Heterogeneous intelligent unmanned cluster cooperative positioning method and device, and storage medium

Abstract

The application provides a heterogeneous intelligent unmanned cluster cooperative positioning method, device and storage medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring first position information of a first intelligent agent; the first intelligent agent acquires relative position information of a second intelligent agent according to a preset distance threshold, and obtains measurement position information of the second intelligent agent position according to the first position information; and the measurement position information is sent to the second intelligent agent, so that the second intelligent agent combines the measurement position information and the second position information acquired by the second intelligent agent to calculate target positioning information of the second intelligent agent. In the application, the first intelligent agent is a strong intelligent agent, and the second intelligent agent is a weak intelligent agent. The strong intelligent agent has a strong ability to actively acquire information, while the weak intelligent agent has a weak ability to actively acquire information. Therefore, the strong intelligent agent is used to realize high-precision positioning, the remaining weak intelligent agents are positioned and optimized by the strong intelligent agent with partial positioning accuracy, and the application cost is reduced while the overall positioning accuracy is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and particularly relates to a heterogeneous intelligent unmanned cluster cooperative positioning method and device and a storage medium. BACKGROUND

[0002] An intelligent unmanned cluster refers to intelligent behaviors of a plurality of non-intelligent individuals in a group through simple cooperation between the individuals. The intelligent unmanned cluster is widely used in many fields such as transportation, manufacturing, agriculture, military and finance. The environmental information provided by the intelligent unmanned cluster in different environments provides important information basis for scene analysis, environment modeling, thorough perception and dynamic decision-making, and is an important part of the development of modern society.

[0003] In related technologies, the intelligent unmanned cluster often appears in a homogeneous manner, that is, the configurations of individuals in the intelligent unmanned cluster are almost the same. This leads to the fact that the individuals in the intelligent unmanned cluster need to be equipped with high-performance sensors, or rely on external positioning infrastructure, so as to estimate their own states. Because of high positioning requirements and great limitations, the positioning accuracy of the intelligent unmanned cluster is poor, and the application cost is increased. SUMMARY

[0004] Embodiments of the present application provide a heterogeneous intelligent unmanned cluster cooperative positioning method, device and storage medium, which can improve the positioning accuracy of the unmanned cluster and reduce the application cost.

[0005] To achieve the above object, a first aspect of embodiments of the present application provides a heterogeneous intelligent unmanned cluster cooperative positioning method, which comprises: acquiring first position information of a first intelligent agent; if a distance between the first intelligent agent and a second intelligent agent in an environment is less than a preset distance threshold, acquiring relative position information of the second intelligent agent relative to the first intelligent agent; calculating measurement position information for calibrating a position of the second intelligent agent according to the relative position information and the first position information; and sending the measurement position information to the second intelligent agent, so that the second intelligent agent calculates target positioning information of the second intelligent agent according to the second position information and the measurement position information after acquiring the second position information of the second intelligent agent.

[0006] In some embodiments, the method further comprises: acquiring the target positioning information of the second intelligent agent; performing flight path planning according to the target positioning information and the first position information to obtain a planned path; and controlling a flight state of the first intelligent agent according to the planned path, so that the first intelligent agent flies on the planned path.

[0007] In some embodiments, the target positioning information represents a real position of the second agent, and the measured position information represents a measured position of the second agent; the flight path planning according to the target positioning information and the first position information to obtain a planned path comprises: obtaining speed estimation information of the second agent; obtaining mutual information between the real position and the measured position of the second agent according to the target positioning information, the measured position information, the first position information and the speed estimation information; performing optimization operation according to the mutual information to optimize the first position information to obtain third position information; and determining the planned path of the first agent according to the third position information.

[0008] In some embodiments, there are multiple second agents; the optimization operation according to the mutual information to optimize the first position information to obtain third position information comprises: maximizing the mutual information to obtain target information for describing uncertainty of the second agents, obtaining first state information of each second agent based on the target information; obtaining second state information of the first agent and the second agents according to the first position information and the first state information; obtaining a speed instruction of the first agent, establishing a reward function according to the speed instruction, the first state information and the second state information; adjusting the speed instruction according to the reward function, and obtaining third position information according to the adjusted speed instruction and the first position information.

[0009] In some embodiments, the obtaining of the first state information of each second agent based on the target information comprises: obtaining the second position information, the speed estimation information and the measured position information of each second agent at a current time; and obtaining the first state information of each second agent according to the second position information, the speed estimation information, the measured position information and the target information at the current time.

[0010] To achieve the above object, a second aspect of the embodiments of the present application provides a heterogeneous intelligent unmanned cluster cooperative positioning method, applied to a second agent, and the method comprises: obtaining second position information of the second agent; if a distance between the second agent and a first agent is less than a preset distance threshold, receiving measured position information sent by the first agent; wherein the measured position information is calculated by the first agent according to relative position information and first position information, the first position information is obtained by the first agent itself, and the relative position information is obtained by the first agent when a distance between the first agent and the second agent in an environment is less than the preset distance threshold; and target positioning information of the second agent is calculated according to the measured position information and the second position information.

[0011] In some embodiments, the second agent is multiple, the target positioning information represents a real position of the second agent, the measurement position information represents a measurement position of the second agent, and the first position information is obtained by the first agent; the method further comprises: obtaining speed estimation information of the second agent; sending the speed estimation information to the first agent, so that the first agent obtains mutual information between the real position and the measurement position of each second agent according to the target positioning information, the measurement position information, the first position information and the speed estimation information, and performs optimization operation according to the mutual information to optimize the third position information obtained from the first position information, so that the first agent determines the planned path of the first agent according to the third position information.

[0012] In some embodiments, the second position information, the speed estimation information and the measurement position information are all information at the current time, and the first agent obtains the first state information of each second agent according to the second position information, the speed estimation information, the measurement position information and the target information at the current time.

[0013] To achieve the above object, a third aspect of the embodiments of the present application provides an electronic device, which comprises a memory and a processor, the memory stores a computer program, and the processor implements the method of the first aspect or the method of the second aspect when executing the computer program.

[0014] To achieve the above object, a fourth aspect of the embodiments of the present application provides a storage medium, which is a computer readable storage medium, the storage medium stores a computer program, and the computer program is executed by a processor to implement the method of the first aspect or the method of the second aspect.

[0015] The heterogeneous intelligent unmanned cluster cooperative positioning method, device and storage medium provided by the present application do not need to equip each agent with high-performance sensors with high price, but use part of the agents to carry high-performance sensors with high positioning accuracy to optimize the positioning of the remaining agents, thereby reducing the cost of application while improving the positioning accuracy of the heterogeneous intelligent unmanned cluster. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 is a schematic diagram of the heterogeneous intelligent unmanned cluster cooperative positioning system provided by the embodiments of the present application;

[0017] Figure 2 is a flowchart of the heterogeneous intelligent unmanned cluster cooperative positioning method provided by the embodiments of the present application;

[0018] Figure 3 is a path planning flowchart of the heterogeneous intelligent unmanned cluster cooperative positioning method provided by the embodiment of the present application;

[0019] Figure 4 is Figure 3 is a flowchart of step S202 in

[0020] Figure 5 is Figure 4 is a flowchart of step S303 in

[0021] Figure 6 is Figure 5 is a flowchart of step S401 in

[0022] Figure 7 is another flowchart of the heterogeneous intelligent unmanned cluster cooperative positioning method provided by the embodiment of the present application;

[0023] Figure 8 is still another flowchart of the heterogeneous intelligent unmanned cluster cooperative positioning method provided by the embodiment of the present application;

[0024] Figure 9 is a hardware structure schematic diagram of the electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the objectives, technical solutions and advantages of the present application clearer, further detailed description will be made to the present application in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0026] It should be noted that although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a manner different from the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification and claims and the above drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.

[0027] Unless otherwise defined, all 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 application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application, and are not intended to limit the present application.

[0028] The intelligent unmanned cluster system refers to an intelligent joint system composed of a certain number of homogeneous or heterogeneous unmanned systems or equipment, control systems and human-machine interfaces, which realizes mutual behavior cooperation, adapts to dynamic environment and completes specific tasks through information interaction and feedback, incentive and response.

[0029] In related technologies, intelligent unmanned swarms often appear in a homogeneous manner, that is, the configurations of individuals in the intelligent unmanned swarm are almost identical. This means that each individual in the intelligent unmanned swarm needs to be equipped with high-performance sensors or rely on external positioning infrastructure in order to estimate its own state. Because the positioning requirements are high and the limitations are large, the positioning accuracy of the intelligent unmanned swarm is poor and the application cost is increased.

[0030] Based on this, embodiments of this application provide a heterogeneous intelligent unmanned swarm collaborative positioning method, device, and storage medium, which can improve the positioning accuracy of intelligent unmanned swarms and reduce application costs.

[0031] The heterogeneous intelligent unmanned swarm cooperative positioning method, device, and storage medium provided in this application are specifically described through the following embodiments. First, the heterogeneous intelligent unmanned swarm cooperative positioning system of this application is introduced, and the heterogeneous intelligent unmanned swarm cooperative positioning method is applied to the heterogeneous intelligent unmanned swarm cooperative positioning system.

[0032] For example, refer to Figure 1 As shown, Figure 1 This is a schematic diagram of the heterogeneous intelligent unmanned swarm cooperative positioning system provided in the embodiments of this application. Figure 1 The first and second intelligent agents within the rectangular frame together constitute a heterogeneous intelligent unmanned swarm cooperative positioning system. The system comprises multiple first and second intelligent agents, with the number of second agents exceeding the number of first agents. The first intelligent agent is configured with a preset distance threshold. Figure 1 In the dashed line, the first and second intelligent agents represent entities within a preset distance threshold range of the first intelligent agent. Entities without dashed lines represent entities outside this range. The second intelligent agent can acquire a coarser second position information, while the first intelligent agent can acquire a more precise first position information. The first intelligent agent has a preset distance threshold. When the distance between the second and first intelligent agents is less than this threshold, the first intelligent agent acquires its relative position information and calculates its measured position information based on this relative information. This measured position information is then sent to the second intelligent agent. The second intelligent agent calculates its target positioning information based on the measured position information and its acquired second position information, and uses this target positioning information to represent its estimated positioning. Since only the first intelligent agent is equipped with an expensive device capable of accurately locating its own position, the heterogeneous intelligent unmanned swarm cooperative positioning method in this embodiment can achieve high-precision positioning of the heterogeneous intelligent unmanned swarm cooperative positioning system at a lower cost.

[0033] An agent refers to a computing entity that resides in an environment, can continuously and autonomously function, and has characteristics such as residency, reactivity, sociality, and initiative. In the embodiments of the present application, the first agent is a strong agent, and the second agent is a weak agent. The strong agent has strong perception ability, strong computing ability, and strong storage ability, and thus has strong ability to actively acquire information. In contrast, the weak agent has weak perception ability, weak computing ability, and weak storage ability, and thus has weak ability to actively acquire information. Therefore, in the embodiments of the present application, the strong agent can achieve high-precision positioning through strong acquisition ability, and the positioning accuracy of the weak agent is poor.

[0034] It should be noted that in each specific embodiment of the present application, when relevant processing needs to be performed according to user information, user behavior data, user historical data, and user location information, and other data related to the identity or characteristics of the user, the user's permission or consent is obtained first, for example, when a request for accessing user-stored data and user cache data is obtained, the user's permission or consent is obtained first. Moreover, the collection, use, and processing of such data comply with relevant national and regional laws, regulations, and standards. In addition, when the embodiments of the present application need to obtain sensitive personal information of the user, the user's separate permission or separate consent is obtained through a pop-up window or by jumping to a confirmation page, and after obtaining the user's separate permission or separate consent, the necessary user-related data for enabling the embodiments of the present application to normally operate is obtained.

[0035] Figure 2 is a flowchart of a heterogeneous intelligent unmanned cluster cooperative positioning method provided by the embodiments of the present application, Figure 2 The method in the flowchart can include, but is not limited to, steps S101 to S104:

[0036] Step S101: Obtain first position information of a first agent.

[0037] In some embodiments, the first position information is the coordinates of the first agent in a geodetic coordinate system or other unified coordinate system, and the first position information can accurately locate the specific position of the first agent in a recognized coordinate system. Specifically, the first position information can be obtained by a device carried by the first agent itself, can be obtained through a public mobile communication base station (hereinafter referred to as a "base station"), or can be obtained through a global positioning system (Global Positioning System, hereinafter referred to as "GPS").

[0038] In some embodiments, the first agent is a strong agent, which can obtain the first position information by itself carrying a high-performance sensor. Illustratively, the first agent carries a depth camera, which can detect the depth distance from the surrounding shooting space. By using the distance from each point in the image obtained by the depth camera to the depth camera and combining the two-dimensional coordinates of the image, the three-dimensional coordinates of each point in the image are obtained, so as to realize the acquisition of the first position information of the first agent.

[0039] It should be noted that the high-performance sensor can be a depth camera or a laser radar. The embodiments of the present application are only described by way of preferred embodiments and are not specifically limited.

[0040] In some embodiments, the first agent can calculate the first position information by the signals transmitted by the surrounding base stations. Illustratively, the first agent does not have a related high-performance sensor, but estimates the distance to the base station by the signal strength. Since the positions of the base stations are determined, the positioning information of the first agent, i.e., the first position information of the first agent, can be easily obtained by the base stations by using the characteristics that the distance from the first agent to the base station gradually increases and the signal weakens.

[0041] In some embodiments, the first agent can obtain the first position information by GPS. GPS is a high-precision radio navigation positioning system based on artificial earth satellites, which can provide high-precision geographic position. Illustratively, since GPS can easily obtain the current position by the satellite positioning system covering the whole world, the first agent can obtain the first position information by carrying the GPS system.

[0042] It should be noted that the acquisition of the first position information of the first agent is not limited to the acquisition method exemplified in the embodiments of the present application. The embodiments of the present application are only described by way of preferred embodiments and are not specifically limited.

[0043] In step S102, if the distance between the first agent and the second agent in the environment is less than a preset distance threshold, the relative position information of the second agent relative to the first agent is obtained.

[0044] In some embodiments, the second agent is a weak agent and the cost is low, the first agent is provided with a preset distance threshold value, the preset distance threshold value is used to represent the distance limit between the first agent and the second agent, and whether the second agent enters the range of the first agent to obtain the relative position information of the second agent can be determined by the preset distance threshold value between the first agent and the second agent. Specifically, the first agent is provided with a preset distance threshold value that can capture the second agent, when the second agent enters the distance threshold value range of the first agent, that is, the distance between the second agent and the first agent is less than the preset distance threshold value, the first agent can obtain the relative position information of the second agent relative to the first agent.

[0045] In some embodiments, the first agent is provided with a distance measuring sensor, the distance measuring sensor can sense the distance between the first agent and the second agent, and the distance measuring sensor is provided with a preset distance threshold value, when the distance between the second agent and the first agent is less than the preset distance threshold value set by the distance measuring sensor carried on the first agent, the first agent can obtain the relative position information of the second agent relative to the first agent.

[0046] In some embodiments, the relative position information includes the position, speed and other information of the second agent relative to the first agent. Since the first agent can obtain more accurate first position information of itself through a high-performance sensor, when the first agent obtains the relative position information of the second agent relative to the first agent, the relative position information has a certain positioning accuracy for positioning the second agent.

[0047] In some embodiments, the preset distance threshold value can be changed by modifying the threshold parameter in the distance measuring sensor of the first agent, or a distance measuring sensor with higher manufacturing precision can be selected to improve the preset distance threshold value range.

[0048] Exemplarily, as shown in Figure 1 , the first agent can obtain the relative position information of the second agent relative to the first agent within the preset distance threshold value range. For example, in Figure 1 , the first agent and the second agent are connected by a dashed line, which represents that the distance between the second agent and the first agent is less than the preset distance threshold value, at this time the first agent can obtain the relative position information of the second agent relative to the first agent within the distance threshold value range; while the first agent and the second agent without a dashed line represent that the second agent is not within the preset distance threshold value range of the first agent, at this time the first agent cannot obtain the relative position information of the second agent relative to the first agent within the distance threshold value range.

[0049] In step S103, the measurement position information of the second agent is calculated according to the relative position information and the first position information.

[0050] In some embodiments, after the first agent obtains the relative position information of the second agent relative to the first agent, the first agent can calculate the measurement position information of the second agent according to the obtained first position information and the relative position information. Specifically, the measurement position information represents the coordinates of the second agent in the geodetic coordinate system or other unified coordinate system calculated by the first agent according to the obtained first position information and the relative position information.

[0051] For example, the second agent generates relative position information such as relative position and speed during startup. The first agent can obtain the relative position information within the preset distance threshold range set by the distance measurement sensor mounted on the first agent, so that the first agent can calculate the measurement position information of the second agent position combined with the first position information. Since the first agent can obtain its own accurate position information through a high-performance sensor, when the first agent obtains the relative position information of the second agent relative to the first agent and calculates the measurement position information using the relative position information, the measurement position information has a certain positioning accuracy.

[0052] In step S104, the measurement position information is sent to the second agent, so that the second agent calculates the target positioning information of the second agent according to the second position information and the measurement position information after obtaining the second position information of the second agent.

[0053] In some embodiments, the second agent can obtain its own second position information, specifically, the second position information represents the second agent's estimation of its own position. After the first agent calculates the measured position information of the second agent, the first agent sends the calculated measured position information to the second agent, and the second agent can obtain the target positioning information of the second agent according to the second position information and the measured position information, the target positioning information represents the positioning coordinates of the second agent in the geodetic coordinate system or other unified coordinate system, and the target positioning information can more accurately represent the positioning position of the second agent in the recognized coordinate system. For example, the second agent estimates its own position by a low-cost and low-precision navigation positioning device carried by itself, the second agent entering the preset distance threshold range of the first agent can be obtained by the first agent relative position information, which can be calculated by the first agent with high positioning accuracy to obtain the measured position information of the second agent relative to the first agent, and the second agent adjusts the obtained second position information according to the measured position information to obtain the target positioning information with high positioning accuracy in the same coordinate system as the first agent. Adjusting the positioning estimation of the remaining second agent by a small part of the first agent with high positioning accuracy can achieve high-precision positioning of the heterogeneous intelligent unmanned cluster at a low cost.

[0054] In some embodiments, the second agent is equipped with an inertial navigation system, which is an autonomous navigation system that can measure the motion data of the second agent during operation and obtain the second position information of the second agent, i.e., the second agent's estimation of its own position, through calculation, such as the dead reckoning algorithm. The position estimation can provide the approximate position of the second agent, but the positioning accuracy is poor. For example, the second agent generates acceleration, angular acceleration and other motion data during operation, and the inertial navigation system carried by the second agent can perform time integration operation on the obtained acceleration, angular acceleration and other data to obtain the velocity and position data of the second agent, and then convert it to the geodetic coordinate system or other recognized coordinate system to obtain the rough position estimation of the second agent in the geodetic coordinate system or other recognized coordinate system.

[0055] In some embodiments, the first agent can receive the relative position information of the second agent within the preset distance threshold range of the first agent, and calculate the measured position information of the second agent relative to the first agent according to the relative position information. The first agent sends the calculated measured position information to the corresponding second agent within the preset distance threshold range, and the second agent calculates the target positioning information of the second agent according to the second position obtained by itself and the measured position information sent by the first agent to the second agent.

[0056] In some embodiments, the second agent uses a Bayesian filter to calculate the target positioning information of the second agent. In the embodiments of the present application, a special case Kalman filter in the Bayesian filter is used to calculate the target positioning information of the second agent. Specifically, the Kalman filter is a kind of linear system state equation, which uses the second position information of the second agent and the measured position data of the second agent by the first agent to perform prediction and update operations, and outputs the target positioning information of the second agent. The Kalman filter is used to fuse the second position information with relatively rough positioning accuracy of the second agent and the relative position information obtained by the first agent with relatively high positioning accuracy, so as to obtain target position information with relatively high positioning accuracy, which can represent the positioning information of the second agent with high accuracy.

[0057] It should be noted that the calculation of the target positioning information can select a suitable calculation method according to the specific use scene, such as a particle filter method, and the embodiments of the present application are only described in the preferred embodiments and are not specifically limited.

[0058] It should be noted that the embodiments of the present application are a heterogeneous intelligent unmanned cluster cooperative positioning method. In the case that the second agent can obtain the second position information, i.e., the self-position estimation, the first agent with accurate positioning is used to calculate the measured position information from the relative position information obtained by the second agent, and the measured position information is sent to the second agent. The second agent optimizes the obtained second position information according to the measured position information to obtain the target positioning information, thereby improving the positioning accuracy of the second agent, and realizing the high-precision positioning of the heterogeneous intelligent unmanned cluster at a low cost without the need to install an accurate positioning system on each agent.

[0059] To better enable the first agent to obtain the relative position information of the second agent, the heterogeneous intelligent unmanned cluster cooperative positioning method in the embodiments of the present application further plans a flight path for the first agent, Figure 3 is a path planning flowchart of the heterogeneous intelligent unmanned cluster cooperative positioning method provided by the embodiments of the present application, Figure 3 The method in the above embodiment can include but is not limited to including steps S201 to S202:

[0060] Step S201, obtaining target positioning information of a second agent;

[0061] In some embodiments, the target positioning information is obtained by the second agent by optimizing the second position information obtained by the second agent according to the measured position information. The second agent can send the target positioning information to the first agent, so that the first agent obtains the target positioning information in the second agent.

[0062] Step S202, flight path planning is performed according to the target positioning information and the first position information, and a planned path is obtained.

[0063] In some embodiments, the signal detected by the first agent will become weaker as the height rises, and similarly, when the distance between the second agent and the first agent is greater than the preset range, the first agent cannot obtain the relative position information of the second agent. In actual motion conditions, the second agent is in a state of irregular running trajectory, and in the case of multiple second agents moving at the same time, it is impossible for the first agent to always be in the center of only a part of the second agents to control that part of the second agents. In order to maximize the number of second agents within the preset distance threshold range of the first agent, flight path planning needs to be performed on the first agent, and a planned path is obtained.

[0064] It should be noted that the flight path planning of the first agent enables the first agent to enter the preset distance threshold range by moving itself, so that as many second agents as possible within the preset distance threshold range of the first agent can enter the preset distance threshold range of the first agent to obtain the relative position information of the second agents within the range, so that the second agents can obtain target positioning information with high precision according to the relative position information sent by the first agent. The flight path planning of the first agent enables multiple second agents to obtain accurate measurement position information in a timely manner to obtain target positioning information with higher positioning accuracy. In the case of not needing to install an accurate positioning system on each agent and achieving high-precision positioning of the intelligent unmanned cluster at a lower cost, the positioning accuracy of the heterogeneous intelligent unmanned cluster is further improved by flight path planning of the first agent equipped with a high-precision positioning system. At the same time, the cooperative positioning mode of the heterogeneous intelligent unmanned cluster is to enable a small number of first agents to optimize the positioning of the remaining second agents, so the heterogeneous intelligent unmanned cluster system has scalability, and can improve the execution efficiency and shorten the task execution time when a large-scale cluster is used to perform perception tasks.

[0065] Referring to Figure 4 , Figure 4 is Figure 3 a flowchart of step S202 in some embodiments, step S202 can further include steps S301 to S304:

[0066] Step S301, obtaining speed estimation information of the second agent;

[0067] In some embodiments, the first agent can obtain the speed estimation information of the second agent within the preset distance threshold range, and the speed estimation information of the second agent can enable the first agent to obtain the flight conditions of the second agent within the preset distance threshold range and adjust the flight path of the first agent through the speed estimation information.

[0068] In some embodiments, the second agent generates noise in the process of movement, and the first agent can process the received noise to obtain the speed estimation information of the second agent.

[0069] In some embodiments, the first agent can capture the movement image of the second agent, estimate the speed of the second agent according to the movement track of the second agent in the image, and obtain the speed estimation information of the second agent.

[0070] It should be noted that the manner in which the first agent obtains the speed estimation information of the second agent is not limited to the manner exemplified in the embodiments of the present application, and the embodiments of the present application are only described with the preferred embodiments and are not specifically limited.

[0071] In step S302, mutual information between the real position and the measured position of the second agent is obtained according to the target positioning information, the measured position information, the first position information and the speed estimation information.

[0072] In some embodiments, the first agent can obtain the mutual information between the real position and the measured position of the second agent according to the target positioning information, the measured position information, the first position information and the speed estimation information. Exemplarily, the target positioning information of the second agent represents the real position of the second agent , the second position information obtained by the second agent itself represents the measured position of the second agent , represents the position of the first agent at time 1 to t, is the speed estimation information of the i-th second agent at time 1 to t-1, represents the mutual information of two variables, and maximizes the mutual information between the real position and the measured position of the N weak agents within the time T, and is specifically represented as follows:

[0073]

[0074] In the embodiments of the present application, the mutual information is used to represent the correlation between the real position and the measured position of the second agent. The greater the value of the mutual information, the higher the correlation between the real position and the measured position of the second agent, and the accuracy of the heterogeneous intelligent unmanned cluster positioning is improved.

[0075] In step S303, optimization operation is performed according to the mutual information to optimize the first position information to obtain third position information.

[0076] In step S304, the planned path of the first agent is determined according to the third position information.

[0077] In some embodiments, the first agent optimizes mutual information between the real positions of the second agents and the measured positions, and optimizes the first position information to obtain third position information, which is used to indicate a flight path of the first agent.

[0078] In some embodiments, the first position information of the first agent represents position information of the first agent at a current time, and in order to better send the measured position information to more second agents, the flight path of the first agent needs to be optimized. According to the mutual information between the real positions of the second agents and the measured positions, the first position information of the first agent can be optimized to obtain third position information used to indicate a flight path of the first agent at a next time. The third position information can guide the flight path of the first agent, and by optimizing the flight path of the first agent, the second agents can be maximally brought into a preset distance threshold of the first agent to improve the positioning accuracy of the second agents.

[0079] In some embodiments, the third position information represents an action state used to indicate the first agent at a next time. For example, the third position information includes up, down, forward, backward, left or right of the first agent. When the third position information is up and when the next time comes, the first agent will fly upward, indicating that the second agents can be maximally brought into the preset distance threshold of the first agent when the first agent is up at the next time, and the second agents are provided with the measured position information.

[0080] It should be noted that the third position information of the first agent can be preset according to specific needs, and is not limited to the mentioned up, down, forward, backward, left or right, but can also include third position information such as 45° left or 45° right. The embodiments of the present application are only described with the preferred embodiments, and are not specifically limited.

[0081] Referring to Figure 5 , Figure 5 is Figure 4 a flowchart of step S302 in FIG. 4. In some embodiments, step S303 can further include steps S401 to S404:

[0082] In step S401, mutual information is maximized to obtain target information used to describe uncertainty of the second agents, and based on the target information, first state information of each second agent is obtained.

[0083] In some embodiments, the mutual information represents a correlation degree of the real positions and the measured positions of the second agents. In order to maximize the correlation degree, a maximum value of the mutual information is taken, which is used to describe the uncertainty of the second agents, and is denoted as an uncertainty metric of the second agents. The speed, position information and uncertainty metric of the second intelligent agent can be obtained by the inertial navigation system mounted on the second intelligent agent The first state information of the second intelligent agent. The first state information includes important parameter data of the second intelligent agent when running, and the first intelligent agent can establish a reward function for flight path planning of the first intelligent agent through the first state information, to guide the flight path planning of the first intelligent agent.

[0084] Referring to Figure 6 , Figure 6 is Figure 5 the flowchart of step S401, in some embodiments, step S401 can further include steps S501 to S502:

[0085] Step S501, obtaining the second position information, speed estimation information and measured position information of each second intelligent agent at the current time;

[0086] Step S502, obtaining the first state information of each second intelligent agent according to the second position information, speed estimation information, measured position information and target information at the current time.

[0087] Specifically, the first state information of the i-th second intelligent agent at time t is represented by , wherein the first state information includes the position of the second intelligent agent at time t , the speed estimation of the second intelligent agent at time t , the uncertainty of the position estimation of the second intelligent agent , and the measured position information of the second intelligent agent by the first intelligent agent at time t , which is specifically represented as:

[0088]

[0089] The first state information of the second intelligent agent includes the measurement of the second intelligent agent on its own motion data, the measurement of the first intelligent agent on the motion data of the second intelligent agent, and the uncertainty metric value between them. The first state information more completely contains the measurement data of the second intelligent agent, which can enable the first intelligent agent to adjust the flight path according to the measurement data.

[0090] Step S402, obtaining the second state information of the first intelligent agent and the second intelligent agent according to the first position information and the first state information;

[0091] In some embodiments, the first intelligent agent and the second intelligent agent together constitute a heterogeneous intelligent unmanned cluster, which is represented by The second state information of the heterogeneous intelligent unmanned cluster represents the second state information of the heterogeneous intelligent unmanned cluster. Exemplarily, the high-performance sensor carried on the first intelligent agent can obtain first position information of the motion of the first intelligent agent itself. In the embodiments of the present application, the first position information includes motion data such as the flight speed and flight position of the first intelligent agent, and together with the first state information, constitutes the second state information of the heterogeneous intelligent unmanned cluster .

[0092] In some embodiments, the second state information of the heterogeneous intelligent unmanned cluster system at time t is represented by , wherein the second state information includes the state of all second intelligent agents at time t and the first position information of the first intelligent agent at time t , and is specifically represented as

[0093]

[0094] The second state information of the heterogeneous intelligent unmanned cluster system includes the state of all second intelligent agents at time t and the first position information of the first intelligent agent at time t , which covers the motion data of the first intelligent agent and the second intelligent agent, and enables the first intelligent agent to plan a flight path according to the overall motion information of the heterogeneous intelligent unmanned cluster system.

[0095] In step S403, the speed instruction of the first intelligent agent is obtained, and a reward function is established according to the speed instruction, the first state information and the second state information;

[0096] In step S404, the speed instruction is adjusted according to the reward function, and third position information is obtained according to the adjusted speed instruction and the first position information.

[0097] In some embodiments, in order to enable the first intelligent agent to maximize the entry of the second intelligent agent into the preset distance threshold range of the first intelligent agent, the flight path of the first intelligent agent needs to be planned so that when the first intelligent agent moves from the current state to the next state, as many second intelligent agents as possible enter the preset threshold range of the first intelligent agent, so that the second intelligent agent can obtain the measurement position information sent by the first intelligent agent. Therefore, a reward function is established according to the speed instruction of the first intelligent agent, the first state information of the second intelligent agent and the second state information of the heterogeneous intelligent unmanned cluster system. The reward function can generate a reward value when the current state is changed to the next time state by the speed instruction, and the reward value is used to evaluate the benefit performance of the first intelligent agent when the current state is changed to the next time state by the speed instruction, so as to guide the first intelligent agent to better obtain the speed instruction.

[0098] In some embodiments, the speed instruction of the first agent includes a speed size and a speed direction, and the speed direction is a preset value, for example, in the embodiments of the present application, the speed direction of the first agent is up, down, forward, backward, left or right, and the speed size is adjusted by the first agent itself, and the speed instruction can guide the first agent to transit from the current time state to the next time state. Specifically, the reward function is represented as:

[0099]

[0100] wherein, is the second state information of the heterogeneous intelligent unmanned cluster at time t, is the speed instruction of the first agent at time t, and is the second state information of the heterogeneous intelligent unmanned cluster at time t+1. represents the uncertainty of the position estimation of the i-th second agent at time t, and the greater the value, the greater the uncertainty of the position estimation, is used to calculate the mean value of the position estimation uncertainty of all second agents. is a set of position estimation uncertainty of all second agents, means calculating the variance of the set, means calculating the variance of the position estimation uncertainty of all second agents. By minimizing the variance of the position estimation uncertainty of the second agent, the first agent not only pays attention to a part of the second agent, but also generates measurement data for all second agents as much as possible. and is an adjustment factor, which is used to adjust the importance of the reward function to the mean value and the variance. The reward function can optimize the flight path of the first agent according to the motion data of the first agent, the second agent and the heterogeneous intelligent unmanned cluster composed of them.

[0101] In some embodiments, the reward value of the reward function is calculated when the first agent transits from the current state to the next time state by the speed instruction of up, down, forward, backward, left or right, and according to the reward value of the reward function, for example, the speed instruction with the maximum reward value is taken as the next time flight path instruction of the first agent.

[0102] Figure 7 is another flowchart of the heterogeneous intelligent unmanned cluster cooperative positioning method provided by the embodiments of the present application, Figure 7 The method in the flowchart can include but is not limited to steps S601 to S603:

[0103] Step S601, obtaining the second position information of the second agent;

[0104] In some embodiments, the second agent is capable of obtaining its own second position information. For example, the second agent is equipped with an inertial navigation system, which is a self-contained navigation system capable of measuring the motion data of the second agent when it is running, and obtaining the second position information of the second agent, i.e. the estimation of the position of the second agent, by calculation, such as dead reckoning algorithm. The position estimation can provide the approximate position of the second agent, but the positioning accuracy is poor. For example, the second agent generates acceleration, angular acceleration and other motion data during running. The inertial navigation system carried by the second agent can perform time integration operation on the obtained acceleration, angular acceleration and other data to obtain the speed and position data of the second agent, and then convert it into the geodetic coordinate system or other recognized coordinate system to obtain the rough position estimation of the second agent in the geodetic coordinate system or other recognized coordinate system.

[0105] In step S602, if the distance between the second agent and the first agent is less than the preset distance threshold, the first agent sends the measurement position information to the second agent. The measurement position information is calculated by the first agent according to the relative position information and the first position information. The first position information is obtained by the first agent itself, and the relative position information is obtained by the first agent when the distance between the first agent and the second agent in the environment is less than the preset distance threshold.

[0106] In step S603, the target positioning information of the second agent is calculated according to the measurement position information and the second position information.

[0107] In some embodiments, the first agent is provided with a preset distance threshold. When the second agent enters the preset distance threshold range of the first agent, the first agent is capable of obtaining the relative position information of the second agent within the preset threshold range. The first agent calculates the measurement position information of the second agent according to the relative position information and sends the measurement position information to the second agent. For example, in Figure 1 In some embodiments, the first agent is provided with a preset distance threshold. When the second agent enters the preset distance threshold range of the first agent, the first agent is capable of obtaining the relative position information of the second agent within the preset threshold range. The first agent calculates the measurement position information of the second agent according to the relative position information and sends the measurement position information to the second agent. For example, in

[0108] In some embodiments, the second agent within the preset distance threshold can obtain target positioning information according to the measurement position information calculated by the first agent according to the relative position information and the second position information obtained by the second agent itself. Exemplarily, in Figure 1 the dashed line between the first agent and the second agent indicates that the distance between the second agent and the first agent is less than the preset distance threshold, at which time the first agent can obtain the relative position information of the second agent within the distance threshold range with respect to the first agent and calculate the measurement position information and then send it to the second agent, which receives the measurement position information.

[0109] It should be noted that if the second agent within the preset distance threshold range receives the measurement position information sent by the first agent, the target positioning information is the measurement position information; if the second agent is not within the preset distance threshold range of the first agent, the target positioning information is the second position information.

[0110] The first agent can obtain the relative position information of the second agent within the preset distance threshold range with respect to the first agent. For example, in Figure 1 the dashed line between the first agent and the second agent indicates that the distance between the second agent and the first agent is less than the preset distance threshold, at which time the first agent can obtain the relative position information of the second agent within the distance threshold range with respect to the first agent; and the first agent and the second agent without the dashed line indicate that the second agent is not within the preset distance threshold range of the first agent, at which time the first agent cannot obtain the relative position information of the second agent within the distance threshold range with respect to the first agent.

[0111] To enable the first agent to obtain the relative position information of the second agent, the second agent needs to send speed estimation information to the first agent, Figure 8 is another flowchart of the heterogeneous intelligent unmanned cluster cooperative positioning method provided by the embodiments of the present application, Figure 8 the method in may include but is not limited to steps S701 to S702:

[0112] Step S701, obtaining speed estimation information of the second agent;

[0113] Step S702, sending the speed estimation information to the first agent, so that the first agent obtains mutual information between the real position and the measurement position of each second agent according to the target positioning information, the measurement position information, the first position information and the speed estimation information, and performs optimization operation according to the mutual information to optimize the first position information to obtain third position information, so that the first agent determines the planning path of the first agent according to the third position information.

[0114] In some embodiments, the second agent is provided with an inertial navigation system, which is capable of obtaining speed estimation information of the second agent at runtime, specifically, the speed estimation information includes the speed size and the speed direction of the second agent. When the second agent enters the preset distance threshold range of the first agent, the speed estimation information is sent to the first agent.

[0115] In some embodiments, the second agent obtains its own speed estimation information through the inertial navigation system carried by itself, the speed estimation information includes the speed size and the speed direction, the first agent is provided with a preset distance threshold, when the distance between the second agent and the first agent is less than the preset distance threshold, the second agent is capable of sending the obtained speed estimation information to the first agent, the first agent receives the speed estimation information and obtains the mutual information between the real position of each second agent and the measured position according to the target positioning information, the measured position information, the first position information and the speed estimation information, optimizes the first position information to obtain the third position information, and plans the flight path of the first agent with the third position information. The speed estimation information of the second agent provides an important parameter for the planned path of the first agent, so that the first agent can improve the overall positioning accuracy of the heterogeneous intelligent unmanned cluster through path planning.

[0116] Further, the heterogeneous intelligent unmanned cluster cooperative positioning method provided by the embodiments of the present application further includes that the second position information, the speed estimation information and the measured position information are all information at the current time, and the first agent obtains the first state information of each second agent according to the second position information, the speed estimation information, the measured position information and the target information at the current time.

[0117] In some embodiments, the second position information is obtained by the second agent through an inertial navigation system carried by the second agent, the speed estimation information includes a speed size and a speed direction, and is obtained by the second agent through the inertial navigation system carried by the second agent, the measured position information is calculated by the first agent through the second position information and the relative position information, the target information is calculated by the first agent according to mutual information between the real position of the second agent and the measured position, the second position information, the speed estimation information, the measured position information and the target information are all motion data at the current moment, and jointly constitute the first state information, the first state information can be used by the first agent to optimize the flight path of the first agent, the purpose is to maximize the second agent to enter the preset distance threshold range of the first agent, so that the multiple second agents can obtain the measured position information with high positioning accuracy in time, to obtain the target positioning information with higher positioning accuracy, in the case that each agent does not need to carry a high-precision positioning system and realizes high-precision positioning of the intelligent unmanned cluster at a lower cost, the positioning accuracy of the heterogeneous intelligent unmanned cluster is further improved by flight path planning of the first agent carrying the high-precision positioning system.

[0118] It should be noted that the heterogeneous intelligent unmanned cluster cooperative positioning method in the embodiments of the present application realizes high-precision positioning of the heterogeneous intelligent unmanned cluster at a lower cost by positioning optimization of the remaining second agents by a small part of first agents carrying high-performance positioning equipment with a higher price. At the same time, the heterogeneous intelligent unmanned cluster cooperative positioning method is capable of positioning optimization of the remaining second agents by a small part of first agents, so that the heterogeneous intelligent unmanned cluster system has scalability, and when a large-scale cluster is used to perform perception and other tasks, the execution efficiency can be improved and the task execution time can be shortened.

[0119] The embodiments of the present application also provide an electronic device, which includes a memory and a processor, the memory stores a computer program, and the processor realizes the above-mentioned heterogeneous intelligent unmanned cluster cooperative positioning method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer and the like.

[0120] Reference Figure 9 , Figure 9 The hardware structure schematic diagram of the electronic device provided by the embodiments of the present application, the electronic device includes:

[0121] The processor 801 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, and is configured to execute related programs to implement the technical solutions provided by the embodiments of the present application.

[0122] The memory 802 can be implemented by a ROM (Read Only Memory), a static storage device, a dynamic storage device, or a RAM (Random Access Memory), and the like. The memory 802 can store an operating system and other application programs. When the technical solutions provided by the embodiments of the present application are implemented by software or firmware, the related program codes are stored in the memory 802 and are called and executed by the processor 801 to implement the heterogeneous intelligent unmanned cluster cooperative positioning method of the embodiments of the present application.

[0123] The input / output interface 803 is configured to implement information input and output.

[0124] The communication interface 804 is configured to implement the communication interaction between the device and other devices. The communication can be implemented by a wired manner (for example, a USB, a network cable, or the like) or a wireless manner (for example, a mobile network, WIFI, Bluetooth, or the like).

[0125] The bus 805 is configured to transmit information between various components (for example, the processor 801, the memory 802, the input / output interface 803, and the communication interface 804) of the device.

[0126] The processor 801, the memory 802, the input / output interface 803, and the communication interface 804 are connected to each other through the bus 805 to realize the communication connection between the device.

[0127] The embodiments of the present application further provide a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the above-mentioned heterogeneous intelligent unmanned cluster cooperative positioning method.

[0128] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include a high-speed random access memory and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory disposed remotely from the processor, which can be connected to the processor through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0129] The embodiments described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0130] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and can include more or fewer steps than shown in the figures, or combine certain steps, or different steps.

[0131] The device embodiments described above are only schematic, and the units described as separate components can or can not be physically separate, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0132] Those skilled in the art can understand that all or some of the steps in the above disclosed method, the functional modules / units in the system and the device can be implemented as software, firmware, hardware and their appropriate combinations.

[0133] The terms "first", "second", "third", "fourth" and the like used in the specification of the present application and the above-described drawings, if any, are used to distinguish similar objects, and do not necessarily have to describe a particular order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0134] It should be understood that, in the application, "at least one" means one or more, "multiple" means two or more. "And / or" is used to describe the relationship between the associated objects, which means that there can be three relationships, for example, "A and / or B" can mean: only A, only B, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c, can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0135] In several embodiments provided in the application, it should be understood that the disclosed system and method can be implemented in other ways. For example, the above-described system embodiments are only illustrative, for example, the division of the above units is only a logical functional division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0136] The units described above as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple network units. According to actual needs, some or all of the units can be selected to achieve the purpose of the embodiment.

[0137] In addition, the functional units in each embodiment of the application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0138] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program storage media.

[0139] The preferred embodiments of the embodiments of the present application are described above with reference to the accompanying drawings, and are not limited to the scope of the embodiments of the present application. Any modifications, equivalent replacements and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of the embodiments of the present application.

Claims

1. A heterogeneous intelligent swarm cooperative positioning method, characterized in that, Applied to the first agent, the method comprises: obtaining first position information of the first agent; if the distance between the first agent and a second agent in the environment is less than a preset distance threshold, obtaining relative position information of the second agent relative to the first agent; calculating measurement position information for calibrating the position of the second agent according to the relative position information and the first position information; sending the measurement position information to the second agent, so that the second agent calculates target positioning information of the second agent according to the second position information and the measurement position information after obtaining the second position information of itself; the method further comprises: obtaining the target positioning information of the second agent; flight path planning according to the target positioning information and the first position information to obtain a planned path; controlling the flight state of the first agent according to the planned path, so that the first agent flies on the planned path; the target positioning information represents the true position of the second agent, and the measurement position information represents the measured position of the second agent; the flight path planning according to the target positioning information and the first position information to obtain a planned path comprises: obtaining speed estimation information of the second agent; obtaining mutual information between the true position and the measured position of the second agent according to the target positioning information, the measurement position information, the first position information and the speed estimation information; optimization operation according to the mutual information to optimize the first position information to obtain third position information; determining the planned path of the first agent according to the third position information. 2.The heterogeneous intelligent swarm cooperative positioning method according to claim 1, characterized in that, The second agent has multiple; the optimization operation according to the mutual information to optimize the first position information to obtain third position information comprises: maximizing the mutual information to obtain target information for describing the uncertainty of the second agent, and obtaining first state information of each second agent based on the target information; obtaining second state information of the first agent and the second agent according to the first position information and the first state information; obtaining speed command of the first agent, and establishing reward function according to the speed command, the first state information and the second state information; adjusting the speed command according to the reward function, and obtaining third position information according to the adjusted speed command and the first position information. 3.The heterogeneous intelligent swarm cooperative positioning method according to claim 2, characterized in that, The first state information of each second agent based on the target information comprises: obtaining the second position information, the speed estimation information and the measurement position information of each second agent at the current time; obtaining first state information of each second agent according to the second position information, the speed estimation information, the measurement position information and the target information at the current time.

4. A heterogeneous intelligent swarm cooperative positioning method, characterized in that, Applied to the second agent, the method comprises: obtaining second position information of the second agent; if a distance between the second agent and the first agent is less than a preset distance threshold, receiving measurement position information sent by the first agent, wherein the measurement position information is calculated by the first agent according to relative position information and first position information, the first position information is obtained by the first agent itself, and the relative position information is obtained by the first agent when the distance between the first agent and the second agent in the environment is less than the preset distance threshold; calculating target positioning information of the second agent according to the measurement position information and the second position information; the method further comprises: obtaining the target positioning information of the second agent; performing flight path planning according to the target positioning information and the first position information to obtain a planned path; controlling a flight state of the first agent according to the planned path, so that the first agent flies on the planned path; the target positioning information represents a real position of the second agent, and the measurement position information represents a measurement position of the second agent; the flight path planning according to the target positioning information and the first position information to obtain a planned path comprises: obtaining speed estimation information of the second agent; obtaining mutual information between the real position and the measurement position of the second agent according to the target positioning information, the measurement position information, the first position information and the speed estimation information; performing optimization operation according to the mutual information to optimize the first position information to obtain third position information; determining the planned path of the first agent according to the third position information.

5. The heterogeneous intelligent swarm cooperative positioning method according to claim 4, characterized in that, the second agent has a plurality of second agents, the target positioning information represents a real position of the second agent, and the measurement position information represents a measurement position of the second agent, and the first position information is obtained by the first agent; the method further comprises: obtaining speed estimation information of the second agent; sending the speed estimation information to the first agent, so that the first agent obtains mutual information between the real position and the measurement position of each second agent according to the target positioning information, the measurement position information, the first position information and the speed estimation information, and performs optimization operation according to the mutual information to optimize the first position information to obtain third position information, so that the first agent determines the planned path of the first agent according to the third position information.

6. The heterogeneous intelligent swarm cooperative positioning method according to claim 5, wherein, the second position information, the speed estimation information and the measurement position information are all information at the current time, and the first agent obtains first state information of each second agent according to the second position information, the speed estimation information, the measurement position information and target information at the current time, wherein the target information is obtained by maximizing the mutual information.

7. An electronic device, comprising: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the heterogeneous intelligent unmanned cluster cooperative positioning method in any one of claims 1 to 3 or the heterogeneous intelligent unmanned cluster cooperative positioning method in any one of claims 4 to 6 when executing the computer program.

8. A computer readable storage medium, the storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the heterogeneous intelligent unmanned cluster cooperative positioning method in any one of claims 1 to 3 or the heterogeneous intelligent unmanned cluster cooperative positioning method in any one of claims 4 to 6.

Images