Relative state estimation method in distributed unmanned ship cooperative SLAM system

Abstract

The embodiment of the invention provides a relative state estimation method and device in a distributed unmanned ship cooperative SLAM system and a computer readable storage medium. The method comprises the following steps: acquiring first position information and second position information of a current unmanned ship; calculating a first potential area position and a second potential area position based on the first position information and the second position information 1; calculating an axis alignment bounding box of the first potential area position and the second potential area position; screening the point cloud information at the same time based on the axis alignment bounding box to obtain optimized point cloud data; based on the optimized point cloud data, calculating constant-speed motion track prediction information of the current unmanned ship; and estimating the state of the target neighbor relative to the current unmanned ship based on neighbor position information acquired through the fusion network layer, position data acquired through a tracking technology and the constant-speed motion trajectory prediction information. In this way, high-precision relative state estimation is achieved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of data processing, and in particular to a relative state estimation method, device, and computer-readable storage medium in a distributed unmanned boat collaborative SLAM system. Background Art

[0002] In recent years, unmanned boat swarms have been considered to have important application potential in the fields of water target search and post-disaster search and rescue due to their high mobility and mission flexibility, and have become a hot topic of research at home and abroad. Autonomous unmanned boats use multiple sensors such as onboard radars and cameras to perceive the environment in real time and make autonomous decisions to complete mission execution. The accuracy of their positioning and mapping directly determines whether they can successfully navigate and achieve mission objectives, which is an important research direction for autonomous unmanned systems. At present, most field collaborative SLAMs are based on sensors such as GPS and RTK-GPS that rely on satellite signals or external base stations, making it difficult to truly achieve distributed collaborative operations in unknown areas in the wild.

[0003] In the distributed collaborative SLAM system, relative state estimation is the key link to achieve collaborative perception and positioning of unmanned boat clusters. Compared with the self-positioning of a single boat, relative state estimation requires the establishment of accurate associations between relative positions and postures between unmanned boats through noisy observation data. However, due to environmental uncertainty, sensor noise, dynamic interference, and the lack of a global benchmark, the estimation accuracy of the system is difficult to guarantee.

[0004] Therefore, in a distributed architecture, how to overcome sensor errors and dynamic environmental changes and achieve high-precision relative state estimation is a problem that needs to be solved urgently. Summary of the invention

[0005] According to the embodiments of the present application, a relative state estimation scheme in a distributed unmanned boat collaborative SLAM system is provided, which overcomes sensor errors and dynamic environmental changes, solves the most challenging and critical problems in the distributed collaborative SLAM system, and achieves high-precision relative state estimation.

[0006] In a first aspect of the present application, a relative state estimation method in a distributed unmanned boat cooperative SLAM system is provided. The method comprises: Acquire the first position information and the second position information of the current unmanned boat; Calculating a first potential area position and a second potential area position based on the first position information and the second position information; calculating an axis-aligned bounding box of the first potential area position and the second potential area position; filtering the point cloud information at the same time based on the axis-aligned bounding box to obtain optimized point cloud data; Based on the optimized point cloud data, calculating the uniform motion trajectory prediction information of the current unmanned boat; Based on the neighbor position information obtained through the fusion network layer, the position data obtained through the tracking technology and the uniform motion trajectory prediction information, the state of the target neighbor relative to the current unmanned boat is estimated.

[0007] Further, the calculating the axis-aligned bounding box of the first potential area position and the second potential area position includes: The axis-aligned bounding boxes of the first potential area position and the second potential area position may be calculated as follows: ; ; ; ; ; ; in, , , and is the intersection information; and Used to calculate the first potential area position; and Used to calculate the second potential area position; The thresholdX, thresholdY, and thresholdZ are thresholds set in advance in the three-axis directions respectively.

[0008] Further, the filtering of the point cloud information at the same time based on the axis-aligned bounding box to obtain optimized point cloud data includes: Based on a preset emissivity threshold, the point cloud information of the axis-aligned bounding box pair is filtered through high-pass filtering to obtain optimized point cloud data.

[0009] Furthermore, the step of calculating the uniform motion trajectory prediction information of the current unmanned boat based on the optimized point cloud data includes: Based on the optimized point cloud data, an octree structure is constructed; Based on the octree structure, searching for target point cloud data; The target point cloud data is clustered and analyzed by the K-Means clustering algorithm to calculate the uniform motion trajectory prediction information of the current unmanned boat.

[0010] Furthermore, the target point cloud data is clustered and analyzed by the K-Means clustering algorithm to calculate the uniform motion trajectory prediction information of the current unmanned boat, including: ; ; in, Predict the position of the current unmanned boat's uniform motion trajectory; is the cluster center extracted by K-Means clustering algorithm; The cluster center position of the previous frame is determined based on the extracted cluster center and the acquired historical information; is the time used for track inference.

[0011] Furthermore, the estimating the state of the target neighbor relative to the current unmanned boat based on the neighbor position information obtained by the fusion network layer, the position data obtained by the tracking technology and the uniform motion trajectory prediction information includes: Based on the acquired static time offset and dynamic time frequency drift, the data of the current unmanned boat is time-aligned with its neighbors; After the time alignment is completed, aligning with the local coordinate system of the current unmanned boat based on the neighbor position information and the position data; After the local coordinate system is aligned, the uniform motion trajectory prediction information is used as different constraint input factor graphs for optimization to obtain the unmanned boat cluster collaborative SLAM.

[0012] Furthermore, the dynamic time-frequency drift can be calculated in the following way: ; ; Among them, the is the carrier integral; Said is the frequency shift coefficient; Said is the unit conversion factor; Said is the flight time of the signal; Said The time when the request was sent for the current device; Said The time when the request is received by the other device; Said The time for the other device to send a response; Said The time when the current device receives the response.

[0013] In a second aspect of the present application, a relative state estimation device in a distributed unmanned boat cooperative SLAM system is provided. The device comprises: An acquisition module, used to acquire the first position information and the second position information of the current unmanned boat; A first calculation module, configured to calculate a first potential area position and a second potential area position based on the first position information and the second position information; and calculate an axis-aligned bounding box of the first potential area position and the second potential area position; A screening module, configured to screen the point cloud information at the same time based on the axis-aligned bounding box to obtain optimized point cloud data; A second calculation module is used to calculate the uniform motion trajectory prediction information of the current unmanned boat based on the optimized point cloud data; The estimation module is used to estimate the state of the target neighbor relative to the current unmanned boat based on the neighbor position information obtained through the fusion network layer, the position data obtained through the tracking technology and the uniform motion trajectory prediction information.

[0014] In a third aspect of the present application, an electronic device is provided, which includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the program, the method described above is implemented.

[0015] In a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method according to the first aspect of the present application is implemented.

[0016] The relative state estimation method in the distributed unmanned boat collaborative SLAM system provided in the embodiment of the present application obtains the first position information and the second position information of the current unmanned boat; calculates the first potential area position and the second potential area position based on the first position information and the second position information; calculates the axis-aligned bounding box of the first potential area position and the second potential area position; filters the point cloud information of the same time based on the axis-aligned bounding box to obtain optimized point cloud data; calculates the uniform motion trajectory prediction information of the current unmanned boat based on the optimized point cloud data; estimates the state of the target neighbor relative to the current unmanned boat based on the neighbor position information obtained through the fusion network layer, the position data obtained through the tracking technology and the uniform motion trajectory prediction information, thereby achieving high-precision relative state estimation.

[0017] It should be understood that the contents described in the Summary of the Invention are not intended to limit the key or important features of the embodiments of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein: Figure 1 A system architecture diagram of the method provided in the embodiments of the present application; Figure 2 A schematic diagram of an experimental platform according to an embodiment of the present application; Figure 3 It is a flowchart of a relative state estimation method in a distributed unmanned boat collaborative SLAM system according to an embodiment of the present application; Figure 4 A schematic diagram of a dual UWB ranging positioning search solution for an unmanned boat according to an embodiment of the present application; Figure 5 is a schematic diagram of a UWB SS-TWR ranging algorithm according to an embodiment of the present application; Figure 6 is a block diagram of a relative state estimation device in a distributed unmanned boat cooperative SLAM system according to an embodiment of the present application; Figure 7 It is a schematic diagram of the structure of a terminal device or a server suitable for implementing the embodiments of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0020] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0021] Figure 1 The system architecture diagram involved in the method provided in the embodiment of the present application is shown. It includes heartbeat detection, neighbor detection, relative state estimation and back-end collaborative optimization modules. The system includes a distributed unmanned boat cluster collaborative SLAM system of laser radar (LiDAR), inertial measurement unit (IMU) and anchor-free ultra-wideband (Anchor-free UWB).

[0022] Figure 2FIG. 1 is a schematic diagram of an experimental platform according to an embodiment of the present application. Figure 2 As shown in the figure, each unmanned boat is equipped with the same hardware: a LiDAR and its own IMU module are installed in the center of the hull for environmental perception and self-motion state estimation; a UWB module is configured on the left and right sides of the rear of the hull for relative distance measurement between neighbors; the hull is covered with white reflective strips to enhance the radar reflectivity to ensure the neighbor detection effect. Collaborative SLAM adopts a distributed architecture, and each unmanned boat independently estimates its own state and infers the relative state of its neighbors based on the perception information. Subsequently, through the factor graph optimization method, the information of neighboring unmanned boats is combined to minimize the residual, thereby obtaining the global optimal estimated state of the cluster.

[0023] Figure 3 A flow chart of a relative state estimation method in a distributed unmanned boat cooperative SLAM system according to an embodiment of the present disclosure is shown. The method comprises: S310, obtaining first position information and second position information of the current unmanned boat.

[0024] In some embodiments, a 2.4GHz frequency band Ad Hoc distributed network can be constructed based on the IEEE 802.11 protocol at the network layer to achieve efficient communication between unmanned boats. At the same time, each unmanned boat builds a heartbeat detection module to regularly broadcast its own IP and positioning status in the local coordinate system at a frequency of 1Hz. , and listen to the IP and tracks broadcast by other neighbors in the network at the same frequency The set of communicable neighbors obtained by the network layer at low frequency is defined as That is, an Ad-Hoc network is established to realize distributed networking among the unmanned boat groups, and a heartbeat detection is constructed to realize regular broadcasting of its own IP address and local location information at the network layer.

[0025] Furthermore, a neighbor detection module is constructed. The unmanned boat uses the Robot Operating System (ROS) to align and synchronize the timestamps of the left and right UWB ranging information and radar data, and makes neighbor judgments based on the data validity. If there is no one in the boat The UWB modules on either side failed to effectively detect other unmanned boats , then It is classified as a non-neighbor and the relevant data is discarded directly; on the contrary, if the unmanned boat The UWB modules on both sides successfully detected the unmanned boat , and the left distance value , The distance value on the right , If both are valid, then further calculate the potential intersection area, refer to Figure 4 That is, each unmanned boat is equipped with two ultra-wideband (UWB) modules to measure the location area of ​​the neighboring unmanned boat relative to the current unmanned boat and the corresponding time delay information.

[0026] In some embodiments, in the unmanned boat Radar coordinate system The positions of the UWB modules on the left and right sides are and , that is, the first position information and the second position information.

[0027] S320: Calculate a first potential area position and a second potential area position based on the first position information and the second position information; and calculate axis-aligned bounding boxes of the first potential area position and the second potential area position.

[0028] In some embodiments, reference Figure 4 , through the distance value , and , , forming two groups of radius and , corresponding to the constraints of the two circles. Then, the equations of the two circles are used to solve their intersection points, and two sets of potential intersection coordinates are obtained, as shown in formula (1): ; in, is the midpoint of the line connecting the intersection points of the two circles, is the length of the line connecting the centers of the two circles, is an intermediate variable, as shown in formula (2): ; In practical applications, due to the radar coordinate system on the unmanned boat platform of The axis coincides with the central axis of the unmanned boat. The axis coincides with the middle of the section of the unmanned boat, so it can be considered that the two UWB modules are in the radar coordinate system. The coordinates are the same, The coordinates are opposite. That is: ; Furthermore, based on the geometric symmetry of the above formula, formula (2) is simplified to reduce its computational complexity, as shown in formula (3): ; Further, we substitute equation (3) into equation (1) and select , and , The radius and , we can get two groups of two intersection points as shown in formula (4): ; in, and For selection , Parameters to be calculated when and For selection , Parameters to be calculated.

[0029] In some embodiments, reference Figure 4 The right side of and A group of potential locations of unmanned boats can be formed; similarly, the intersection points and This constitutes another set of potential location areas.

[0030] Furthermore, by calculating the axis aligned bounding boxes (AABB) of the above two groups of regions, the possible position range of the unmanned boat can be accurately limited, providing clearer spatial constraints for subsequent unmanned boat detection and tracking, as shown in formula (5): ; in, , , and is the intersection information; and Used to calculate the first potential area position; and Used to calculate the second potential area position; The thresholdX, thresholdY, and thresholdZ are thresholds set in advance in the three-axis directions respectively.

[0031] S330, filtering the point cloud information at the same time based on the axis-aligned bounding box to obtain optimized point cloud data.

[0032] In some embodiments, the AABB area (axis-aligned bounding box) estimated by UWB is used to filter the point cloud information at the same time. The white reflective strips covered by the unmanned boat platform can significantly increase its reflectivity in the radar field of view of other unmanned boats. Therefore, the predefined reflectivity threshold thresholdIntensity can be used to remove the point cloud data with low reflectivity through high-pass filtering, thereby retaining the high reflectivity points that may belong to the unmanned boat and obtaining optimized point cloud data.

[0033] S340, calculating the uniform motion trajectory prediction information of the current unmanned boat based on the optimized point cloud data.

[0034] In some embodiments, in order to efficiently search the unmanned boat point cloud, an octree structure may be constructed on the filtered point cloud, and the number of point clouds within two potential AABB areas may be counted in turn.

[0035] Specifically, if the number of point clouds in a certain AABB area exceeds the threshold (reflectivity threshold), the area is judged as the AABB area of ​​the actual unmanned boat, and the other area is considered to be a false area and discarded.

[0036] Furthermore, the K-Means clustering algorithm can be used to process the searched point cloud data and extract the cluster center. , as the input for subsequent tracking. For the extracted cluster center, combined with the cluster center position of the previous frame in the historical information , calculate the speed of the unmanned boat by difference, and infer the uniform motion trajectory prediction information of the unmanned boat , as shown in formula (6): ; in, Predict the position of the current unmanned boat's uniform motion trajectory; is the cluster center extracted by K-Means clustering algorithm; The cluster center position of the previous frame is determined based on the extracted cluster center and the acquired historical information; is the time used for track inference; if both UWB and radar publish data at a frequency of 10 Hz during actual operation, then =0.1s.

[0037] S350, based on the neighbor position information obtained through the fusion network layer, the position data obtained through the tracking technology and the uniform motion trajectory prediction information, the state of the target neighbor relative to the current unmanned boat is estimated.

[0038] In some embodiments, a relative state estimation module is constructed. When the unmanned boat cluster platform starts operating, the relative state estimation result of the first frame is recorded as the reference value of the initial spatial relative relationship, that is, This baseline value is used as a reference in the subsequent relative position and attitude estimation process.

[0039] In some embodiments, Figure 5 As shown, when obtaining UWB ranging information, the following algorithm can be used to obtain the static time offset, as shown in formula (7): ; Among them, the The time when the request was sent for the current device; Said The time when the request is received by the other device; Said The time for the other device to send a response; Said The time when the current device receives the response.

[0040] Furthermore, in the actual operation process, it is necessary to fully consider the clock frequency response problem caused by the migration of UWB devices over time. When this device receives the response signal sent by the other party, if it is confirmed that the response signal and the request signal belong to the same frame data, the carrier integrator value of the chip is read, multiplied by the corresponding frequency offset coefficient for correction, and multiplied by the corresponding coefficient to convert it from Hertz (Hz) to parts per million (PPM), as shown in formula (8): ; Among them, the is the carrier integral; Said is the frequency shift coefficient; Said is the unit conversion factor; Said is the flight time of the signal.

[0041] In some embodiments, after obtaining the static time offset Offset and the dynamic time frequency drift Drift, the data of the current unmanned boat can be aligned with the time of other neighbors, as shown in formula (9): ; Further, based on The trajectories of other unmanned boats obtained by the network layer Align with the local coordinate system of the current unmanned boat, and then track the predicted trajectory obtained by detection The factor graph is used as the input for different constraints to be optimized, and then the unmanned boat cluster collaborative SLAM is obtained.

[0042] According to the embodiments of the present disclosure, the following technical effects are achieved: It overcomes sensor errors and dynamic environmental changes, solves the most challenging and critical problems in distributed collaborative SLAM systems, and achieves high-precision relative state estimation.

[0043] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0044] The above is an introduction to the method embodiment. The following is a further explanation of the scheme described in this application through an apparatus embodiment.

[0045] Figure 6 A block diagram 600 of a relative state estimation device in a distributed unmanned boat cooperative SLAM system according to an embodiment of the present application is shown. Figure 6 Shown include: An acquisition module 610 is used to acquire first position information and second position information of the current unmanned boat; A first calculation module 620 is used to calculate a first potential area position and a second potential area position based on the first position information and the second position information; and calculate an axis-aligned bounding box of the first potential area position and the second potential area position; A screening module 630, configured to screen the point cloud information of the same time based on the axis-aligned bounding box to obtain optimized point cloud data; A second calculation module 640 is used to calculate the uniform motion trajectory prediction information of the current unmanned boat based on the optimized point cloud data; The estimation module 650 is used to estimate the state of the target neighbor relative to the current unmanned boat based on the neighbor position information obtained through the fusion network layer, the position data obtained through the tracking technology and the uniform motion trajectory prediction information.

[0046] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0047] Figure 7 A schematic diagram of the structure of a terminal device or server suitable for implementing an embodiment of the present application is shown.

[0048] like Figure 7 As shown, the terminal device or server includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 702 or the program loaded from the storage part 708 into the random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the terminal device or server are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0049] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.

[0050] In particular, according to an embodiment of the present application, the above method flow steps can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a machine-readable medium, and the computer program includes a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the central processing unit (CPU) 701, the above-mentioned functions defined in the system of the present application are executed.

[0051] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0052] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of the code, and the aforementioned module, program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0053] The units or modules involved in the embodiments described in the present application may be implemented by software or hardware. The units or modules described may also be arranged in a processor. The names of these units or modules do not, in some cases, constitute limitations on the units or modules themselves.

[0054] As another aspect, the present application further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable storage medium stores one or more programs, and when the above programs are used by one or more processors to execute the method described in the present application.

[0055] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. A relative state estimation method in a distributed unmanned boat cooperative SLAM system, characterized in that: include: Acquire the first position information and the second position information of the current unmanned boat; Calculating a first potential area position and a second potential area position based on the first position information and the second position information; Calculate an axis-aligned bounding box of the first potential area position and the second potential area position; filtering the point cloud information at the same time based on the axis-aligned bounding box to obtain optimized point cloud data; Based on the optimized point cloud data, calculating the uniform motion trajectory prediction information of the current unmanned boat; Based on the neighbor position information obtained through the fusion network layer, the position data obtained through the tracking technology and the uniform motion trajectory prediction information, the state of the target neighbor relative to the current unmanned boat is estimated.

2. The method according to claim 1, characterized in that The calculating the axis-aligned bounding box of the first potential area position and the second potential area position comprises: The axis-aligned bounding boxes of the first potential area position and the second potential area position may be calculated as follows: ； ； ； ； ； ； in, , , and is the intersection information; and Used to calculate the first potential area position; and Used to calculate the second potential area position; The thresholdX, thresholdY, and thresholdZ are thresholds set in advance in the three-axis directions respectively.

3. The method according to claim 2, characterized in that The step of filtering the point cloud information at the same time based on the axis-aligned bounding box to obtain optimized point cloud data includes: Based on a preset emissivity threshold, the point cloud information of the axis-aligned bounding box pair is filtered through high-pass filtering to obtain optimized point cloud data.

4. The method according to claim 3, characterized in that The step of calculating the uniform motion trajectory prediction information of the current unmanned boat based on the optimized point cloud data includes: Based on the optimized point cloud data, an octree structure is constructed; Based on the octree structure, searching for target point cloud data; The target point cloud data is clustered and analyzed by the K-Means clustering algorithm to calculate the uniform motion trajectory prediction information of the current unmanned boat.

5. The method according to claim 4, characterized in that The method of performing cluster analysis on the target point cloud data by using the K-Means clustering algorithm to calculate the uniform motion trajectory prediction information of the current unmanned boat includes: ； ； in, Predict the position of the current unmanned boat's uniform motion trajectory; is the cluster center extracted by K-Means clustering algorithm; The cluster center position of the previous frame is determined based on the extracted cluster center and the acquired historical information; is the time used for track inference.

6. The method according to claim 5, characterized in that The estimating the state of the target neighbor relative to the current unmanned boat based on the neighbor position information obtained by the fusion network layer, the position data obtained by the tracking technology and the uniform motion trajectory prediction information includes: Based on the acquired static time offset and dynamic time frequency drift, the data of the current unmanned boat is time-aligned with its neighbors; After the time alignment is completed, aligning with the local coordinate system of the current unmanned boat based on the neighbor position information and the position data; After the local coordinate system is aligned, the uniform motion trajectory prediction information is used as different constraint input factor graphs for optimization to obtain the unmanned boat cluster collaborative SLAM.

7. The method according to claim 6, characterized in that The dynamic time-frequency drift can be calculated as follows: ； ； Among them, the is the carrier integral; Said is the frequency shift coefficient; Said is the unit conversion factor; Said is the flight time of the signal; Said The time when the request was sent for the current device; Said The time when the request is received by the other party's device; Said The time for the other device to send a response; Said The time when the current device receives the response.

8. A relative state estimation device in a distributed unmanned boat cooperative SLAM system, characterized in that: include: An acquisition module, used to acquire the first position information and the second position information of the current unmanned boat; A first calculation module, used for calculating a first potential area position and a second potential area position based on the first position information and the second position information; Calculate an axis-aligned bounding box of the first potential area position and the second potential area position; A screening module, configured to screen the point cloud information at the same time based on the axis-aligned bounding box to obtain optimized point cloud data; A second calculation module is used to calculate the uniform motion trajectory prediction information of the current unmanned boat based on the optimized point cloud data; The estimation module is used to estimate the state of the target neighbor relative to the current unmanned boat based on the neighbor position information obtained through the fusion network layer, the position data obtained through the tracking technology and the uniform motion trajectory prediction information.

9. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images