Multi-agent collaborative guiding type positioning method and device

Abstract

The invention provides a multi-agent cooperative guiding type positioning method and device, multiple agents comprise a portable terminal and a mobile platform, and the method comprises the following steps: aligning pose coordinate systems of the portable terminal and the mobile platform; under the pose coordinate system, calculating a first six-degree-of-freedom pose when the portable terminal moves to the target point in real time so as to generate a path local map; the mobile platform is deployed on the mobile equipment, and the mobile platform calculates an optimal planning path of the mobile equipment under the pose coordinate system based on the path local map and calculates a second six-degree-of-freedom pose corresponding to the optimal planning path in real time so as to generate a vertex of the optimal planning path; and comparing and optimizing the path local map and the vertexes to obtain a target moving track of the mobile device moving to the target point, and guiding the mobile device to move to the target point. Therefore, the track of the mobile platform is aligned to the track of the portable terminal in real time, the moving track of the target is dynamically updated, and the positioning precision and efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of collaborative positioning, and in particular to a guided positioning method, device, electronic device and storage medium for multi-agent collaboration. Background Art

[0002] Problems of navigation and positioning in mobile vehicles, collaborative robots, and indoor scenarios. In the prior art, positioning technologies mainly rely on the independent positioning systems of individual devices, such as the Global Positioning System (GPS), inertial navigation System (INS), visual-inertial odometry (VIO), etc. These independent positioning systems perform well in a single environment, but in complex environments or large-scale movements, problems such as cumulative positioning errors are likely to occur, resulting in low positioning accuracy. Summary of the Invention The present invention aims to solve at least one of the technical problems in the related art to some extent.

[0003] To this end, the first object of the present invention is to propose a guided positioning method for multi-agent collaboration, which aligns the trajectory of the mobile platform to the trajectory of the portable terminal in real time, dynamically updates the target movement trajectory, and improves the positioning accuracy and efficiency.

[0004] The second object of the present invention is to propose a guided positioning device for multi-agent collaboration.

[0005] The third object of the present invention is to propose an electronic device.

[0006] The fourth object of the present invention is to propose a non-transitory computer-readable storage medium storing computer instructions.

[0007] To achieve the above object, an embodiment of the first aspect of the present invention proposes a guided positioning method for multi-agent collaboration, where the multi-agent includes a portable terminal and a mobile platform, and the method includes: Align the pose coordinate systems of the portable terminal and the mobile platform; In the pose coordinate system, the first six-degree-of-freedom pose when the portable terminal moves to the target point is calculated in real time by fusing the odometer of the visual sensor and the inertial measurement unit, and based on the first six-degree-of-freedom pose, a path local map when the mobile terminal moves is generated and sent to the mobile platform. The path local map includes visual feature points, descriptors, and waypoints corresponding to the movement of the portable terminal; The mobile platform is deployed on a mobile device. Based on the local path map, the mobile platform calculates the optimal planned path of the mobile device in the pose coordinate system through a path planning algorithm, and calculates in real time the second six-degree-of-freedom pose of the mobile device moving to the target point based on the optimal planned path by fusing the odometer of a vision sensor and an inertial measurement unit. Based on the second six-degree-of-freedom pose, vertices of the optimal planned path are generated, and the vertices include visual feature points, descriptors, and waypoints corresponding to the movement of the mobile device along the optimal planned path. The local path map and the vertices are compared and optimized by a service module deployed on the mobile platform to obtain the target movement trajectory of the mobile device moving to the target point, and the mobile device is guided to move to the target point based on the target movement trajectory.

[0008] To achieve the above object, a guided positioning device for multi-agent collaboration according to a second aspect embodiment of the present invention includes a portable terminal and a mobile platform as the multi-agents, and the device includes: An alignment module for aligning the pose coordinate systems of the portable terminal and the mobile platform. A first calculation module for calculating in real time the first six-degree-of-freedom pose of the portable terminal when moving to the target point in the pose coordinate system by fusing the odometer of a vision sensor and an inertial measurement unit, generating a local path map of the movement of the mobile terminal based on the first six-degree-of-freedom pose, and sending it to the mobile platform. The local path map includes visual feature points, descriptors, and waypoints corresponding to the movement of the portable terminal. A second calculation module for deploying the mobile platform on a mobile device. The mobile platform calculates the optimal planned path of the mobile device in the pose coordinate system through a path planning algorithm based on the local path map, and calculates in real time the second six-degree-of-freedom pose of the mobile device moving to the target point based on the optimal planned path by fusing the odometer of a vision sensor and an inertial measurement unit. Based on the second six-degree-of-freedom pose, vertices of the optimal planned path are generated, and the vertices include visual feature points, descriptors, and waypoints corresponding to the movement of the mobile device along the optimal planned path. A guiding module for comparing and optimizing the local path map and the vertices by a service module deployed on the mobile platform to obtain the target movement trajectory of the mobile device moving to the target point, and guiding the mobile device to move to the target point based on the target movement trajectory.

[0009] To achieve the above object, an embodiment of the third aspect of the present invention provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method described in the first aspect.

[0010] To achieve the above object, an embodiment of the fourth aspect of the present invention provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method described in the first aspect.

[0011] The multi-agent collaborative guided positioning method, device, electronic device and storage medium provided by the embodiments of the present invention are applied to a portable terminal and a mobile platform, aligning the pose coordinate systems of the portable terminal and the mobile platform; in the pose coordinate system, the first six-degree-of-freedom pose when the portable terminal moves to a target point is calculated in real time to generate a local path map; the mobile platform is deployed on a mobile device, and based on the local path map, the mobile platform calculates the optimal planned path of the mobile device in the pose coordinate system, and calculates the corresponding second six-degree-of-freedom pose of the optimal planned path in real time to generate the vertices of the optimal planned path; the local path map and the vertices are compared and optimized to obtain the target movement trajectory of the mobile device moving to the target point, and the mobile device is guided to move to the target point. Thus, the trajectory of the mobile platform is aligned with the trajectory of the portable terminal in real time, and the target movement trajectory is dynamically updated, improving the accuracy and efficiency of positioning.

[0012] The additional aspects and advantages of the present invention will be partly given in the following description, partly will become obvious from the following description, or will be understood through the practice of the present invention. Description of the Drawings

[0013] The above and / or additional aspects and advantages of the present invention will become obvious and easy to understand from the following description of the embodiments in conjunction with the drawings, where: Figure 1 is a schematic flow chart of a multi-agent collaborative guided positioning method provided by an embodiment of the present invention; Figure 2 is a schematic diagram of a multi-agent collaborative positioning trajectory provided by an embodiment of the present invention; Figure 3 is an application flow chart of another multi-agent collaborative guided positioning method provided by an embodiment of the present invention; Figure 4 is a schematic structural diagram of a multi-agent collaborative guided positioning device provided by an embodiment of the present invention. Detailed Embodiments

[0014] Embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0015] It should be noted that in the technical solution of the present invention, the acquisition, storage, use, processing, etc. of data all comply with the relevant regulations of relevant laws and regulations.

[0016] The following describes a multi-agent collaborative guided positioning method, device, electronic device, and storage medium according to an embodiment of the present invention with reference to the accompanying drawings.

[0017] Figure 1 It is a schematic flowchart of a multi-agent collaborative guided positioning method provided by an embodiment of the present invention.

[0018] As Figure 1 shown, the multi-agent includes a portable terminal and a mobile platform, and the method includes the following steps: Step 101, align the pose coordinate systems of the portable terminal and the mobile platform.

[0019] In some possible implementation manners, the pose coordinate systems of the portable terminal and the mobile platform can be aligned by using visual tags corresponding to visual sensors or measurement data of an Inertial Measurement Unit (IMU) to solve the problem of benchmark differences between heterogeneous devices.

[0020] Among them, the visual sensor can be composed of one or two graphic sensors, and the inertial measurement unit can be a device for measuring the three-axis attitude angle (or angular rate) and acceleration of an object.

[0021] In some other possible implementation manners, the pose coordinate systems of the portable terminal and the mobile platform can also be aligned by Ultra Wide Band (UWB) positioning or lidar calibration to improve the alignment accuracy of the pose coordinate systems.

[0022] Optionally, the portable terminal can be a positioning pen, but is not limited thereto.

[0023] Optionally, the mobile platform can be a mobile vehicle, a service platform of a collaborative robot, but is not limited thereto.

[0024] Step 102: In the pose coordinate system, the first six-degree-of-freedom pose of the portable terminal when it moves to the target point is calculated in real time by fusing the visual sensor and the inertial measurement unit odometer. Based on the first six-degree-of-freedom pose, a local path map of the mobile terminal during movement is generated and sent to the mobile platform. The local path map contains visual feature points, descriptors, and waypoints corresponding to the movement of the portable terminal.

[0025] Among them, the six-degree-of-freedom pose means that an object has six degrees of freedom in space, namely the translational degrees of freedom along the three rectangular coordinate axes x, y, and z and the rotational degrees of freedom around these three coordinate axes.

[0026] Among them, the visual feature point refers to a point with uniqueness and stability in the image. These points remain unchanged even when the camera's perspective changes and are commonly used for camera pose estimation. Feature points can be corner points, edges, or blocks, etc. Among them, corner points are the easiest to identify and are commonly used in visual sensors (Visual SLAM).

[0027] The descriptor is a data structure related to the visual feature point and is used to describe the appearance and attributes of the feature point. In the SLAM system, the descriptor is used to match the visual feature points in the new frame with the feature points in the map. Each visual feature point has one or more descriptors, and the visual feature points are matched by calculating the distance or similarity between the descriptors.

[0028] The waypoint in the SLAM system usually refers to the feature point in the image. These feature points are sparsely represented in the map and are used to construct a sparse map. Waypoints are not only used for positioning and navigation but also participate in tasks such as path planning and obstacle avoidance.

[0029] The local map (Submap) refers to the map constructed within a certain area and is usually used in real-time SLAM systems. The local map contains key frames and map points within this area and is used for real-time positioning and navigation. The construction and maintenance of the local map are crucial for improving the real-time performance and accuracy of the SLAM system.

[0030] Step 103: The mobile platform is deployed on the mobile device. Based on the local path map, the mobile platform calculates the optimal planned path of the mobile device in the pose coordinate system through a path planning algorithm, and in real time calculates the second six-degree-of-freedom pose of the mobile device moving to the target point based on the optimal planned path by fusing the visual sensor and the inertial measurement unit odometer. Based on the second six-degree-of-freedom pose, the vertices of the optimal planned path are generated. The vertices contain visual feature points, descriptors, and waypoints corresponding to the movement of the mobile device based on the optimal planned path.

[0031] Optionally, the path planning algorithm is a computational method for determining the optimal path from a starting point to a target point, including but not limited to traditional graph search algorithms, sampling-based algorithms, and intelligent bionic algorithms.

[0032] Among them, the Vertex containing visual feature points, descriptors, and waypoint markers is a node in the SLAM system used to represent a waypoint marker in the map. It contains the 3D position of the waypoint marker, related visual feature points, and descriptors, and is optimized together with other nodes (such as the pose of the visual sensor) through graph optimization to achieve accurate positioning and map construction.

[0033] In some possible implementation manners, after the odometer that fuses the visual sensor and the inertial measurement unit calculates in real time the optimal planned path of the mobile device, the speed and steering angle of the mobile device can be adjusted in real time through the controller in the mobile platform to guide it to move to the target point based on the optimal planned path. The mobile platform publishes Vertex at a high frequency to support loop detection and global optimization at the millisecond level.

[0034] Step 104: Compare and optimize the path local map and vertices through the service module deployed on the mobile platform to obtain the target movement trajectory for the mobile device to move to the target point, and guide the mobile device to move to the target point based on the target movement trajectory.

[0035] In some possible implementation manners, the multi-threaded service in the service module deployed on the mobile platform is used to perform local map optimization to complete the correction of the path local map, and a loop detection database is constructed according to the corrected path local map; when performing loop detection on the vertices through the Bag-of-words model (BoW) installed on the service module deployed on the mobile platform, the target path corresponding to the vertices is obtained; the real-time path local map corresponding to the target path is intercepted from the loop detection database through the sliding window method; the target path is compared and optimized based on the real-time path local map to obtain the target movement trajectory for the mobile device to move to the target point, and guide the mobile device to move to the target point based on the target movement trajectory. Through the hierarchical processing of Submap local optimization and Vertex global optimization, the computational load is reduced, enabling the mobile platform to respond in real time to changes in the target point of the portable terminal and adapt to complex scenarios.

[0036] In summary, the schematic diagram of the multi-agent collaborative positioning trajectory is as Figure 2 shown. The multi-agent collaborative positioning trajectory includes a portable terminal, a mobile platform, a portable path (path local map), a mobile path (vertices), and the target point position.

[0037] In the guided positioning method with multi-agent collaboration according to the embodiments of the present invention, digital object data that digitally describes the position, shape, and attitude information of an object to be manipulated by a robot is obtained through a preset positioning pen module. This digital object data is used as the input to the deep neural network of the corresponding simulation platform of the robot, and the manipulation position of the object controlled by the robot is used as the output to train an initial position planning model of the robot. Based on the application scenario of the object, the corresponding observation space and task reward logic are selected to optimize the initial position planning model for the scenario, and a robot position planning model is obtained. The robot position planning model predicts the digital object data of the object to be manipulated to obtain the target position of the robot for manipulating the object to be manipulated. Thus, based on the trained robot position planning model, the planning accuracy of the robot meets the implementation requirements of various industrial scenarios, and the workload of manual operation is significantly reduced.

[0038] To clearly illustrate the previous embodiment, Figure 3 The following is an application flowchart of a guided positioning method with multi-agent collaboration provided by the embodiments of the present invention. Specifically, in the case where the portable terminal is a positioning pen and the mobile platform is a service platform of a mobile vehicle, the local path map (Submap_n,..., Submap_0) during the movement of the positioning pen is collected in real time and sent to the service module deployed on the service platform. The multi-threaded service in the service module is used to perform local map optimization to complete the correction of the local path map. A loop detection database (Submap_0, Submap_1,..., Submap_n) is constructed based on the corrected local path map. At the same time, based on the local path map, the optimal planned path of the mobile vehicle is calculated, and the vertices (Vertex_n,..., Vertex_0) of the optimal planned path are generated. When performing loop detection on the vertices through the bag-of-words model installed on the service module, the target path corresponding to the vertices is obtained, and the real-time path local map corresponding to the target path is intercepted from the loop detection database by the sliding window method. The target path is optimized based on the real-time path local map to obtain the target movement trajectory for the mobile vehicle to move to the target point, and the mobile vehicle is guided to move to the target point based on the target movement trajectory. Thus, through the dynamic acquisition of the portable terminal and the collaborative optimization of the path of the mobile platform, the redundant vertex data volume is reduced, and the positioning efficiency is improved.

[0039] In addition, when communicating between the vehicle-end server, the pen-end, and the vehicle-end, if the wireless bandwidth is limited, compression transmission can be adopted, including but not limited to compressing Submap data using the data structure serialization and deserialization framework ProtoBuf.

[0040] To implement the above embodiments, the present invention also proposes a guided positioning device with multi-agent collaboration.

[0041] Figure 4Schematic diagram of a guided positioning device for multi-agent collaboration provided by an embodiment of the present invention.

[0042] As Figure 4 shown, the multi-agent includes a portable terminal and a mobile platform. The guided positioning device 40 for multi-agent collaboration includes: a comparison module 41, a first calculation module 42, a second calculation module 43, and a guidance module 44.

[0043] The comparison module 41 is used to align the pose coordinate systems of the portable terminal and the mobile platform; The first calculation module 42 is used to, in the pose coordinate system, calculate in real time the first six-degree-of-freedom pose when the portable terminal moves to the target point by fusing the odometer of the vision sensor and the inertial measurement unit, and generate a local path map when the mobile terminal moves based on the first six-degree-of-freedom pose, and send it to the mobile platform. The local path map includes visual feature points, descriptors, and waypoints corresponding to the movement of the portable terminal; The second calculation module 43 is used to deploy the mobile platform on a mobile device. The mobile platform calculates the optimal planned path of the mobile device in the pose coordinate system based on the local path map through a path planning algorithm, and calculates in real time the second six-degree-of-freedom pose when the mobile device moves to the target point based on the optimal planned path by fusing the odometer of the vision sensor and the inertial measurement unit, and generates vertices of the optimal planned path. The vertices include visual feature points, descriptors, and waypoints corresponding to the movement of the mobile device based on the optimal planned path; The guidance module 44 is used to compare and optimize the local path map and the vertices through a service module deployed on the mobile platform to obtain the target movement trajectory of the mobile device moving to the target point, and guide the mobile device to move to the target point based on the target movement trajectory.

[0044] Further, in a possible implementation manner of the embodiment of the present invention, the comparison module 41 is specifically used for: Aligning the pose coordinate systems of the portable terminal and the mobile platform through visual tags corresponding to the vision sensor or measurement data of the inertial measurement unit.

[0045] Further, in a possible implementation manner of the embodiment of the present invention, the comparison module 41 is also specifically used for: Aligning the pose coordinate systems of the portable terminal and the mobile platform through ultra-wideband positioning or laser radar calibration.

[0046] Further, in a possible implementation manner of the embodiment of the present invention, the guidance module 44 is specifically used for: Local map optimization is performed through multi-threaded services in the service module deployed on the mobile platform to complete the correction of the local path map, and a loop detection database is constructed based on the corrected local path map; When performing loop detection on the vertex through the bag-of-words model installed on the service module deployed on the mobile platform, the target path corresponding to the vertex is obtained; The real-time local path map corresponding to the target path is intercepted from the loop detection database by the sliding window method; The target path is compared and optimized based on the real-time local path map to obtain the target movement trajectory for the mobile device to move to the target point, and the mobile device is guided to move to the target point based on the target movement trajectory.

[0047] It should be noted that the foregoing explanation of the method embodiment also applies to the device of this embodiment, and will not be repeated here.

[0048] The guided positioning device with multi-agent collaboration according to the embodiment of the present invention, the multi-agents include a portable terminal and a mobile platform, and the pose coordinate systems of the portable terminal and the mobile platform are aligned; in the pose coordinate system, the first six-degree-of-freedom pose when the portable terminal moves to the target point is calculated in real time to generate a local path map; the mobile platform is deployed on the mobile device, and based on the local path map, the optimal planned path of the mobile device in the pose coordinate system is calculated, and the second six-degree-of-freedom pose corresponding to the optimal planned path is calculated in real time to generate the vertex of the optimal planned path; the local path map and the vertex are compared and optimized to obtain the target movement trajectory for the mobile device to move to the target point, and it is guided to move to the target point. Thus, the trajectory of the mobile platform is aligned with the trajectory of the portable terminal in real time, and the target movement trajectory is dynamically updated, improving the accuracy and efficiency of positioning.

[0049] To implement the above embodiment, the present invention also proposes an electronic device, including: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the foregoing method.

[0050] To implement the above embodiment, the present invention also proposes a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the foregoing method.

[0051] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples", etc., mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0052] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of the present invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0053] Any process or method description shown in a flowchart or described in other ways herein can be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a customized logic function or process, and the scope of the preferred embodiments of the present invention includes additional implementations, where the functions may be executed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0054] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite ordered listing of executable instructions for implementing logical functions, which can be embodied specifically in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processor, or other systems that can fetch instructions from and execute the instructions of the instruction execution system, apparatus, or device. As used in this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection part having one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable medium on which the program can be printed, as the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.

[0055] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.

[0056] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the method of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0057] In addition, each functional unit in various embodiments of the present invention may be integrated into a processing module, or each unit may exist physically alone, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0058] The above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A multi-agent collaborative guided positioning method, characterized in that: The multi-agent comprises a portable terminal and a mobile platform, and the method comprises: Aligning the pose coordinate systems of the portable terminal and the mobile platform; In the pose coordinate system, a first six-degree-of-freedom pose of the portable terminal when it moves to a target point is calculated in real time by fusing a visual sensor and an odometer of an inertial measurement unit, and a local map of the path of the mobile terminal when it moves is generated based on the first six-degree-of-freedom pose, and sent to the mobile platform, wherein the local map of the path includes visual feature points, descriptors, and landmarks corresponding to the movement of the portable terminal; The mobile platform is deployed on the mobile device. The mobile platform calculates the optimal planned path of the mobile device in the pose coordinate system based on the path local map through a path planning algorithm, and calculates the second six-degree-of-freedom pose of the mobile device moving to the target point based on the optimal planned path in real time by fusing the visual sensor and the odometer of the inertial measurement unit, and generates the vertices of the optimal planned path based on the second six-degree-of-freedom pose, wherein the vertices include visual feature points, descriptors, and landmark points corresponding to the movement of the mobile device based on the optimal planned path; The local map and vertices of the path are compared and optimized through a service module deployed on the mobile platform to obtain a target movement trajectory of the mobile device moving to the target point, and guide the mobile device to move to the target point based on the target movement trajectory.

2. The method according to claim 1, characterized in that: Align the pose coordinate systems of the portable terminal and the mobile platform, including: The position coordinate system of the portable terminal and the mobile platform is aligned through the visual tag corresponding to the visual sensor or the measurement data of the inertial measurement unit.

3. The method according to claim 2, characterized in that The method further comprises: The pose coordinate systems of the portable terminal and the mobile platform are aligned through ultra-wideband positioning or lidar calibration.

4. The method according to claim 1, characterized in that: The service module deployed on the mobile platform compares and optimizes the path local map and vertices to obtain a target movement trajectory of the mobile device moving to the target point, and guides the mobile device to move to the target point based on the target movement trajectory, including: Perform local map optimization through the multi-threaded service in the service module deployed on the mobile platform to complete the path local map correction, and build a loop detection database based on the corrected path local map; When loop closure detection is performed on the vertex by using a bag-of-words model installed on a service module deployed on a mobile platform, a target path corresponding to the vertex is obtained; Extracting a real-time path local map corresponding to the target path from the loop detection database by a sliding window method; The target path is optimized based on the comparison of the real-time path local map to obtain a target movement trajectory of the mobile device moving to the target point, and the mobile device is guided to move to the target point based on the target movement trajectory.

5. A multi-agent collaborative guided positioning device, characterized in that: The multi-agent comprises a portable terminal and a mobile platform, and the device comprises: A comparison module, used for aligning the pose coordinate systems of the portable terminal and the mobile platform; A first calculation module is used to calculate in real time in the pose coordinate system a first six-degree-of-freedom pose of the portable terminal when it moves to a target point by fusing a visual sensor and an odometer of an inertial measurement unit, and based on the first six-degree-of-freedom pose, generate a local map of the path of the mobile terminal when it moves, and send it to the mobile platform, wherein the local map of the path includes visual feature points, descriptors, and landmarks corresponding to the movement of the portable terminal; A second calculation module is used for deploying the mobile platform on the mobile device. The mobile platform calculates the optimal planned path of the mobile device in the pose coordinate system based on the path local map through a path planning algorithm, and calculates in real time the second six-degree-of-freedom pose of the mobile device moving to the target point based on the optimal planned path through the fusion of the visual sensor and the odometer of the inertial measurement unit, and generates the vertices of the optimal planned path based on the second six-degree-of-freedom pose, wherein the vertices include visual feature points, descriptors, and landmark points corresponding to the movement of the mobile device based on the optimal planned path; The guidance module is used to compare and optimize the local map and vertices of the path through the service module deployed on the mobile platform to obtain the target movement trajectory of the mobile device to the target point, and guide the mobile device to move to the target point based on the target movement trajectory.

6. The device according to claim 5, characterized in that The comparison module is specifically used for: The position coordinate system of the portable terminal and the mobile platform is aligned through the visual tag corresponding to the visual sensor or the measurement data of the inertial measurement unit.

7. The device according to claim 6, characterized in that The comparison module is also specifically used for: The pose coordinate systems of the portable terminal and the mobile platform are aligned through ultra-wideband positioning or lidar calibration.

8. The device according to claim 5, characterized in that The guiding module is specifically used for: Perform local map optimization through the multi-threaded service in the service module deployed on the mobile platform to complete the path local map correction, and build a loop detection database based on the corrected path local map; When loop closure detection is performed on the vertex by using a bag-of-words model installed on a service module deployed on a mobile platform, a target path corresponding to the vertex is obtained; Extracting a real-time path local map corresponding to the target path from the loop detection database by a sliding window method; The target path is optimized based on the comparison of the real-time path local map to obtain a target movement trajectory of the mobile device moving to the target point, and the mobile device is guided to move to the target point based on the target movement trajectory.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 4.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-4.

Images