset of search strategies in the search strategy set that corresponds to the search perception range.

[0079] S130: If a subset of search strategies exists in the search strategy set, a matching search strategy is determined from the subset of search strategies, and the matching search strategy is adjusted to obtain a candidate search strategy.

[0080] Here, the matching search strategy refers to the search strategy determined from a subset of search strategies according to preset matching rules. For example, when the subset of search strategies includes multiple search strategies, the search strategy with the highest strategy score among all search strategies can be determined as the matching search strategy.

[0081] Specifically, after determining the matching search strategy from the subset of search strategies, the matching search strategy is adjusted to obtain candidate search strategies; that is, the candidate search strategies are derived based on the matching search strategy through information adjustment. This information adjustment includes adjusting the parameters in the matching search strategy based on the parameter adjustment range to obtain an updated search strategy, i.e., determining the candidate search strategies.

[0082] S140: Update the search strategy set using candidate search strategies.

[0083] Specifically, after determining the candidate search strategies, the candidate search strategies are compared with each search strategy in the search strategy set according to preset comparison rules to determine the merits of the candidate search strategies and each search strategy; the worst search strategy among the candidate search strategies and each search strategy in the search strategy set is determined; if the worst search strategy is a candidate search strategy, it is deleted; if the worst search strategy is a search strategy in the search strategy set, it is replaced by a candidate search strategy, and the search strategy set is updated. The worst search strategy can be determined based on a comparison of the strategy scores corresponding to the search strategies; this embodiment does not limit the preset comparison rules.

[0084] It should be noted that after the search strategy set is determined, the search strategy set can be forwarded and output so that other autonomous vehicles in the autonomous vehicle cluster or other autonomous vehicle clusters can obtain the search strategy set.

[0085] This application provides a method for updating a search strategy set. After determining the search perception range corresponding to the current location of each autonomous vehicle in an autonomous vehicle cluster, and confirming the existence of a subset of search strategies corresponding to that range in the search strategy set, this method determines a matching search strategy from the subset. Candidate search strategies are then determined by adjusting the matching search strategies, and the search strategy set is updated and expanded using these candidate strategies. Therefore, when an autonomous vehicle in the cluster determines a target search strategy from the search strategy set determined by the method of this application, the probability that the determined target search strategy meets the coverage search requirements is higher. In other words, this method can improve the search efficiency of coverage searches performed by an autonomous vehicle cluster.

[0086] Based on the above embodiments, this embodiment further explains and optimizes the technical solution. Specifically, in this embodiment, a method for updating a search strategy set further includes: if there is no subset of search strategies in the search strategy set, then creating a candidate search strategy corresponding to the search perception range, and proceeding to the step of updating the search strategy set using the candidate search strategy.

[0087] In this step, if no subset of search strategies exists in the search strategy set, a new search strategy is randomly generated, thus obtaining candidate search strategies. In practice, if the search strategy is to search for a target location, a target location is randomly generated, and the candidate search strategies are obtained by selecting the target locations that correspond to the search perception range of the current location from the randomly generated target locations.

[0088] Specifically, after determining the candidate search strategies, the candidate search strategies are compared with each search strategy in the search strategy set according to preset comparison rules to determine the merits of the candidate search strategies and each search strategy; the worst search strategy among the candidate search strategies and each search strategy in the search strategy set is determined; if the worst search strategy is a candidate search strategy, it is deleted; if the worst search strategy is a search strategy in the search strategy set, it is replaced by a candidate search strategy, and the search strategy set is updated. The worst search strategy can be determined based on a comparison of the strategy scores corresponding to the search strategies; this embodiment does not limit the preset comparison rules.

[0089] In this embodiment, candidate search strategies are determined according to the existence of a subset of search strategies in the search strategy set that corresponds to the search perception range. Therefore, this method can further improve the search efficiency of coverage search of unmanned equipment clusters.

[0090] Based on the above embodiments, this embodiment further explains and optimizes the technical solution. Specifically, in this embodiment, each search strategy in the search strategy set is provided with corresponding encoding information; determining whether there is a subset of search strategies in the search strategy set that corresponds to the search perception range includes:

[0091] Determine the coding information to be searched that corresponds to the search perception range;

[0092] Based on the correspondence between the coding information to be searched and the coding information in the search strategy set, determine whether there exists a subset of search strategies in the search strategy set that corresponds to the coding information to be searched.

[0093] The encoded information refers to the encoding corresponding to the search perception range, which can be represented by a string.

[0094] Specifically, after determining the search perception range, the search perception range is encoded according to a preset encoding rule to obtain the search-to-be-searched encoded information corresponding to the search perception range, that is, the search perception range is represented by the search-to-be-searched encoded information; then, according to the correspondence between the search-to-be-searched encoded information and the encoded information in the search strategy set, the same encoded information as the search-to-be-searched encoded information is queried in the search strategy set, and the search strategy corresponding to the same encoded information as the search-to-be-searched encoded information is determined. Based on the determined search strategy, a subset of search strategies is derived, and it is determined that a subset of search strategies exists in the search strategy set; if no encoded information as the same as the search-to-be-searched encoded information exists in the search strategy set, it is determined that no subset of search strategies exists in the search strategy set.

[0095] As can be seen, the method of this embodiment can efficiently and conveniently determine whether there is a subset of search strategies in the search strategy set that corresponds to the search perception range.

[0096] In one specific embodiment, determining the encoding information to be searched corresponding to the search sensing range includes:

[0097] Establish a grid map corresponding to the search and sensing range;

[0098] For each grid cell in the grid map, the encoding value of the grid cell is determined based on the actual region state corresponding to the grid cell. If the pheromone concentration of the actual region corresponding to the grid cell is greater than or equal to a preset concentration threshold, or if there is an obstacle in the actual region corresponding to the grid cell, the encoding value of the grid cell is determined to be a first preset value; otherwise, the encoding value of the grid cell is determined to be a second preset value. The pheromone concentration is a quantitative value representing the degree to which the corresponding actual region is searched by the autonomous driving equipment cluster.

[0099] The encoding information to be searched corresponding to the raster map is determined based on the encoding value corresponding to each raster cell.

[0100] Raster maps refer to a data organization method that uses a two-dimensional matrix (rows and columns or grids) to represent the distribution of spatial features or phenomena. Each matrix unit is called a raster cell.

[0101] Specifically, a grid map corresponding to the search sensing range is established according to a preset method; for each grid cell in the grid map, the actual area state corresponding to the grid cell is obtained, and the grid cell is encoded based on the actual area state to determine the encoding value of the grid cell; after determining the encoding value corresponding to each grid cell, the encoding information to be searched corresponding to the grid map is determined based on the encoding value corresponding to each grid cell.

[0102] In this embodiment, the encoding value corresponding to the grid cell is determined based on the pheromone concentration and the presence of obstacles. Specifically, if the pheromone concentration in the actual area corresponding to the grid cell is greater than or equal to a preset concentration threshold, or if there are obstacles in the actual area corresponding to the grid cell, the encoding value of the grid cell is determined to be a first preset value; otherwise, the encoding value of the grid cell is determined to be a second preset value.

[0103] Here, pheromone concentration is a quantitative value representing the degree to which a corresponding real-world area is searched by a cluster of autonomous vehicles. In practice, pheromone concentration can be set to be positively correlated with search intensity, meaning the shorter the time an area is searched, the higher its pheromone concentration; or negatively correlated, meaning the shorter the time an area is searched, the lower its pheromone concentration. In one example, assuming a positive correlation between pheromone concentration and search intensity, if a real-world area is searched by autonomous vehicles within 5 minutes, its pheromone concentration is high; if a real-world area is not searched by any autonomous vehicles within 5 minutes, its pheromone concentration is low. Within a preset timeframe, the more autonomous vehicles search a real-world area, the higher its pheromone concentration. Furthermore, the initial pheromone concentration for each real-world area is 0, indicating that coverage searching has not yet begun.

[0104] Specifically, for each grid cell in the raster image, the pheromone concentration of the actual area corresponding to each grid cell is determined, and a preset concentration threshold determined in advance according to the setting rules of pheromone concentration is obtained. Then, the encoding value of the grid cell is determined based on the comparison result between the preset concentration and the preset concentration threshold.

[0105] For example, in one embodiment, if the pheromone concentration is positively correlated with the search intensity, and if the pheromone concentration in the actual area corresponding to the grid unit is greater than or equal to a preset concentration threshold, then the encoding value of the grid unit is determined to be a first preset value; in addition, it is determined whether there are obstacles (including other autonomous driving devices) in the actual area corresponding to the grid unit. If there are obstacles in the actual area, then the encoding value of the grid unit is determined to be the first preset value; if the pheromone concentration in the actual area corresponding to the grid unit is less than the preset concentration threshold and there are no obstacles (including other autonomous driving devices) in the actual area corresponding to the grid unit, then the encoding value of the grid unit is determined to be a second preset value.

[0106] In another embodiment, if the pheromone concentration is negatively correlated with the search intensity, and if the pheromone concentration in the actual area corresponding to the grid unit is less than or equal to a preset concentration threshold, then the encoding value of the grid unit is determined to be a first preset value. Additionally, it is determined whether there are obstacles (including other autonomous driving devices) in the actual area corresponding to the grid unit. If there are obstacles in the actual area, then the encoding value of the grid unit is determined to be the first preset value. If the pheromone concentration in the actual area corresponding to the grid unit is equal to the preset concentration threshold and there are no obstacles (including other autonomous driving devices) in the actual area corresponding to the grid unit, then the encoding value of the grid unit is determined to be a second preset value.

[0107] Figure 2This is a schematic diagram illustrating a process for determining the encoded information to be searched corresponding to the search sensing range, provided as an embodiment of this application. In this embodiment, the pheromone concentration is positively correlated with the search intensity. Figure 2 As shown, the current position of the autonomous driving device is taken as the center point of the grid map, and the search and perception range of the autonomous driving device is taken as the extension range of the grid map. The grid map (nine-square matrix) is divided, and the search-to-be-searched encoding information (binary encoding) corresponding to the search and perception range is determined based on the nine-square matrix. Specifically, in this nine-square matrix, the encoding value of the grid cell corresponding to the current position of the autonomous driving device is 1; the pheromone concentration of the actual area corresponding to the grid cell is obtained. If the pheromone concentration is greater than or equal to 0.5, the encoding value of the grid cell is determined to be 1, or if there is an obstacle (including other autonomous driving devices) in the grid cell, the encoding value of the corresponding grid cell is determined to be 1; otherwise, that is, if the pheromone concentration is less than 0.5 and there is no obstacle (including other autonomous driving devices) in the grid cell, the encoding value of the grid cell is determined to be 0; the search-to-be-searched encoding information corresponding to the nine-square matrix is ​​determined to be 100011011 in the above manner.

[0108] According to the method of this embodiment, the code information to be searched corresponding to the search sensing range can be determined efficiently and conveniently, and the actual regional state of the corresponding search sensing range can be accurately represented.

[0109] Based on the above embodiments, this embodiment further explains and optimizes the technical solution. Specifically, in this embodiment, a matching search strategy is determined from a subset of search strategies, and information adjustment is performed on the matching search strategy to obtain candidate search strategies, including:

[0110] Determine the strategy score corresponding to each search strategy in the subset of search strategies, and determine the matching search strategy based on the highest strategy score among all strategy scores;

[0111] The matching search strategy is adjusted based on the information to obtain candidate search strategies.

[0112] The strategy score is a quantitative value used to determine the merits of a search strategy. In this embodiment, after determining a subset of search strategies, the strategy score corresponding to each search strategy in the subset is obtained, and the relationship between the strategy scores is compared to determine the highest strategy score. The search strategy corresponding to the highest strategy score is then determined as the matching search strategy. Based on the matching search strategy, information adjustment is performed to obtain candidate search strategies.

[0113] Combination Figure 3The diagram illustrates a search target location. In a specific embodiment, if the matching search strategy is to search for the target location, then the target location is its relative position to the autonomous driving device. Correspondingly, the process of adjusting the matching search strategy to obtain candidate search strategies includes: pre-setting an adjustment range for the target location; adjusting the target location based on the adjustment range; for example, modifying the horizontal and / or vertical coordinates of the target location within the adjustment range to obtain new coordinates, which are then the modified target location, thus obtaining the candidate search strategy.

[0114] In this embodiment, the search strategy corresponding to the highest strategy score in the search strategy subset is determined as the matching search strategy, and information is adjusted based on the matching search strategy to obtain candidate search strategies, thereby relatively guaranteeing the strategy score of the determined candidate search strategies.

[0115] Based on the above embodiments, this embodiment further explains and optimizes the technical solution. Specifically, in this embodiment, updating the search strategy set using candidate search strategies includes:

[0116] Obtain candidate strategy scores for candidate search strategies;

[0117] The search strategy set is updated based on the ranking relationship between the candidate strategy scores and the strategy scores corresponding to each search strategy in the search strategy subset.

[0118] In this embodiment, after determining the candidate search strategy, the candidate strategy score corresponding to the candidate search strategy is obtained, and the strategy score corresponding to each search strategy in the search strategy subset is obtained. The candidate strategy scores and the strategy scores corresponding to each search strategy in the search strategy subset are sorted by score to determine the candidate strategy score and the lowest strategy score among all strategy scores. If the candidate strategy score is the lowest strategy score, that is, all candidate strategy scores of the candidate search strategy are less than the strategy scores of the search strategy in the search strategy subset, then the candidate search strategy is directly deleted. If the candidate strategy score of the candidate search strategy is greater than the strategy score of any search strategy in the search strategy subset, that is, there is a search strategy in the search strategy subset with a strategy score less than the candidate strategy score, then the search strategy is deleted, and the candidate search strategy is added to the search strategy set.

[0119] As can be seen, updating the search strategy set according to the method of this embodiment and iteratively deleting the search strategy with the lowest strategy score in the search strategy set can ensure that the search strategies in the search strategy set are the selected search strategies with relatively high strategy scores. Therefore, when the target search strategy is subsequently determined from the search strategy set, the target search strategy is more likely to meet the search coverage requirements.

[0120] Based on the above embodiments, this embodiment further explains and optimizes the technical solution. Specifically, in this embodiment, a method for updating a search strategy set further includes:

[0121] Determine the strategy similarity between each search strategy in the search strategy subset and the candidate search strategies;

[0122] The search strategies corresponding to the similarity scores of strategies that exceed the similarity threshold are identified as search strategies to be confirmed.

[0123] Correspondingly, the search strategy set is updated based on the ranking relationship between the candidate strategy scores and the strategy scores corresponding to each search strategy in the search strategy subset, including:

[0124] The search strategy set is updated based on the ranking relationship between the candidate strategy scores and the strategy scores corresponding to the search strategies to be confirmed.

[0125] Here, strategy similarity represents the similarity between two search strategies, which can be understood as the degree of similarity of the search target locations contained in different search strategies. In this embodiment, the strategy similarity is calculated between search strategies with the same search perception range (same encoded information), such as the strategy similarity between each search strategy in the search strategy subset and the candidate search strategy.

[0126] In this embodiment, as Figure 4 The diagram illustrates a method for calculating strategy similarity according to an embodiment of this application; determining the search target position (first relative position (Δx1, Δy1)) corresponding to the search strategy in a subset of search strategies; determining the search target position (second relative position (Δx2, Δy2)) corresponding to the candidate search strategy; and calculating the Euclidean distance between the first relative position and the second relative position. Strategy similarity is determined by Euclidean distance D; the smaller the Euclidean distance D, the higher the similarity between the two search strategies; the larger the Euclidean distance D, the lower the similarity between the two search strategies.

[0127] Specifically, a similarity threshold is pre-set. The calculated similarity of each strategy is compared with the similarity threshold, and the search strategies corresponding to similarities greater than the threshold are identified as search strategies to be confirmed. Correspondingly, the search strategy set is updated according to the ranking relationship between the candidate strategy scores and the strategy scores corresponding to the search strategies to be confirmed. In other words, in this embodiment, the search strategies to be confirmed are first selected from the subset of search strategies using strategy similarity, and then the search strategy set is updated based on the ranking relationship between the candidate strategy scores and the strategy scores of the search strategies to be confirmed.

[0128] As can be seen, the method described in this embodiment can efficiently and conveniently update the search strategy set.

[0129] Based on the above embodiments, this embodiment further explains and optimizes the technical solution. Specifically, in this embodiment, obtaining the candidate strategy score of the candidate search strategy includes:

[0130] The relative positions of the candidates to be searched are determined based on the candidate search strategy;

[0131] The absolute position of the candidate to be searched is determined based on the relative position of the candidate and the current position;

[0132] After the autonomous vehicle performs a search task based on the candidate absolute position, the candidate strategy score is determined according to the corresponding search coverage.

[0133] Here, the relative position of a candidate refers to the relative position between the search target and the autonomous vehicle in the candidate search strategy; the absolute position of a candidate refers to the actual position corresponding to the search target in the candidate search strategy. Specifically, the relative positions of the candidates to be searched are first determined according to the candidate search strategy, and then the absolute positions of the candidates to be searched are determined based on the relative positions of the candidates and the current position.

[0134] The search coverage rate is the dynamic coverage rate of the preset area, calculated based on the ratio of the searched area corresponding to each autonomous vehicle in the autonomous vehicle cluster to the preset area. Due to interference from global situational changes in the preset area, the strategy score corresponding to the same search strategy may differ at different times. That is, the strategy score corresponding to the search strategy is not constant. Search strategies and strategy scores should be continuously collected, updated, and accumulated during the cluster search task time to obtain a set of search strategies with relatively high scores.

[0135] It should be noted that as each autonomous vehicle in the autonomous vehicle cluster moves towards its corresponding candidate absolute position according to its respective candidate search strategy, the search coverage of the preset area will change in real time. The search coverage at a preset interval (e.g., 0.2s) is calculated, and it is determined whether the autonomous vehicle has met the conditions for ending the search task. These conditions include the autonomous vehicle's remaining energy being lower than a preset energy threshold, and / or the autonomous vehicle's driving time reaching a preset duration threshold. If the autonomous vehicle has not met the conditions for ending the search task, the process returns to the step "Determine the search perception range corresponding to the current position of the autonomous vehicle in the autonomous vehicle cluster," i.e., updating the search perception range based on the autonomous vehicle's current position. When the autonomous vehicle meets the conditions for ending the search task, the search coverage corresponding to the candidate search strategy for each search perception range is determined, and the strategy score corresponding to the candidate search strategy is determined based on the search coverage.

[0136] According to the method of this embodiment, the candidate strategy score of the candidate search strategy can be accurately determined.

[0137] In one specific embodiment, a method for updating a search strategy set further includes:

[0138] If the real-time distance between any autonomous vehicle and any candidate absolute position is less than or equal to a preset distance threshold, and / or the pheromone concentration corresponding to any candidate absolute position exceeds a preset concentration threshold, then return to the step of determining the search and perception range of the autonomous vehicle in the autonomous vehicle cluster at the current position.

[0139] In actual operation, as the autonomous vehicle moves toward the candidate absolute position, the current position of the autonomous vehicle is updated in real time, and the real-time distance between the current position and the candidate absolute position is calculated. If the real-time distance is less than or equal to a preset distance threshold, it means that the candidate absolute position has been searched. At this time, it is necessary to change the search target, so the process returns to the step of "determining the search perception range of the autonomous vehicle in the autonomous vehicle cluster at the current position".

[0140] In practical applications, when a certain unmanned surface vessel (USV) is traveling towards its corresponding search target (candidate absolute position), it may "pass by" the search targets (candidate absolute positions) of other USVs. For example, when USV A is traveling towards candidate absolute position a, it "passes by" the candidate absolute position b corresponding to USV B. If the real-time distance between the real-time position of USV A and the candidate absolute position b is less than a preset distance threshold, USV B also needs to update its search target.

[0141] In actual operation, as the autonomous vehicle moves toward the candidate absolute position, the pheromone concentration corresponding to the candidate absolute position is updated in real time. The judgment rule is determined according to the setting rule of pheromone concentration, and the autonomous vehicle is then determined whether it needs to update the search target, that is, whether it needs to return to the step of "determining the search perception range of the autonomous vehicle in the autonomous vehicle cluster at the current position".

[0142] In one embodiment, if the pheromone concentration is positively correlated with the search intensity, and if the pheromone concentration at the candidate absolute position exceeds a preset concentration threshold, it is determined that the search target of the autonomous driving device corresponding to the candidate absolute position needs to be updated, and the step of "determining the search perception range of the autonomous driving device in the autonomous driving device cluster at the current position" is returned.

[0143] In another embodiment, if the pheromone concentration is negatively correlated with the search intensity, and if the pheromone concentration at the candidate absolute position is lower than a preset concentration threshold, it is determined that the search target of the autonomous vehicle corresponding to the candidate absolute position needs to be updated, and the process returns to the step of "determining the search perception range of the autonomous vehicle in the autonomous vehicle cluster at the current position".

[0144] The method described in this embodiment can update the search target in a timely manner, thereby improving the efficiency of updating the search strategy set.

[0145] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application are described in detail below with reference to practical application scenarios. In this application embodiment, the determination of the search strategy set corresponding to the unmanned surface vessel swarm is used as an example for illustration. In this application embodiment, combined with... Figure 5 The diagram illustrates another method for updating the search strategy set. The specific steps of this method are as follows:

[0146] Step 1: Acquire unmanned surface vessel (USV) cluster data, iterate through each USV in the USV cluster, and for each USV, calculate the real-time distance between the current position of the USV and the candidate absolute position of the search target; if the real-time distance is less than 100 meters, or if the pheromone concentration corresponding to the candidate absolute position of the USV is greater than 0.5, proceed to Step 2; otherwise, repeat Step 1.

[0147] Step 2: Determine the new search target; this includes the following steps:

[0148] Step 2.1: Generate the search code information based on the search and perception range corresponding to the current location of the unmanned surface vessel;

[0149] Step 2.2: Check if there exists a subset of search strategies corresponding to the same search code information in the search strategy set;

[0150] Step 2.3: If a subset of search strategies exists, obtain the strategy score corresponding to each search strategy in the subset of search strategies (the subset of search strategies includes search strategies A1, A2, A3 and A4), and determine the matching search strategy corresponding to the highest strategy score;

[0151] Step 2.4: Set the adjustment range of the search target position, and adjust the search target position of the matching search strategy according to the adjustment range to obtain the candidate search strategy (as shown in A5 in the figure);

[0152] Step 2.5: If no subset of search strategies exists, randomly generate a candidate search strategy corresponding to the search awareness range (as shown in Figure A5);

[0153] Step 2.6: Determine the candidate relative position to be searched according to the candidate search strategy, and determine the candidate absolute position to be searched based on the candidate relative position and the current position;

[0154] Step 3: The unmanned boat travels towards the candidate absolute position, calculates the search coverage rate at the corresponding moment according to a preset period (such as an interval of 0.2 s), and at the same time determines whether the unmanned driving device meets the condition for ending the search task; if the unmanned driving device does not meet the condition for ending the search task, return to Step 1; if the unmanned driving device meets the condition for ending the search task, determine the search coverage rate corresponding to the candidate search strategy corresponding to each search perception range, and determine the candidate strategy score corresponding to the candidate search strategy according to the search coverage rate (such as f5 in the figure).

[0155] Step 4: Update the search strategy set; specifically, it includes the following steps:

[0156] Step 4.1: Determine the strategy similarity between each search strategy in the search strategy subset and the candidate search strategy (such as d1, d2, d3, and d4 in the figure);

[0157] Step 4.2: Determine the search strategies corresponding to the strategy similarities that exceed the similarity threshold among the strategy similarities as the search strategies to be confirmed; as shown in the figure, assume that the size relationship between each strategy similarity and the similarity threshold is: d4 < similarity threshold < d1 < d3 < d2, and determine the search strategies corresponding to d1, d3, and d2 as the search strategies to be confirmed, that is, the search strategies to be confirmed include A1, A2, and A3;

[0158] Step 4.3: Compare the size relationship between the strategy scores corresponding to the candidate search strategy and each search strategy to be confirmed. If the candidate strategy score is the lowest strategy score, directly delete the candidate search strategy; there is a search strategy in the search strategy subset whose strategy score is less than the candidate strategy score, delete this search strategy, and add the candidate search strategy to the search strategy set; as shown in the figure, assume that the size relationship between the strategy scores corresponding to the candidate search strategy and each search strategy to be confirmed is: f2 > f5 > f1 > f3, that is, f3 is the lowest strategy score, so delete the search strategy A3 corresponding to f3, and add the candidate search strategy A5 to the search strategy set.

[0159] Step 5: Repeat Steps 1 to Step 4 to achieve the experience accumulation of the unmanned boat cluster in the preset area and obtain the search strategy set.

[0160] This application provides a method for updating a search strategy set. After determining the search perception range corresponding to the current location of each autonomous vehicle in an autonomous vehicle cluster, and confirming the existence of a subset of search strategies corresponding to that range in the search strategy set, this method determines a matching search strategy from the subset. Candidate search strategies are then determined by adjusting the matching search strategies, and the search strategy set is updated and expanded using these candidate strategies. Therefore, when an autonomous vehicle in the cluster determines a target search strategy from the search strategy set determined by the method of this application, the probability that the determined target search strategy meets the coverage search requirements is higher. In other words, this method can improve the search efficiency of coverage searches performed by an autonomous vehicle cluster.

[0161] Figure 6 The flowchart illustrates a method for covering and searching a cluster of unmanned vehicles provided in this application embodiment. For ease of explanation, only the parts relevant to this embodiment are shown. The method provided in this embodiment is applied to any unmanned vehicle in an unmanned vehicle cluster and includes the following steps:

[0162] S610: Obtain the real-time search and perception range of the unmanned vehicle at the target's real-time location;

[0163] S620: Determine the target search strategy corresponding to the real-time search perception range from the search strategy set; the search strategy set is obtained using the search strategy set update method as described in any of the above embodiments;

[0164] S630: Controls unmanned vehicles to perform search tasks according to target search strategies.

[0165] Among them, the real-time location of the target refers to the real-time location of the autonomous vehicle when it is conducting a coverage search; the real-time search perception range refers to the search perception range of the autonomous vehicle at the real-time location of the target when it is conducting a coverage search.

[0166] Based on the established search strategy set, a target search strategy corresponding to the real-time search perception range is determined from the search strategy set. This target search strategy can be the search strategy with the highest strategy score corresponding to the real-time search perception range within the search strategy set. After determining the target search strategy, the autonomous driving device is controlled to execute the search task according to the target search strategy.

[0167] It should be noted that since the search strategy set is derived by adjusting the matching search strategy or by direct creation, the probability that the target search strategy determined by the autonomous vehicles in the autonomous vehicle cluster will meet the coverage search requirements is higher. In other words, this method can improve the search efficiency of coverage searches in autonomous vehicle clusters.

[0168] 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.

[0169] Figure 7 The diagram shown is a structural schematic of a search strategy set update device provided in an embodiment of this application. Figure 7 As shown, an apparatus for updating a search strategy set in this embodiment includes:

[0170] The range determination module 710 is used to determine the search and perception range of the unmanned vehicle at its current location.

[0171] The determination module 720 is used to determine whether there is a subset of search strategies in the search strategy set that corresponds to the search perception range; the subset of search strategies includes at least one search strategy.

[0172] The first execution module 730 is used to determine a matching search strategy from the search strategy subset if a search strategy subset exists in the search strategy set, and to adjust the information of the matching search strategy to obtain a candidate search strategy.

[0173] Update module 740 is used to update the search strategy set using candidate search strategies.

[0174] The search strategy set updating apparatus provided in this application embodiment has the same beneficial effects as the search strategy set updating method described above.

[0175] In one embodiment, an apparatus for updating a search strategy set further includes:

[0176] The second execution module is used to create a candidate search strategy corresponding to the search awareness range if there is no subset of search strategies in the search strategy set, and to call the update module 740.

[0177] In one embodiment, each search strategy in the search strategy set is provided with corresponding encoding information; the judgment module includes:

[0178] The first determining submodule is used to determine the coding information to be searched corresponding to the search perception range;

[0179] The second determining submodule is used to determine whether there is a subset of search strategies in the search strategy set that corresponds to the code information to be searched, based on the correspondence between the code information to be searched and the code information in the search strategy set.

[0180] In one embodiment, the first determining submodule includes:

[0181] Establishment unit, used to create a grid map corresponding to the search and sensing range;

[0182] The encoding value determination unit is used to determine the encoding value of each grid cell in the grid diagram based on the actual region state corresponding to the grid cell. The encoding value determination unit includes an encoding value determination subunit, used to determine the encoding value of each grid cell in the grid diagram as a first preset value if the pheromone concentration of the actual region corresponding to the grid cell is greater than or equal to a preset concentration threshold, or if there is an obstacle in the actual region corresponding to the grid cell; otherwise, it determines the encoding value of the grid cell as a second preset value. The pheromone concentration is a quantified value representing the degree to which the corresponding actual region is searched by the autonomous driving equipment cluster.

[0183] The encoding information determination unit is used to determine the encoding information to be searched corresponding to the raster map based on the encoding value corresponding to each raster cell.

[0184] In one embodiment, the first execution module determines a matching search strategy from a subset of search strategies and adjusts the matching search strategies to obtain candidate search strategies, including:

[0185] The strategy determination submodule is used to determine the strategy score corresponding to each search strategy in the search strategy subset, and to determine the matching search strategy based on the highest strategy score among all strategy scores.

[0186] The information adjustment submodule is used to adjust the information of the matching search strategy to obtain candidate search strategies.

[0187] In one embodiment, the update module includes:

[0188] The scoring acquisition submodule is used to obtain the candidate strategy scores for candidate search strategies;

[0189] The update submodule is used to update the search strategy set based on the score ranking relationship between the candidate strategy scores and the strategy scores corresponding to each search strategy in the search strategy subset.

[0190] In one embodiment, an apparatus for updating a search strategy set further includes:

[0191] The similarity determination module is used to determine the strategy similarity between each search strategy in the search strategy subset and the candidate search strategies.

[0192] The similarity filtering module is used to identify the search strategies corresponding to the similarity scores of strategies that exceed the similarity threshold as search strategies to be confirmed.

[0193] Correspondingly, the update submodules include:

[0194] The update unit is used to update the search strategy set according to the score ranking relationship between the candidate strategy scores and the strategy scores corresponding to the search strategies to be confirmed.

[0195] In one embodiment, the scoring acquisition submodule includes:

[0196] The first position determination unit is used to determine the relative position of the candidate to be searched according to the candidate search strategy;

[0197] The second position determination unit is used to determine the candidate absolute position to be searched based on the candidate relative position and the current position;

[0198] The scoring acquisition unit is used to determine the candidate strategy score of the candidate search strategy based on the corresponding search coverage after the autonomous driving equipment performs a search task based on the candidate absolute position.

[0199] In one embodiment, an apparatus for updating a search strategy set further includes:

[0200] The target update module is used to call the range determination module if the real-time distance between any autonomous driving device and any candidate absolute position is less than or equal to a preset distance threshold, and / or the pheromone concentration corresponding to any candidate absolute position exceeds a preset concentration threshold.

[0201] Figure 8 The diagram shown is a structural schematic of an unmanned vehicle cluster coverage search device provided in an embodiment of this application. Figure 8 As shown, an unmanned vehicle cluster coverage search device according to this embodiment includes:

[0202] The acquisition module 810 is used to acquire the real-time search and perception range of the unmanned driving device at the real-time location of the target;

[0203] The strategy determination module 820 is used to determine the target search strategy corresponding to the real-time search perception range from the search strategy set; the search strategy set is obtained using the search strategy set update method in any of the above embodiments;

[0204] The search module 830 is used to control the unmanned vehicle to perform search tasks according to the target search strategy.

[0205] The unmanned vehicle cluster coverage search device provided in this application embodiment has the same beneficial effects as the above-mentioned method for updating a search strategy set.

[0206] 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.

[0207] 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.

[0208] Figure 9 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. Figure 9 As shown, the terminal device 900 of this embodiment includes a memory 901, a processor 902, and a computer program 903 stored in the memory 901 and executable on the processor 902; when the processor 902 executes the computer program 903, it implements the steps in the above-mentioned update method embodiments of various search strategy sets or the steps in the various unmanned vehicle cluster coverage search method embodiments; or when the processor 902 executes the computer program 903, it implements the functions of each module / unit in the above-mentioned device embodiments.

[0209] For example, computer program 903 can be divided into one or more modules / units, one or more of which are stored in memory 901 and executed by processor 902 to implement the method of the embodiments of this application. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of computer program 903 in terminal device 900. For example, computer program 903 can be divided into a range determination module, a judgment module, a first execution module, a second execution module, and an update module, with the specific functions of each module as follows:

[0210] The range determination module is used to determine the search and perception range of the autonomous driving equipment at its current location;

[0211] The determination module is used to determine whether there exists a subset of search strategies in the search strategy set that corresponds to the search perception range; the subset of search strategies includes at least one search strategy.

[0212] The first execution module is used to determine a matching search strategy from the search strategy subset if a subset of search strategies exists in the search strategy set, and to adjust the information of the matching search strategy to obtain a candidate search strategy.

[0213] The update module is used to update the search strategy set using candidate search strategies.

[0214] In applications, terminal device 900 can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. Terminal device 900 may include, but is not limited to, memory 901 and processor 902. Those skilled in the art will understand that... Figure 9 This is merely an example of a terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than shown, or combine certain components, or different components. For example, a terminal device may also include input / output devices, network access devices, buses, etc.; among which, input / output devices may include cameras, audio acquisition / playback devices, displays, etc.; network access devices may include communication modules for wireless communication with external devices.

[0215] In applications, the processor can be a Central Processing Unit (CPU), or 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. A general-purpose processor can be a microprocessor or any conventional processor.

[0216] In applications, memory can be an internal storage unit of a terminal device, such as its hard drive or RAM; it can also be an external storage device, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card; or it can include both internal and external storage units. Memory is used to store operating systems, applications, boot loaders, data, and other programs, such as computer program code. Memory can also be used to temporarily store data that has been output or will be output.

[0217] This application also provides an unmanned surface vessel (USV), which includes a USV body and a controller for executing the steps of any of the methods described in the above embodiments.

[0218] Unmanned surface vessels (USVs) are surface ships operated without human intervention, primarily used for dangerous tasks or missions unsuitable for manned vessels. Equipped with advanced control, sensor, communication, and weapon systems, they can perform a variety of wartime and non-wartime military missions, such as reconnaissance, search, detection, and mine clearance; search and rescue, navigation, and hydrographic surveys; anti-submarine warfare, counter-special operations, patrols, anti-piracy operations, and counter-terrorism operations. This embodiment, based on current USV technology, has the controller executing the steps of any one of the methods described in the above embodiments.

[0219] The unmanned surface vessel provided in this application embodiment has the same beneficial effects as the above-mentioned method for updating a search strategy set or a method for covering and searching a cluster of unmanned vehicles.

[0220] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the steps in the above-described method embodiments.

[0221] The computer-readable storage medium provided in this application embodiment has the same beneficial effects as the above-described method for updating a search strategy set or a method for covering a cluster of unmanned vehicles.

[0222] This application implements all or part of the processes in the methods of the above embodiments, which can be accomplished 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 file, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a terminal device, 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, such as a USB flash drive, a portable hard drive, a magnetic disk, or an optical disk.

[0223] 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.

[0224] Those skilled in the art will recognize that the device 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.

[0225] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interface, or the device may be indirectly coupled or communicated, and may be electrical, mechanical, or other forms.

[0226] 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 updating a search strategy set, characterized in that, The method includes: Determine the search and perception range of the autonomous vehicles in the autonomous vehicle cluster at their current location; A grid map corresponding to the search perception range is established; for each grid cell in the grid map, the encoding value of the grid cell is determined based on the actual area state corresponding to the grid cell; wherein, if the pheromone concentration of the actual area corresponding to the grid cell is greater than or equal to a preset concentration threshold, or if there is an obstacle in the actual area corresponding to the grid cell, the encoding value of the grid cell is determined to be a first preset value; otherwise, the encoding value of the grid cell is determined to be a second preset value; the pheromone concentration is a quantitative value representing the degree to which the corresponding actual area is searched by the autonomous driving equipment cluster; the encoding information to be searched corresponding to the grid map is determined based on the encoding value corresponding to each grid cell; based on the correspondence between the encoding information to be searched and the encoding information in the search strategy set, it is determined whether there is a subset of search strategies in the search strategy set corresponding to the encoding information to be searched; each search strategy in the search strategy set is respectively set with corresponding encoding information; the subset of search strategies includes at least one search strategy. If the search strategy subset exists in the search strategy set, then obtain the strategy score corresponding to each search strategy in the search strategy subset, and determine the search strategy corresponding to the highest strategy score among the strategy scores as the matching search strategy; A pre-set adjustment range for the search target location is used. The horizontal and / or vertical coordinates of the search target location are modified according to the adjustment range, and the modified search target location is determined as a candidate search strategy. Obtain the candidate strategy score of the candidate search strategy, sort the candidate strategy score with the strategy scores corresponding to each search strategy in the search strategy subset, if the candidate strategy score is the lowest strategy score, delete the candidate search strategy; if the candidate strategy score is greater than any strategy score, delete the search strategy corresponding to the strategy score, and add the candidate search strategy to the search strategy set.

2. The method according to claim 1, characterized in that, The method further includes: If the subset of search strategies does not exist in the search strategy set, then a candidate search strategy corresponding to the search awareness range is created, and the process proceeds to the step of updating the search strategy set using the candidate search strategy.

3. The method according to claim 1, characterized in that, The method further includes: Determine the strategy similarity between each search strategy in the subset of search strategies and the candidate search strategies; The search strategies corresponding to the similarity scores of the strategies that exceed the similarity threshold are identified as search strategies to be confirmed. Correspondingly, updating the search strategy set based on the score ranking relationship between the candidate strategy scores and the strategy scores corresponding to each search strategy in the search strategy subset includes: The search strategy set is updated according to the score ranking relationship between the candidate strategy scores and the search strategy to be confirmed.

4. The method according to claim 1, characterized in that, The process of obtaining the candidate strategy score for the candidate search strategy includes: The relative positions of the candidates to be searched are determined according to the candidate search strategy. The absolute position of the candidate to be searched is determined based on the relative position of the candidate and the current position; After the autonomous driving device performs a search task based on the candidate absolute position, the candidate strategy score of the candidate search strategy is determined according to the corresponding search coverage.

5. The method according to claim 4, characterized in that, The method further includes: If the real-time distance between any of the autonomous driving devices and any of the candidate absolute positions is less than or equal to a preset distance threshold, and / or the pheromone concentration corresponding to any of the candidate absolute positions exceeds a preset concentration threshold, then return to the step of determining the search and perception range of the autonomous driving devices in the autonomous driving device cluster at the current position.

6. A method for clustered coverage search of unmanned vehicles, characterized in that, The method, applied to any autonomous vehicle in a cluster of autonomous vehicles, includes: Obtain the real-time search and perception range of the unmanned vehicle at the target's real-time location; The target search strategy corresponding to the real-time search perception range is determined from the search strategy set; the search strategy set is obtained using the search strategy set update method as described in any one of claims 1 to 5; Control the unmanned vehicle to perform the search task according to the target search strategy.

7. 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 steps of the method as described in any one of claims 1 to 5 or 6.

8. An unmanned surface vessel (USV), comprising a USV body, characterized in that, The unmanned surface vessel also includes a controller for performing the steps of the method as described in any one of claims 1 to 5 or 6.

Images