Air-ground unmanned swarm consensus decision-making method and device for conflict resolution

Abstract

The conflict resolution-oriented air-ground unmanned swarm consensus decision-making method and device provided by the embodiments of the present disclosure include: obtaining the initial traffic state of the air-ground swarm group, the status information of each air-ground swarm included in the air-ground swarm group, and the coordinate information of obstacles within the air-ground swarm group's detection range; determining the target traffic spacing and target reference point based on the coordinate information of obstacles within the air-ground swarm group's detection range; and determining the target traffic state of the air-ground swarm group passing obstacles within the air-ground swarm group's detection range based on the initial traffic state of the air-ground swarm group, the status information of each air-ground swarm, the target traffic spacing, and the target reference point. This ensures the effectiveness of collaborative navigation through narrow lanes for multiple air-ground swarms.

Description

Technical Field

[0001] The present invention relates to the fields of computer technology and related technologies, and in particular to an air-to-ground unmanned cluster consensus decision-making method and device suitable for conflict resolution. Background Art

[0002] In modern military operations, collaborative operations among heterogeneous multi-platforms have become essential for improving operational efficiency and flexibility. However, conflict resolution in a heterogeneous, multi-platform battlefield environment remains a complex and challenging problem. In actual combat missions, different platforms often possess varying physical capabilities. For example, drones and ground robots offer significant complementarity in speed, sensing, communications, and payload capacity. Collaboration between these two approaches offers new breakthroughs in the effective application of unmanned ground and air systems, potentially enabling widespread application in scenarios such as battlefield situational awareness and penetration, border control, urban warfare, and logistics. Leveraging the strengths of heterogeneous platforms to resolve conflicts, achieve consensus within a cluster, and maximize the benefits of cluster operations has become a crucial issue.

[0003] Spatial self-organizing behavior (SBO) is a highly effective technology for swarm collaborative control, particularly for heterogeneous swarms. Existing technologies in the field of swarm collaborative control generally employ cluster consensus algorithms. However, the problem of conflict resolution in heterogeneous air-to-ground unmanned swarms in a combat environment presents a complex and critical challenge. Traditional algorithms face several difficulties in addressing this issue, primarily due to the difficulty of SBO's application to heterogeneous unmanned swarms, and the inability of swarm collaborative control to overcome the limitations of relying on fixed communication topologies and fixed, changing formation configurations. Summary of the Invention

[0004] The embodiments described herein provide a method and apparatus for air-to-ground unmanned swarm consensus decision-making for conflict resolution, addressing the problems of the prior art.

[0005] In a first aspect, according to the present disclosure, a consensus decision-making method for air-ground unmanned swarms oriented to conflict resolution is provided, comprising:

[0006] Obtaining an initial traffic state of an air-land cluster group, state information of each air-land cluster included in the air-land cluster group, and coordinate information of obstacles within the detection range of the air-land cluster group, wherein the initial traffic state of the air-land cluster includes an undeformed side-by-side state, an undeformed sequential state, a deformed side-by-side state, and a deformed sequential state, and the state information of each air-land cluster included in the air-land cluster group includes current position information, speed information, and detection diameter;

[0007] Determine the target clearance distance and target reference point based on the coordinate information of obstacles within the detection range of the air-ground cluster group;

[0008] The target passage state of the open-land cluster group passing through obstacles within the detection range of the open-land cluster group is determined according to the initial passage state of the open-land cluster group, the state information of each of the open-land clusters, the target passage distance and the target reference point.

[0009] In some embodiments of the present disclosure, determining the target clearance distance and the target reference point based on the coordinate information of the obstacles within the detection range of the air-ground cluster group includes:

[0010] Determining an obstacle point set group based on coordinate information of obstacles within the detection range of the air-ground cluster group, wherein the obstacle point set group includes multiple obstacle point sets, and any obstacle point set includes multiple obstacle points;

[0011] Determining a first pass distance between any two obstacle point sets in the obstacle point set group, wherein the first pass distance is the shortest pass distance between any two obstacle point sets;

[0012] Selecting the shortest of the first pass distances of any two obstacle point sets in the obstacle point set group as the target pass distance;

[0013] Determining a target obstacle point according to the target clearance distance;

[0014] A target reference point is determined according to the coordinate information of the target obstacle point.

[0015] In some embodiments of the present disclosure, determining the obstacle point set group based on the coordinate information of obstacles within the detection range of the open-ground cluster group includes:

[0016] Selecting an obstacle point from obstacles within the detection range of the open space cluster group as a first matching obstacle point;

[0017] Determining, based on a relationship between coordinate information of the first matching obstacle point and coordinate information of other obstacle points within a detection range of the open-ground cluster group, a first target matching obstacle point that matches the first matching obstacle point, so that the first matching obstacle point and the first target matching obstacle point form a first obstacle point set;

[0018] After eliminating the first matching obstacle point and the first target matching obstacle point, an obstacle point is again selected from the obstacles within the detection range of the open space cluster group as a second matching obstacle point, and a second obstacle point set is determined based on the second matching obstacle point.

[0019] In some embodiments of the present disclosure, determining a first pass distance between any two obstacle point sets in the obstacle point set group includes:

[0020] arbitrarily selecting two obstacle point sets from the obstacle point set group to form a sub-obstacle point set group, wherein any sub-obstacle point set group includes a first obstacle point set and a second obstacle point set;

[0021] Selecting a first target obstacle point from the first obstacle point set of the first sub-obstacle point set group, and obtaining coordinate information of the first target obstacle point;

[0022] determining, based on the coordinate information of the first target obstacle point and the coordinate information of any second obstacle point in the second obstacle point set, distance information between the first obstacle point and any second obstacle point in the second obstacle point set;

[0023] determining, based on distance information between the first obstacle point and any second obstacle point in the second obstacle point set of the first sub-obstacle point set, a second target obstacle point in the second obstacle point set having the shortest distance to the first target obstacle point;

[0024] Determining a sub-passing distance of a first sub-obstacle point set according to the coordinate information of the first target obstacle point and the coordinate information of the second target obstacle point, and selecting a first target obstacle point from the first obstacle point set of the first sub-obstacle point set again;

[0025] A shortest passage spacing is selected from a plurality of sub-passage spacings to form a target sub-passage spacing of the first sub-obstacle group, where the target sub-passage spacing is the first passage spacing of the first obstacle point set and the second obstacle point set.

[0026] In some embodiments of the present disclosure, the open space cluster group includes a first open space cluster and a second open space cluster;

[0027] The determining, based on the initial pass state of the open-ground cluster group, the state information of each of the open-ground clusters, the target pass distance, and the target reference point, of a target pass state of the open-ground cluster group passing through obstacles within the detection range of the open-ground cluster group includes:

[0028] When the initial passage state of the open space cluster group is the undeformed side-by-side state, if the target passage spacing is greater than or equal to the sum of the detection diameter of the first open space cluster and the detection diameter of the second open space cluster, it is determined that the target passage state of the open space cluster group passing through the obstacle within the detection range of the open space cluster group is the undeformed side-by-side state;

[0029] If the target passage distance is less than the sum of the detection diameters of the first open space cluster and the second open space cluster, and greater than the maximum of the detection diameters of the first open space cluster and the second open space cluster, determine first time information when the first open space cluster moves to the target reference point and second time information when the second open space cluster moves to the first reference point based on the current position information of the first open space cluster, the current position information of the second open space cluster, the speed information of the first open space cluster, the speed information of the second open space cluster, and the target reference point;

[0030] When the absolute value of the difference between the first time information and the second time information is less than a preset time, it is determined that the target passage state of the open-ground cluster group passing through the obstacle within the detection range of the open-ground cluster group is a deformed side-by-side state; when the absolute value of the difference between the first time information and the second time information is greater than or equal to the preset time, it is determined that the target passage state of the open-ground cluster group passing through the obstacle within the detection range of the open-ground cluster group is an undeformed sequential state, and the open-ground cluster corresponding to the smaller time information between the first time information and the second time information is selected to pass first;

[0031] If the target passage distance is less than or equal to the maximum value of the detection diameter of the first open space cluster and the detection diameter of the second open space cluster, it is determined that the target passage state of the open space cluster group passing through the obstacles within the detection range of the open space cluster group is a deformation order state, and the open space cluster corresponding to the smaller time information between the first time information and the second time information is selected to pass first.

[0032] In some embodiments of the present disclosure, the open space cluster group includes a first open space cluster and a second open space cluster;

[0033] The determining, based on the initial pass state of the open-ground cluster group, the state information of each of the open-ground clusters, the target pass distance, and the target reference point, of a target pass state of the open-ground cluster group passing through obstacles within the detection range of the open-ground cluster group includes:

[0034] When the initial passage state of the open space cluster group is the undeformed sequential state, if the target passage spacing is greater than or equal to the sum of the detection diameter of the first open space cluster and the detection diameter of the second open space cluster, it is determined that the target passage state of the open space cluster group passing through obstacles within the detection range of the open space cluster group is the undeformed side-by-side state;

[0035] If the target passage distance is less than the sum of the detection diameters of the first open space cluster and the second open space cluster, and greater than the maximum of the detection diameters of the first open space cluster and the second open space cluster, it is determined that the target passage state of the open space cluster group passing through the obstacles within the detection range of the open space cluster group is the undeformed order state;

[0036] If the target passing distance is less than or equal to the maximum of the detection diameters of the first open space cluster and the second open space cluster, determining, based on the current position information of the first open space cluster, the current position information of the second open space cluster, the speed information of the first open space cluster, the speed information of the second open space cluster, and the target reference point, first time information when the first open space cluster moves to the target reference point and second time information when the second open space cluster moves to the first reference point;

[0037] When the absolute value of the difference between the first time information and the second time information is greater than or equal to the preset time, it is determined that the target passage state of the open-ground cluster group through the obstacles within the detection range of the open-ground cluster group is a deformation order state, and the open-ground cluster corresponding to the smaller time information between the first time information and the second time information is selected to pass first.

[0038] In some embodiments of the present disclosure, the open space cluster group includes a first open space cluster and a second open space cluster;

[0039] The determining, based on the initial pass state of the open-ground cluster group, the state information of each of the open-ground clusters, the target pass distance, and the target reference point, of a target pass state of the open-ground cluster group passing through obstacles within the detection range of the open-ground cluster group includes:

[0040] When the initial passage state of the open space cluster group is the deformed side-by-side state, if the target passage spacing is greater than or equal to the sum of the detection diameters of the first open space cluster and the second open space cluster, it is determined that the target passage state of the open space cluster group passing through obstacles within the detection range of the open space cluster group is the undeformed side-by-side state;

[0041] If the target passage distance is smaller than the sum of the detection diameters of the first open space cluster and the second open space cluster, and larger than the maximum of the detection diameters of the first open space cluster and the second open space cluster, it is determined that the target passage state of the open space cluster group passing through the obstacle within the detection range of the open space cluster group is a deformed side-by-side state;

[0042] If the target passing distance is less than or equal to the maximum of the detection diameters of the first open space cluster and the second open space cluster, determining, based on the current position information of the first open space cluster, the current position information of the second open space cluster, the speed information of the first open space cluster, the speed information of the second open space cluster, and the target reference point, first time information when the first open space cluster moves to the target reference point and second time information when the second open space cluster moves to the first reference point;

[0043] When the absolute value of the difference between the first time information and the second time information is greater than or equal to the preset time, it is determined that the target passage state of the open-ground cluster group through the obstacles within the detection range of the open-ground cluster group is a deformation order state, and the open-ground cluster corresponding to the smaller time information between the first time information and the second time information is selected to pass first.

[0044] In some embodiments of the present disclosure, the open space cluster group includes a first open space cluster and a second open space cluster;

[0045] The determining, based on the initial pass state of the open-ground cluster group, the state information of each of the open-ground clusters, the target pass distance, and the target reference point, of a target pass state of the open-ground cluster group passing through obstacles within the detection range of the open-ground cluster group includes:

[0046] When the initial passage state of the open space cluster group is the deformed order state, if the target passage spacing is greater than or equal to the sum of the detection diameter of the first open space cluster and the detection diameter of the second open space cluster, it is determined that the target passage state of the open space cluster group passing through obstacles within the detection range of the open space cluster group is the undeformed side-by-side state;

[0047] If the target passage spacing is smaller than the sum of the detection diameter of the first open space cluster and the detection diameter of the second open space cluster, it is determined that the target passage state of the open space cluster group passing through obstacles within the detection range of the open space cluster group is a deformation order state.

[0048] In some embodiments of the present disclosure, before determining the target passage state of the open-ground cluster group passing through obstacles within the detection range of the open-ground cluster group based on the initial passage state of the open-ground cluster group, the state information of each of the open-ground clusters, the target passage distance, and the target reference point, the method further includes:

[0049] The deformation ratio is determined according to the target passage distance and the detection diameter of each of the open space clusters.

[0050] In a second aspect, according to the present disclosure, a conflict resolution-oriented air-to-ground unmanned cluster consensus decision-making device is provided, comprising:

[0051] an information acquisition module, configured to acquire an initial traffic state of an air-land cluster group, state information of each air-land cluster included in the air-land cluster group, and coordinate information of obstacles within the detection range of the air-land cluster group, wherein the initial traffic state of the air-land cluster includes an undeformed side-by-side state, an undeformed sequential state, a deformed side-by-side state, and a deformed sequential state; and the state information of each air-land cluster included in the air-land cluster group includes current position information, speed information, and detection diameter;

[0052] A target information determination module, configured to determine a target clearance distance and a target reference point based on the coordinate information of obstacles within the detection range of the air-ground cluster group;

[0053] A target passage state determination module is used to determine the target passage state of the open-land cluster group passing through obstacles within the detection range of the open-land cluster group based on the initial passage state of the open-land cluster group, the state information of each of the open-land clusters, the target passage distance and the target reference point.

[0054] The conflict resolution-oriented air-ground unmanned cluster consensus decision-making method and device provided by the disclosed embodiment first obtains the initial traffic state of the air-ground cluster group, the status information of each air-ground cluster included in the air-ground cluster group, and the coordinate information of the obstacles within the detection range of the air-ground cluster group. Then, based on the coordinate information of the obstacles within the detection range of the air-ground cluster group, the target traffic spacing and the target reference point are determined. Finally, based on the initial traffic state of the air-ground cluster group, the status information of each air-ground cluster, the target traffic spacing and the target reference point, the target traffic state of the air-ground cluster group passing through the obstacles within the detection range of the air-ground cluster group is determined. By decomposing the complex air-ground coordination problem into four basic sub-problems and then designing specific decisions, and automatically switching to the corresponding target traffic state based on the initial traffic state of the air-ground cluster group and the obstacles within the detection range of the air-ground cluster group, consensus decision-making of heterogeneous clusters is achieved. The method disclosed in the disclosed embodiment combines the perception advantages of drones with the self-organization advantages of ground robots, solving the problem that traditional spatial self-organizing behavior methods cannot solve the problem of heterogeneous cluster coordination, and realizing dynamic adaptive changes of ground robots, thereby ensuring the effectiveness of coordinated passage through narrow roads under multiple air-ground clusters.

[0055] The above description is only an overview of the technical solutions of the embodiments of the present application. In order to more clearly understand the technical means of the embodiments of the present application, they can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiments of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments will be briefly described below. It should be noted that the drawings described below only relate to some embodiments of the present disclosure and are not intended to limit the present disclosure.

[0057] Figure 1 This is a flow chart of a consensus decision-making method for air-ground unmanned clusters oriented to conflict resolution provided by an embodiment of the present disclosure;

[0058] Figure 2 This is a schematic diagram of the relationship between an open space cluster group and obstacles provided by an embodiment of the present disclosure;

[0059] Figure 3 This is a schematic diagram of the structure of an air-ground unmanned cluster consensus decision-making device for conflict resolution provided by an embodiment of the present disclosure;

[0060] Figure 4 It is a structural diagram of a computer device provided by an embodiment of the present disclosure.

[0061] In the drawings, reference numerals having the same last two digits correspond to the same elements. It should be noted that the elements in the drawings are schematic and not drawn to scale. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the described embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative work also fall within the scope of protection of the present disclosure.

[0063] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present disclosure belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the specification and the relevant art, and will not be interpreted in an idealized or overly formal manner unless otherwise explicitly defined herein. As used herein, a statement that two or more parts are "connected" or "coupled" together shall mean that the parts are joined together either directly or through one or more intermediate components.

[0064] References to "embodiments" herein mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase "embodiment" in various places in the specification does not necessarily refer to the same embodiment, nor does it necessarily refer to independent or alternative embodiments that are mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0065] The term "and / or" in this document simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists, A and B exist, and B exists. Additionally, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0066] Furthermore, in all embodiments of the present disclosure, terms such as “first” and “second” are used only to distinguish one component (or a portion of a component) from another component (or another portion of a component).

[0067] In the description of this application, unless otherwise specified, "plurality" means more than two (including two), and similarly, "multiple groups" means more than two (including two).

[0068] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0069] Based on the problems existing in the prior art, the present invention provides an air-ground unmanned cluster consensus decision-making method. Figure 1 This is a flow chart of the air-ground unmanned cluster consensus decision-making method provided by the embodiment of the present disclosure. Figure 1 As shown in the figure, the consensus decision-making method of air-ground unmanned cluster includes:

[0070] S110 , obtaining the initial traffic status of the air-land cluster group, status information of each air-land cluster included in the air-land cluster group, and coordinate information of obstacles within the detection range of the air-land cluster group.

[0071] The initial traffic states of the air-land clusters include the undeformed side-by-side state, the undeformed order state, the deformed side-by-side state and the deformed order state. The state information of each air-land cluster included in the air-land cluster group includes the current position information, speed information and detection diameter.

[0072] Specifically, in the disclosed embodiment, the air-ground cluster group includes a first air-ground cluster and a second air-ground cluster. Each air-ground cluster includes a drone and several ground robots. For each air-ground cluster, only the drone can obtain the corresponding target location information, and both the drone and the ground robot can obtain their own current location information. Within the same air-ground cluster, the drone can communicate with all ground robots, and drones between different air-ground clusters can communicate. Figure 2 , the detection diameter of the first open space cluster is 2r1, the current position information of the first open space cluster is (x1, y1), the speed information of the first open space cluster is v1, the detection diameter of the second open space cluster is 2r2, the current position information of the second open space cluster is (x2, y2), and the speed information of the first open space cluster is v2.

[0073] It should be noted that the current position information, speed information and detection diameter of the embodiment of the present disclosure are the current position information, speed information and detection diameter of the drones in each air-ground cluster.

[0074] Figure 2 The bold solid lines in the middle are obstacles within the detection range of the air-ground cluster group, where X1 is the obstacle within the detection range of the first air-ground cluster, and X2 is the obstacle within the detection range of the second air-ground cluster.

[0075] S120. Determine the target clearance distance and target reference point based on the coordinate information of obstacles within the detection range of the air-ground cluster group.

[0076] After determining the coordinate information of the obstacles within the detection range of the air-ground cluster group, the target clearance distance and the target reference point can be determined based on the coordinate information of the obstacles within the detection range of the air-ground cluster group.

[0077] In a specific embodiment, the target passage spacing and the target reference point are determined based on the coordinate information of obstacles within the detection range of the air-ground cluster group, including: determining an obstacle point set group based on the coordinate information of obstacles within the detection range of the air-ground cluster group, wherein the obstacle point set group includes multiple obstacle point sets, and any obstacle point set includes multiple obstacle points; determining a first passage spacing between any two obstacle point sets in the obstacle point set group, wherein the first passage spacing is the shortest passage spacing between any two obstacle point sets; selecting the shortest passage spacing between the first passage spacings between any two obstacle point sets in the obstacle point set group as the target passage spacing; determining the target obstacle point based on the target passage spacing; and determining the target reference point based on the coordinate information of the target obstacle point.

[0078] Combine Figure 2The obstacle points on the X1 line segment constitute a first obstacle point set, and the obstacle points on the X2 line segment constitute a second obstacle point set. The obstacle point set composed of the first obstacle point set and the second obstacle point set constitutes an obstacle point set group. The first pass distance is determined by determining the shortest pass distance between the first obstacle point set and the second obstacle point set. Since the obstacle point set group only includes one obstacle point set, the target pass distance is also the first pass distance. After determining the target pass distance, two target obstacle points can be determined based on the target pass distance. The coordinate information of the target reference point is determined by averaging the coordinate information of the two target obstacle points.

[0079] In a specific embodiment, an obstacle point set is determined based on the coordinate information of obstacles within the detection range of the air-ground cluster group, including: selecting an obstacle point from the obstacles within the detection range of the air-ground cluster group as a first matching obstacle point; determining a first target matching obstacle point that matches the first matching obstacle point based on the relationship between the coordinate information of the first matching obstacle point and the coordinate information of other obstacle points within the detection range of the air-ground cluster group, so that the first matching obstacle point and the first target matching obstacle point constitute a first obstacle point set; after eliminating the first matching obstacle point and the first target matching obstacle point, selecting an obstacle point from the obstacles within the detection range of the air-ground cluster group as a second matching obstacle point again, and determining a second obstacle point set based on the second matching obstacle point.

[0080] Specifically, the specific process of determining the obstacle point set group is: if the obstacle points included in the obstacles within the detection range of the air-ground cluster group are n0, n1, n2, ..., ni, first select n0 as the first matching obstacle point, and match the coordinate information of the obstacle point n0 with the coordinate information of other obstacle points (n1, n2, ..., ni) within the detection range of the air-ground cluster group. If there are obstacle points (n1, n2, n8, n9, n12, n18, ..., ni) with the coordinate information of the obstacle points, the obstacle point set is matched. When the distance of the coordinate information of the object point n0 is less than or equal to the preset distance, the obstacle points (n1, n2, n8, n9, n12, n18, ..., ni) are determined as the first target matching obstacle points of the obstacle point n0, and the matched first target matching obstacle points and the first matching obstacle points are combined into a first obstacle point set. The first obstacle point set includes the obstacle points (n0, n1, n2, n8, n9, n12, n18, ..., ni) respectively; then n3 is selected as the second Match the obstacle points, match the coordinate information of the obstacle point n3 with the coordinate information of other obstacle points (n4, n5, ..., ni-1) within the detection range of the air-ground cluster group except the obstacle points included in the first obstacle point set, and if the distance between the coordinate information of the obstacle point (n4, n5, n6, n7, n10, n11, ..., ni-1) and the coordinate information of the obstacle point n3 is less than or equal to the preset distance, determine the obstacle point (n4, n5, n6, n7, n10, n11, ..., ni-1) 1, ..., ni-1) is the second target matching obstacle point of obstacle point n3, and the matched second target matching obstacle points and the second matching obstacle points are combined into a second obstacle point set. The second obstacle point set includes the obstacle points (n3, n4, n5, n6, n7, n10, n11, ..., ni-1) respectively. Similarly, multiple obstacle point sets are matched in sequence until all the obstacle points included in the obstacles within the detection range of the air-ground cluster group are matched, and the loop process ends.

[0081] Specifically, the obstacle point set groups obtained by dividing the obstacle point set within the detection range of the air-ground cluster group are: {O1, O2, ..., O m}.

[0082] In a specific embodiment, determining a first pass distance between any two obstacle point sets in an obstacle point set group includes: arbitrarily selecting two obstacle point sets from the obstacle point set group to form a sub-obstacle point set group, wherein any sub-obstacle point set group includes a first obstacle point set and a second obstacle point set; selecting a first target obstacle point from a first obstacle point set in the first sub-obstacle point set group, and obtaining coordinate information of the first target obstacle point; determining the first obstacle point and any second obstacle point in the second obstacle point set based on the coordinate information of the first target obstacle point and the coordinate information of any second obstacle point in the second obstacle point set of the first sub-obstacle point set group. distance information of the first obstacle point and any second obstacle point in the second obstacle point set; determining a second target obstacle point in the second obstacle point set with the shortest distance information to the first target obstacle point based on the distance information of the first obstacle point and the second obstacle point set; determining a sub-passing spacing of the first sub-obstacle point set based on the coordinate information of the first target obstacle point and the coordinate information of the second target obstacle point, and again selecting a first target obstacle point from the first obstacle point set of the first sub-obstacle point set; selecting the shortest passing spacing from the multiple sub-passing spacings to form a target sub-passing spacing of the first sub-obstacle group, and the target sub-passing spacing is the first passing spacing of the first obstacle point set and the second obstacle point set.

[0083] Specifically, the obstacle point set groups obtained by dividing the obstacle point set within the detection range of the air-ground cluster group are: {O1, O2, ..., O m}, then the sub-obstacle point set includes: {O1,O2}, {O1,O3}, {O1,O4}, ..., {O1,O m-1}、{O1,O m-2}, {O2,O3}, {O2,O4}, {O2,O5},..., {O2,O m-1}、{O2,O m-2}, {O3,O4}, {O3,O5}, {O3,O6},..., {O3,O m-1}、{O3,O m-2}、{O m-2 ,O m-1}、{O m-1 ,O m}.

[0084] For example, {O1, O2} is the first sub-obstacle point set, {O1, O3} is the second sub-obstacle point set, {O m-1 ,O m} is the jth sub-obstacle point set. For the first sub-obstacle point set {O1, O2}, O1 is selected as the first obstacle point set and O2 is selected as the second obstacle point set. If the obstacle points included in the first obstacle point set O1 are (n0, n1, n2, n8, n9, n12, n18, ..., ni), and the obstacle points included in the second obstacle point set O2 are (n3, n4, n5, n6, n7, n10, n11, ..., ni-1), then n0 is first selected from the first obstacle point set O1 as the first target obstacle point. According to the coordinate information of the first target obstacle point n0 in the first obstacle point set O1 and the coordinate information of the second obstacle points (n3, n4, n5, n6, n7, n10, n11, ..., ni-1) included in the second obstacle point set O2, The coordinate information of the first obstacle point n0 and any second obstacle point (n3, n4, n5, n6, n7, n10, n11, ..., ni-1) in the second obstacle point set O2 is determined, and the distance information between the first obstacle point n0 and any second obstacle point (n3, n4, n5, n6, n7, n10, n11, ..., ni-1) in the second obstacle point set O2 is determined. By selecting the second obstacle point with the shortest distance information, a sub-passing distance of the first sub-obstacle point set {O1, O2} is determined, that is, the first passing distance of a sub-obstacle point set composed of the first obstacle point set O1 and the second obstacle point set O2 is determined in this way, and so on. m-1 and the second obstacle point set O m The first pass distance of a sub-obstacle point set.

[0085] After determining the first pass distance of a sub-obstacle point set group composed of any two obstacle point sets, the first pass distance of a sub-obstacle point set group composed of the first obstacle point set O1 and the second obstacle point set O2, the first pass distance of a sub-obstacle point set group composed of the first obstacle point set O1 and the third obstacle point set O2, ..., the first obstacle point set O m-1 and the second obstacle point set O m The first pass spacing of a sub-obstacle point set is selected as the target pass spacing.

[0086] For example, the first pass distance of the sub-obstacle point set {O1, O2} is d min (O1, O2), the first pass distance of the sub-obstacle point set {O1, O3} is d min (O1, O3), ..., the sub-obstacle point set {O m-1 ,O m The first pass spacing of} is d min (O m-1 ,O m), the target clearance distance is expressed as follows:

[0087] d=min(d min (O1,O2),d min (O1,O3),...,d min (O m-1 ,O m ))

[0088] S130 , determining a target passage state of the air-ground cluster group passing through obstacles within a detection range of the air-ground cluster group based on the initial passage state of the air-ground cluster group, state information of each air-ground cluster, target passage distance, and target reference point.

[0089] Since the passage states of the air-ground cluster group include the undeformed side-by-side state, the undeformed order state, the deformed side-by-side state and the deformed order state, according to the initial passage state of the air-ground cluster group, the state information of each air-ground cluster included in the air-ground cluster group and the obstacles within the detection range of the air-ground cluster group, the target passage state of the air-ground cluster group passing through the obstacles within the detection range of the air-ground cluster group can be determined, that is, the target passage state can be the undeformed side-by-side state, the undeformed order state, the deformed side-by-side state and the deformed order state.

[0090] The following will be illustrated by specific embodiments.

[0091] As an implementation method, an example analysis is performed by taking the initial traffic state of the open space cluster group as an undeformed side-by-side state.

[0092] If the target passage spacing is greater than or equal to the sum of the detection diameters of the first open space cluster and the second open space cluster, the target passage state of the open space cluster group passing through the obstacle within the detection range of the open space cluster group is determined to be an undeformed side-by-side state; if the target passage spacing is less than the sum of the detection diameters of the first open space cluster and the second open space cluster, and greater than the maximum value of the detection diameters of the first open space cluster and the second open space cluster, the first time information of the first open space cluster moving to the target reference point and the second time information of the second open space cluster moving to the first reference point are determined based on the current position information of the first open space cluster, the current position information of the second open space cluster, the speed information of the first open space cluster, the speed information of the second open space cluster and the target reference point; the difference between the first time information and the second time information When the absolute value is less than the preset time, it is determined that the target passage state of the air-ground cluster group passing through the obstacle within the detection range of the air-ground cluster group is a deformed side-by-side state; when the absolute value of the difference between the first time information and the second time information is greater than or equal to the preset time, it is determined that the target passage state of the air-ground cluster group passing through the obstacle within the detection range of the air-ground cluster group is a non-deformed order state, and the air-ground cluster corresponding to the smaller time information in the first time information and the second time information is selected to pass first; if the target passage spacing is less than or equal to the maximum value of the detection diameter of the first air-ground cluster and the detection diameter of the second air-ground cluster, it is determined that the target passage state of the air-ground cluster group passing through the obstacle within the detection range of the air-ground cluster group is a deformed order state, and the air-ground cluster corresponding to the smaller time information in the first time information and the second time information is selected to pass first.

[0093] As another implementation, an example analysis is performed by taking the initial traffic state of the open space cluster group as the undeformed order state.

[0094] If the target passage distance is greater than or equal to the sum of the detection diameters of the first open space cluster and the detection diameters of the second open space cluster, the target passage state of the open space cluster group passing through the obstacles within the detection range of the open space cluster group is determined to be an undeformed side-by-side state; if the target passage distance is less than the sum of the detection diameters of the first open space cluster and the second open space cluster, and is greater than the maximum value of the detection diameters of the first open space cluster and the second open space cluster, the target passage state of the open space cluster group passing through the obstacles within the detection range of the open space cluster group is determined to be an undeformed sequential state; if the target passage distance is less than or equal to the detection diameters of the first open space cluster and the detection diameters of the second open space cluster When the maximum value of the values ​​is reached, the first time information of the first open-ground cluster moving to the target reference point and the second time information of the second open-ground cluster moving to the first reference point are determined according to the current position information of the first open-ground cluster, the current position information of the second open-ground cluster, the speed information of the first open-ground cluster, the speed information of the second open-ground cluster and the target reference point; when the absolute value of the difference between the first time information and the second time information is greater than or equal to the preset time, it is determined that the target passage state of the open-ground cluster group passing through the obstacle within the detection range of the open-ground cluster group is the deformation order state, and the open-ground cluster corresponding to the smaller time information in the first time information and the second time information is selected to pass first.

[0095] As another implementation method, an example analysis is performed by taking the initial traffic state of the open space cluster group as a deformed side-by-side state.

[0096] If the target passage distance is greater than or equal to the sum of the detection diameters of the first open space cluster and the second open space cluster, it is determined that the target passage state of the open space cluster group passing through the obstacles within the detection range of the open space cluster group is an undeformed side-by-side state; if the target passage distance is less than the sum of the detection diameters of the first open space cluster and the second open space cluster, and is greater than the maximum value of the detection diameters of the first open space cluster and the second open space cluster, it is determined that the target passage state of the open space cluster group passing through the obstacles within the detection range of the open space cluster group is a deformed side-by-side state; if the target passage distance is less than or equal to the detection diameters of the first open space cluster and the detection diameters of the second open space cluster, it is determined that the target passage state of the open space cluster group passing through the obstacles within the detection range of the open space cluster group is a deformed side-by-side state. When the maximum value in the path is obtained, the first time information of the first air-ground cluster moving to the target reference point and the second time information of the second air-ground cluster moving to the first reference point are determined according to the current position information of the first air-ground cluster, the current position information of the second air-ground cluster, the speed information of the first air-ground cluster, the speed information of the second air-ground cluster and the target reference point; when the absolute value of the difference between the first time information and the second time information is greater than or equal to the preset time, it is determined that the target passage state of the air-ground cluster group passing through the obstacle within the detection range of the air-ground cluster group is the deformation order state, and the air-ground cluster corresponding to the smaller time information in the first time information and the second time information is selected to pass first.

[0097] As another implementation method, an example analysis is performed by taking the initial traffic state of the open space cluster group as the deformation order state.

[0098] If the target passage spacing is greater than or equal to the sum of the detection diameters of the first open space cluster and the second open space cluster, the target passage state of the open space cluster group passing through obstacles within the detection range of the open space cluster group is determined to be an undeformed side-by-side state; if the target passage spacing is less than the sum of the detection diameters of the first open space cluster and the second open space cluster, the target passage state of the open space cluster group passing through obstacles within the detection range of the open space cluster group is determined to be a deformed order state.

[0099] In addition, before executing step S130 , the method further includes: determining a deformation ratio according to the target traffic spacing and the detection diameter of each open space cluster.

[0100] When the air-ground cluster group changes from an undeformed side-by-side state or an undeformed sequential state to a deformed side-by-side state or a deformed sequential state, it is necessary to determine the deformation ratio of the air-ground cluster to ensure that the deformed air-ground cluster can smoothly pass through obstacles within the air-ground cluster detection range.

[0101] Specifically, the deformation ratio needs to be greater than the maximum value of the ratio of the target passage distance to the detection diameter of each open space cluster.

[0102] The conflict resolution-oriented air-ground unmanned cluster consensus decision-making method provided by the disclosed embodiment first obtains the initial traffic state of the air-ground cluster group, the status information of each air-ground cluster included in the air-ground cluster group, and the coordinate information of the obstacles within the detection range of the air-ground cluster group. Then, based on the coordinate information of the obstacles within the detection range of the air-ground cluster group, the target traffic spacing and the target reference point are determined. Finally, based on the initial traffic state of the air-ground cluster group, the status information of each air-ground cluster, the target traffic spacing and the target reference point, the target traffic state of the air-ground cluster group passing through the obstacles within the detection range of the air-ground cluster group is determined. By decomposing the complex air-ground coordination problem into four basic sub-problems and then designing specific decisions, and automatically switching to the corresponding target traffic state based on the initial traffic state of the air-ground cluster group and the obstacles within the detection range of the air-ground cluster group, consensus decision-making of heterogeneous clusters is achieved. The method disclosed in the disclosed embodiment combines the perception advantages of drones with the self-organization advantages of ground robots, solves the problem that traditional spatial self-organizing behavior methods cannot solve the problem of heterogeneous cluster coordination, and realizes the dynamic adaptive changes of ground robots, thereby ensuring the effectiveness of coordinated passage through narrow roads under multiple air-ground clusters.

[0103] Based on the above embodiments, the present disclosure also provides an air-ground unmanned cluster consensus decision-making device for conflict resolution. Figure 3 This is a schematic diagram of the structure of the air-ground unmanned cluster consensus decision-making device for conflict resolution provided by the embodiment of the present disclosure. Figure 3As shown in FIG, the air-ground unmanned swarm consensus decision-making device for conflict resolution includes:

[0104] Information acquisition module 310 is used to obtain the initial traffic state of the air-ground cluster group, the state information of each air-ground cluster included in the air-ground cluster group, and the coordinate information of obstacles within the detection range of the air-ground cluster group. The initial traffic state of the air-ground cluster includes the undeformed side-by-side state, the undeformed sequential state, the deformed side-by-side state, and the deformed sequential state. The state information of each air-ground cluster included in the air-ground cluster group includes the current position information, speed information, and detection diameter.

[0105] The target information determination module 320 is used to determine the target clearance distance and target reference point based on the coordinate information of obstacles within the detection range of the air-ground cluster group;

[0106] The target traffic state determination module 330 is used to determine the target traffic state of the air-ground cluster group passing through obstacles within the detection range of the air-ground cluster group based on the initial traffic state of the air-ground cluster group, the state information of each air-ground cluster, the target traffic distance and the target reference point.

[0107] The conflict resolution-oriented air-ground unmanned cluster consensus decision-making device provided by the embodiment of the present disclosure first obtains the initial traffic state of the air-ground cluster group, the status information of each air-ground cluster included in the air-ground cluster group, and the coordinate information of the obstacles within the detection range of the air-ground cluster group. Then, based on the coordinate information of the obstacles within the detection range of the air-ground cluster group, the target traffic spacing and the target reference point are determined. Finally, based on the initial traffic state of the air-ground cluster group, the status information of each air-ground cluster, the target traffic spacing and the target reference point, the target traffic state of the air-ground cluster group passing through the obstacles within the detection range of the air-ground cluster group is determined. By decomposing the complex air-ground coordination problem into four basic sub-problems and then designing specific decisions, and automatically switching to the corresponding target traffic state based on the initial traffic state of the air-ground cluster group and the obstacles within the detection range of the air-ground cluster group, consensus decision-making of heterogeneous clusters is achieved. The method disclosed in the embodiment of the present disclosure combines the perception advantages of drones with the self-organization advantages of ground robots, solving the problem that traditional spatial self-organizing behavior methods cannot solve the problem of heterogeneous cluster coordination, and realizing dynamic adaptive changes of ground robots, thereby ensuring the effectiveness of coordinated passage through narrow roads under multiple air-ground clusters.

[0108] In a specific embodiment, determining the target clearance distance and the target reference point based on the coordinate information of the obstacles within the detection range of the air-ground cluster group includes:

[0109] Determine an obstacle point set group based on the coordinate information of obstacles within the detection range of the air-ground cluster group, wherein the obstacle point set group includes multiple obstacle point sets, and any obstacle point set includes multiple obstacle points;

[0110] Determine a first pass distance between any two obstacle point sets in the obstacle point set group, wherein the first pass distance is the shortest pass distance between any two obstacle point sets;

[0111] The shortest of the first pass distances between any two obstacle point sets in the obstacle point set group is selected as the target pass distance;

[0112] Determine the target obstacle point based on the target clearance distance;

[0113] The target reference point is determined according to the coordinate information of the target obstacle point.

[0114] In a specific embodiment, determining the obstacle point set group according to the coordinate information of the obstacles within the detection range of the open-ground cluster group includes:

[0115] Select an obstacle point from the obstacles within the detection range of the open-ground cluster group as the first matching obstacle point;

[0116] Determining a first target matching obstacle point that matches the first matching obstacle point based on a relationship between coordinate information of the first matching obstacle point and coordinate information of other obstacle points within a detection range of the open-ground cluster group, so that the first matching obstacle point and the first target matching obstacle point form a first obstacle point set;

[0117] After eliminating the first matching obstacle point and the first target matching obstacle point, an obstacle point is selected again from the obstacles within the detection range of the open-ground cluster group as the second matching obstacle point, and a second obstacle point set is determined based on the second matching obstacle point.

[0118] In a specific embodiment, determining a first pass distance between any two obstacle point sets in the obstacle point set group includes:

[0119] Randomly selecting two obstacle point sets from the obstacle point set group to form a sub-obstacle point set group, wherein any sub-obstacle point set group includes the first obstacle point set and the second obstacle point set;

[0120] Selecting a first target obstacle point from the first obstacle point set of the first sub-obstacle point set group, and obtaining coordinate information of the first target obstacle point;

[0121] determining, based on the coordinate information of the first target obstacle point and the coordinate information of any second obstacle point in the second obstacle point set, distance information between the first obstacle point and any second obstacle point in the second obstacle point set;

[0122] Determining, based on distance information between the first obstacle point and any second obstacle point in the second obstacle point set of the first sub-obstacle point set, a second target obstacle point in the second obstacle point set having the shortest distance information to the first target obstacle point;

[0123] Determine a sub-passing distance of the first sub-obstacle point set according to the coordinate information of the first target obstacle point and the coordinate information of the second target obstacle point, and select a first target obstacle point from the first obstacle point set of the first sub-obstacle point set again;

[0124] The shortest passage spacing is selected from the multiple sub-passage spacings to form a target sub-passage spacing of the first sub-obstacle group. The target sub-passage spacing is the first passage spacing of the first obstacle point set and the second obstacle point set.

[0125] In a specific embodiment, the open space cluster group includes a first open space cluster and a second open space cluster;

[0126] According to the initial traffic status of the air-ground cluster group, the status information of each air-ground cluster, the target traffic distance and the target reference point, the target traffic status of the air-ground cluster group passing through obstacles within the detection range of the air-ground cluster group is determined, including:

[0127] When the initial passage state of the open-ground cluster group is the undeformed side-by-side state, if the target passage spacing is greater than or equal to the sum of the detection diameters of the first open-ground cluster and the second open-ground cluster, the target passage state of the open-ground cluster group passing through obstacles within the detection range of the open-ground cluster group is determined to be the undeformed side-by-side state;

[0128] If the target passage distance is less than the sum of the detection diameters of the first open space cluster and the second open space cluster, and greater than the maximum of the detection diameters of the first open space cluster and the second open space cluster, determine first time information when the first open space cluster moves to the target reference point and second time information when the second open space cluster moves to the first reference point based on the current position information of the first open space cluster, the current position information of the second open space cluster, the speed information of the first open space cluster, the speed information of the second open space cluster, and the target reference point;

[0129] When the absolute value of the difference between the first time information and the second time information is less than a preset time, it is determined that the target passage state of the air-ground cluster group passing through the obstacle within the detection range of the air-ground cluster group is a deformed side-by-side state; when the absolute value of the difference between the first time information and the second time information is greater than or equal to the preset time, it is determined that the target passage state of the air-ground cluster group passing through the obstacle within the detection range of the air-ground cluster group is an undeformed sequential state, and the air-ground cluster corresponding to the smaller time information of the first time information and the second time information is selected to pass first;

[0130] If the target passage distance is less than or equal to the maximum value of the detection diameter of the first open space cluster and the detection diameter of the second open space cluster, the target passage state of the open space cluster group passing through the obstacles within the detection range of the open space cluster group is determined to be the deformation order state, and the open space cluster corresponding to the smaller time information in the first time information and the second time information is selected to pass first.

[0131] In a specific embodiment, the open space cluster group includes a first open space cluster and a second open space cluster;

[0132] According to the initial traffic status of the air-ground cluster group, the status information of each air-ground cluster, the target traffic distance and the target reference point, the target traffic status of the air-ground cluster group passing through obstacles within the detection range of the air-ground cluster group is determined, including:

[0133] When the initial passage state of the open-ground cluster group is the undeformed sequential state, if the target passage spacing is greater than or equal to the sum of the detection diameter of the first open-ground cluster and the detection diameter of the second open-ground cluster, the target passage state of the open-ground cluster group passing through obstacles within the detection range of the open-ground cluster group is determined to be the undeformed side-by-side state;

[0134] If the target passage distance is less than the sum of the detection diameters of the first open space cluster and the second open space cluster, and greater than the maximum of the detection diameters of the first open space cluster and the second open space cluster, the target passage state of the open space cluster group passing through the obstacles within the detection range of the open space cluster group is determined to be the undeformed order state;

[0135] If the target clearance distance is less than or equal to the maximum of the detection diameters of the first open space cluster and the detection diameters of the second open space cluster, determining first time information for the first open space cluster to move to the target reference point and second time information for the second open space cluster to move to the first reference point based on the current position information of the first open space cluster, the current position information of the second open space cluster, the speed information of the first open space cluster, the speed information of the second open space cluster, and the target reference point;

[0136] When the absolute value of the difference between the first time information and the second time information is greater than or equal to the preset time, it is determined that the target passage state of the air-ground cluster group passing through the obstacles within the detection range of the air-ground cluster group is the deformation order state, and the air-ground cluster corresponding to the smaller time information in the first time information and the second time information is selected to pass first.

[0137] In a specific embodiment, the open space cluster group includes a first open space cluster and a second open space cluster;

[0138] According to the initial traffic status of the air-ground cluster group, the status information of each air-ground cluster, the target traffic distance and the target reference point, the target traffic status of the air-ground cluster group passing through obstacles within the detection range of the air-ground cluster group is determined, including:

[0139] When the initial passage state of the open-land cluster group is the deformed side-by-side state, if the target passage spacing is greater than or equal to the sum of the detection diameters of the first open-land cluster and the second open-land cluster, the target passage state of the open-land cluster group passing through obstacles within the detection range of the open-land cluster group is determined to be the undeformed side-by-side state;

[0140] If the target passage distance is smaller than the sum of the detection diameters of the first open space cluster and the second open space cluster, and larger than the maximum of the detection diameters of the first open space cluster and the second open space cluster, the target passage state of the open space cluster group passing through obstacles within the detection range of the open space cluster group is determined to be a deformed side-by-side state;

[0141] If the target clearance distance is less than or equal to the maximum of the detection diameters of the first open space cluster and the detection diameters of the second open space cluster, determining first time information for the first open space cluster to move to the target reference point and second time information for the second open space cluster to move to the first reference point based on the current position information of the first open space cluster, the current position information of the second open space cluster, the speed information of the first open space cluster, the speed information of the second open space cluster, and the target reference point;

[0142] When the absolute value of the difference between the first time information and the second time information is greater than or equal to the preset time, it is determined that the target passage state of the air-ground cluster group passing through the obstacles within the detection range of the air-ground cluster group is the deformation order state, and the air-ground cluster corresponding to the smaller time information in the first time information and the second time information is selected to pass first.

[0143] In a specific embodiment, the open space cluster group includes a first open space cluster and a second open space cluster;

[0144] According to the initial traffic status of the air-ground cluster group, the status information of each air-ground cluster, the target traffic distance and the target reference point, the target traffic status of the air-ground cluster group passing through obstacles within the detection range of the air-ground cluster group is determined, including:

[0145] When the initial passage state of the open-ground cluster group is the deformed order state, if the target passage distance is greater than or equal to the sum of the detection diameter of the first open-ground cluster and the detection diameter of the second open-ground cluster, the target passage state of the open-ground cluster group passing through obstacles within the detection range of the open-ground cluster group is determined to be the undeformed side-by-side state;

[0146] If the target passage distance is smaller than the sum of the detection diameter of the first open space cluster and the detection diameter of the second open space cluster, it is determined that the target passage state of the open space cluster group passing through the obstacle within the detection range of the open space cluster group is the deformation order state.

[0147] In a specific embodiment, before determining the target pass state of the air-land cluster group passing through obstacles within the detection range of the air-land cluster group based on the initial pass state of the air-land cluster group, the state information of each air-land cluster, the target pass distance, and the target reference point, the method further includes:

[0148] The deformation ratio is determined based on the target traffic spacing and the detection diameter of each open space cluster.

[0149] The present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0150] The computer device includes a memory 510 and a processor 520 that are interconnected and communicate with each other via a system bus. It should be noted that the figure only shows a computer device having components 510-520, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0151] Computer devices can be desktop computers, laptops, PDAs, cloud servers, etc. Computer devices can interact with users through keyboards, mice, remote controls, touchpads, or voice-activated devices.

[0152] The memory 510 includes at least one type of readable storage medium, and the readable storage medium includes non-volatile memory or volatile memory, such as flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. RAM may include static RAM or dynamic RAM. In some embodiments, the memory 510 may be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the memory 510 may also be an external storage device of the computer device, such as a plug-in hard disk, smart memory card (SMC), secure digital (SD) card or flash card equipped with the computer device. Of course, the memory 510 may also include both an internal storage unit of the computer device and an external storage device thereof. In this embodiment, the memory 510 is generally used to store an operating system and various application software installed on the computer device, such as the program code of the above-mentioned method. In addition, the memory 510 may also be used to temporarily store various types of data that have been output or are about to be output.

[0153] The processor 520 is generally used to perform the overall operation of the computer device. In this embodiment, the memory 510 is used to store program code or instructions, which include computer operating instructions. The processor 520 is used to execute the program code or instructions stored in the memory 510 or process data, such as the program code for running the above method.

[0154] In this document, a bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. This bus system can be divided into address buses, data buses, and control buses. For ease of illustration, the figure uses only one thick line, but this does not mean that there is only one bus or only one type of bus.

[0155] Another embodiment of the present application further provides a computer-readable medium, which may be a computer-readable signal medium or a computer-readable medium. A processor in a computer reads the computer-readable program code stored in the computer-readable medium, enabling the processor to execute the functional actions specified in each step or combination of steps in the above method, and to generate a device that implements the functional actions specified in each block or combination of blocks in the block diagram.

[0156] Computer-readable media include but are not limited to electronic, magnetic, optical, electromagnetic, infrared memory or semiconductor systems, devices or apparatuses, or any appropriate combination of the foregoing, the memory is used to store program codes or instructions, the program codes include computer operating instructions, and the processor is used to execute the program codes or instructions of the above-mentioned methods stored in the memory.

[0157] For the definitions of memory and processor, please refer to the description of the aforementioned computer device embodiment and will not be repeated here.

[0158] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0159] Each functional unit or module in each embodiment of the present application may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The above-mentioned integrated units may be implemented in the form of hardware or software functional units.

[0160] If the integrated unit is implemented in the form of 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, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0161] Unless the context clearly indicates otherwise, as used herein and in the appended claims, the singular includes the plural, and vice versa. Thus, when referring to the singular, the plural of the corresponding term is generally included. Similarly, the words "include" and "comprising" are to be interpreted as inclusive rather than exclusive. Likewise, the terms "include" and "or" should be interpreted as inclusive unless such interpretation is expressly prohibited herein. Where the term "example" is used herein, particularly when it follows a group of terms, the "example" is merely exemplary and illustrative and should not be considered exclusive or comprehensive.

[0162] Further aspects and scope of adaptability become apparent from the description provided herein. It should be understood that various aspects of the present application can be implemented individually or in combination with one or more other aspects. It should also be understood that the description and specific embodiments herein are intended to be illustrative only and are not intended to limit the scope of the present application.

[0163] Several embodiments of the present disclosure have been described in detail above, but it is obvious that those skilled in the art can make various modifications and variations to the embodiments of the present disclosure without departing from the spirit and scope of the present disclosure. The scope of protection of the present disclosure is defined by the appended claims.

Claims

1. A consensus decision-making method for air-ground unmanned swarms oriented to conflict resolution, characterized by: include: Obtaining an initial traffic state of an air-land cluster group, state information of each air-land cluster included in the air-land cluster group, and coordinate information of obstacles within the detection range of the air-land cluster group, wherein the initial traffic state of the air-land cluster includes an undeformed side-by-side state, an undeformed sequential state, a deformed side-by-side state, and a deformed sequential state, and the state information of each air-land cluster included in the air-land cluster group includes current position information, speed information, and detection diameter; Determine the target clearance distance and target reference point based on the coordinate information of obstacles within the detection range of the air-ground cluster group; Determining a target passage state of the open-ground cluster group passing through obstacles within a detection range of the open-ground cluster group according to an initial passage state of the open-ground cluster group, state information of each of the open-ground clusters, the target passage distance, and the target reference point; The determining of the target clearance distance and the target reference point according to the coordinate information of the obstacles within the detection range of the open-ground cluster group includes: Determining an obstacle point set group based on coordinate information of obstacles within the detection range of the air-ground cluster group, wherein the obstacle point set group includes multiple obstacle point sets, and any obstacle point set includes multiple obstacle points; Determining a first pass distance between any two obstacle point sets in the obstacle point set group, wherein the first pass distance is the shortest pass distance between any two obstacle point sets; Selecting the shortest of the first pass distances of any two obstacle point sets in the obstacle point set group as the target pass distance; Determining a target obstacle point according to the target clearance distance; Determine a target reference point according to the coordinate information of the target obstacle point; The determining of a first pass distance between any two obstacle point sets in the obstacle point set group includes: arbitrarily selecting two obstacle point sets from the obstacle point set group to form a sub-obstacle point set group, wherein any sub-obstacle point set group includes a first obstacle point set and a second obstacle point set; Selecting a first target obstacle point from the first obstacle point set of the first sub-obstacle point set group, and obtaining coordinate information of the first target obstacle point; determining, based on the coordinate information of the first target obstacle point and the coordinate information of any second obstacle point in the second obstacle point set, distance information between the first obstacle point and any second obstacle point in the second obstacle point set; determining, based on distance information between the first obstacle point and any second obstacle point in the second obstacle point set of the first sub-obstacle point set, a second target obstacle point in the second obstacle point set having the shortest distance to the first target obstacle point; Determining a sub-passing distance of a first sub-obstacle point set according to the coordinate information of the first target obstacle point and the coordinate information of the second target obstacle point, and selecting a first target obstacle point from the first obstacle point set of the first sub-obstacle point set again; A shortest passage spacing is selected from a plurality of sub-passage spacings to form a target sub-passage spacing of the first sub-obstacle group, where the target sub-passage spacing is the first passage spacing of the first obstacle point set and the second obstacle point set.

2. The method according to claim 1, characterized in that The determining of the obstacle point set group according to the coordinate information of the obstacles within the detection range of the open-ground cluster group includes: Selecting an obstacle point from obstacles within the detection range of the open space cluster group as a first matching obstacle point; Determining, based on a relationship between coordinate information of the first matching obstacle point and coordinate information of other obstacle points within a detection range of the open-ground cluster group, a first target matching obstacle point that matches the first matching obstacle point, so that the first matching obstacle point and the first target matching obstacle point form a first obstacle point set; After eliminating the first matching obstacle point and the first target matching obstacle point, an obstacle point is again selected from the obstacles within the detection range of the open space cluster group as a second matching obstacle point, and a second obstacle point set is determined based on the second matching obstacle point.

3. The method according to claim 1, characterized in that The open space cluster group includes a first open space cluster and a second open space cluster; The determining, based on the initial pass state of the open-ground cluster group, the state information of each of the open-ground clusters, the target pass distance, and the target reference point, of a target pass state of the open-ground cluster group passing through obstacles within the detection range of the open-ground cluster group includes: When the initial passage state of the open space cluster group is the undeformed side-by-side state, if the target passage spacing is greater than or equal to the sum of the detection diameter of the first open space cluster and the detection diameter of the second open space cluster, it is determined that the target passage state of the open space cluster group passing through the obstacle within the detection range of the open space cluster group is the undeformed side-by-side state; If the target passage distance is less than the sum of the detection diameters of the first open space cluster and the second open space cluster, and greater than the maximum of the detection diameters of the first open space cluster and the second open space cluster, determine first time information when the first open space cluster moves to the target reference point and second time information when the second open space cluster moves to the target reference point based on the current position information of the first open space cluster, the current position information of the second open space cluster, the speed information of the first open space cluster, the speed information of the second open space cluster, and the target reference point; When the absolute value of the difference between the first time information and the second time information is less than a preset time, it is determined that the target passage state of the open-ground cluster group passing through the obstacle within the detection range of the open-ground cluster group is a deformed side-by-side state; when the absolute value of the difference between the first time information and the second time information is greater than or equal to the preset time, it is determined that the target passage state of the open-ground cluster group passing through the obstacle within the detection range of the open-ground cluster group is an undeformed sequential state, and the open-ground cluster corresponding to the smaller time information between the first time information and the second time information is selected to pass first; If the target passage distance is less than or equal to the maximum value of the detection diameter of the first open space cluster and the detection diameter of the second open space cluster, it is determined that the target passage state of the open space cluster group passing through the obstacles within the detection range of the open space cluster group is a deformation order state, and the open space cluster corresponding to the smaller time information between the first time information and the second time information is selected to pass first.

4. The method according to claim 1, wherein The open space cluster group includes a first open space cluster and a second open space cluster; The determining, based on the initial pass state of the open-ground cluster group, the state information of each of the open-ground clusters, the target pass distance, and the target reference point, of a target pass state of the open-ground cluster group passing through obstacles within the detection range of the open-ground cluster group includes: When the initial passage state of the open space cluster group is the undeformed sequential state, if the target passage spacing is greater than or equal to the sum of the detection diameter of the first open space cluster and the detection diameter of the second open space cluster, it is determined that the target passage state of the open space cluster group passing through obstacles within the detection range of the open space cluster group is the undeformed side-by-side state; If the target passage distance is less than the sum of the detection diameters of the first open space cluster and the second open space cluster, and greater than the maximum of the detection diameters of the first open space cluster and the second open space cluster, it is determined that the target passage state of the open space cluster group passing through the obstacles within the detection range of the open space cluster group is the undeformed order state; If the target passing distance is less than or equal to the maximum of the detection diameters of the first open space cluster and the second open space cluster, determining first time information when the first open space cluster moves to the target reference point and second time information when the second open space cluster moves to the target reference point based on the current position information of the first open space cluster, the current position information of the second open space cluster, the speed information of the first open space cluster, the speed information of the second open space cluster, and the target reference point; When the absolute value of the difference between the first time information and the second time information is greater than or equal to the preset time, it is determined that the target passage state of the open-ground cluster group through the obstacles within the detection range of the open-ground cluster group is a deformation order state, and the open-ground cluster corresponding to the smaller time information between the first time information and the second time information is selected to pass first.

5. The method according to claim 1, wherein The open space cluster group includes a first open space cluster and a second open space cluster; The determining, based on the initial pass state of the open-ground cluster group, the state information of each of the open-ground clusters, the target pass distance, and the target reference point, of a target pass state of the open-ground cluster group passing through obstacles within the detection range of the open-ground cluster group includes: When the initial passage state of the open space cluster group is the deformed side-by-side state, if the target passage spacing is greater than or equal to the sum of the detection diameters of the first open space cluster and the second open space cluster, it is determined that the target passage state of the open space cluster group passing through obstacles within the detection range of the open space cluster group is the undeformed side-by-side state; If the target passage distance is smaller than the sum of the detection diameters of the first open space cluster and the second open space cluster, and larger than the maximum of the detection diameters of the first open space cluster and the second open space cluster, it is determined that the target passage state of the open space cluster group passing through the obstacle within the detection range of the open space cluster group is a deformed side-by-side state; If the target passing distance is less than or equal to the maximum of the detection diameters of the first open space cluster and the second open space cluster, determining first time information when the first open space cluster moves to the target reference point and second time information when the second open space cluster moves to the target reference point based on the current position information of the first open space cluster, the current position information of the second open space cluster, the speed information of the first open space cluster, the speed information of the second open space cluster, and the target reference point; When the absolute value of the difference between the first time information and the second time information is greater than or equal to the preset time, it is determined that the target passage state of the open-ground cluster group through the obstacles within the detection range of the open-ground cluster group is a deformation order state, and the open-ground cluster corresponding to the smaller time information between the first time information and the second time information is selected to pass first.

6. The method according to claim 1, characterized in that The open space cluster group includes a first open space cluster and a second open space cluster; The determining, based on the initial pass state of the open-ground cluster group, the state information of each of the open-ground clusters, the target pass distance, and the target reference point, of a target pass state of the open-ground cluster group passing through obstacles within the detection range of the open-ground cluster group includes: When the initial passage state of the open space cluster group is the deformed order state, if the target passage spacing is greater than or equal to the sum of the detection diameter of the first open space cluster and the detection diameter of the second open space cluster, it is determined that the target passage state of the open space cluster group passing through obstacles within the detection range of the open space cluster group is the undeformed side-by-side state; If the target passage spacing is smaller than the sum of the detection diameter of the first open space cluster and the detection diameter of the second open space cluster, it is determined that the target passage state of the open space cluster group passing through obstacles within the detection range of the open space cluster group is a deformation order state.

7. The method according to claim 1, characterized in that Before determining the target passage state of the open-land cluster group passing through obstacles within the detection range of the open-land cluster group based on the initial passage state of the open-land cluster group, the state information of each of the open-land clusters, the target passage distance, and the target reference point, the method further includes: The deformation ratio is determined according to the target passage distance and the detection diameter of each of the open space clusters.

8. An air-ground unmanned cluster consensus decision-making device for conflict resolution, characterized by: include: an information acquisition module, configured to acquire an initial traffic state of an air-land cluster group, state information of each air-land cluster included in the air-land cluster group, and coordinate information of obstacles within the detection range of the air-land cluster group, wherein the initial traffic state of the air-land cluster includes an undeformed side-by-side state, an undeformed sequential state, a deformed side-by-side state, and a deformed sequential state; and the state information of each air-land cluster included in the air-land cluster group includes current position information, speed information, and detection diameter; A target information determination module, configured to determine a target clearance distance and a target reference point based on the coordinate information of obstacles within the detection range of the air-ground cluster group; a target passage state determination module, configured to determine the target passage state of the open-ground cluster group passing through obstacles within the detection range of the open-ground cluster group based on the initial passage state of the open-ground cluster group, the state information of each of the open-ground clusters, the target passage distance, and the target reference point; The determining of the target clearance distance and the target reference point according to the coordinate information of the obstacles within the detection range of the open-ground cluster group includes: Determining an obstacle point set group based on coordinate information of obstacles within the detection range of the air-ground cluster group, wherein the obstacle point set group includes multiple obstacle point sets, and any obstacle point set includes multiple obstacle points; Determining a first pass distance between any two obstacle point sets in the obstacle point set group, wherein the first pass distance is the shortest pass distance between any two obstacle point sets; Selecting the shortest of the first pass distances of any two obstacle point sets in the obstacle point set group as the target pass distance; Determining a target obstacle point according to the target clearance distance; Determine a target reference point according to the coordinate information of the target obstacle point; The determining of a first pass distance between any two obstacle point sets in the obstacle point set group includes: arbitrarily selecting two obstacle point sets from the obstacle point set group to form a sub-obstacle point set group, wherein any sub-obstacle point set group includes a first obstacle point set and a second obstacle point set; Selecting a first target obstacle point from the first obstacle point set of the first sub-obstacle point set group, and obtaining coordinate information of the first target obstacle point; determining, based on the coordinate information of the first target obstacle point and the coordinate information of any second obstacle point in the second obstacle point set, distance information between the first obstacle point and any second obstacle point in the second obstacle point set; determining, based on distance information between the first obstacle point and any second obstacle point in the second obstacle point set of the first sub-obstacle point set, a second target obstacle point in the second obstacle point set having the shortest distance to the first target obstacle point; Determining a sub-passing distance of a first sub-obstacle point set according to the coordinate information of the first target obstacle point and the coordinate information of the second target obstacle point, and selecting a first target obstacle point from the first obstacle point set of the first sub-obstacle point set again; A shortest passage spacing is selected from a plurality of sub-passage spacings to form a target sub-passage spacing of the first sub-obstacle group, where the target sub-passage spacing is the first passage spacing of the first obstacle point set and the second obstacle point set.

Images