Beacon-based positioning system and positioning method under denial condition

Abstract

The invention discloses a positioning system and a positioning method based on beacons under a denial condition. The system comprises a beacon device and a terminal to be positioned. The beacon device comprises an inertial navigation module, an information processing module and an optical communication module; wherein the inertial navigation module is used for recording position movement data of the beacon device in the throwing process; the information processing module is used for determining the position information of the beacon device according to the position movement data and carrying out optical coding; the optical communication module is used for sending the position information of the beacon device subjected to optical coding to a terminal to be positioned; and the to-be-positioned terminal performs positioning according to the position information of the beacon device. According to the invention, accurate positioning of the user equipment under the denial condition can be realized; and compared with the prior art, the method has the advantages of rapid deployment, accurate calculation, efficient transmission, strong adaptability and the like.

Description

Technical Field

[0001] The present invention relates to the field of positioning technology, and more particularly to a beacon-based positioning system and positioning method under denial conditions. Background Art

[0002] In modern society, positioning technology has become an indispensable part of people's daily life and various industry applications. However, under denied conditions, such as indoor environments, underground spaces or areas with severe electromagnetic interference, traditional global positioning systems (GPS) often cannot provide accurate location information.

[0003] Existing indoor positioning technologies, such as visible light positioning (VLP), have solved the indoor positioning problem to a certain extent. However, due to factors such as ambient light interference and receiver performance limitations, their positioning accuracy is often not high and the deployment cost is expensive, so they cannot be widely promoted and applied. Summary of the invention

[0004] In view of this, in order to solve the positioning problem under denied conditions, the present invention provides a beacon-based positioning system and positioning method under denied conditions.

[0005] In order to achieve the above object, the present invention adopts the following technical solution:

[0006] A beacon-based positioning system under denial conditions, comprising a beacon device and a terminal to be positioned; the beacon device comprises an inertial navigation module, an information processing module and an optical communication module; wherein,

[0007] An inertial navigation module is used to record the position movement data of the beacon device during the casting process;

[0008] An information processing module, used to determine the position information of the beacon device according to the position movement data and perform optical encoding;

[0009] The optical communication module is used to send the optically encoded location information of the beacon device to the terminal to be located; the terminal to be located performs positioning according to the location information of the beacon device.

[0010] Preferably, the position movement data includes acceleration and angular velocity of the movement.

[0011] As a preferred embodiment, the beacon device is thrown by an unmanned platform, and the beacon device has a throwing shell that matches the throwing device on the unmanned platform. The throwing process is:

[0012] S1, scan the casting environment and build an environment map;

[0013] S2, identify the beacon placement mark, and calculate the relative position of the mark based on the environment map and the unmanned platform posture;

[0014] S3, converting the relative position into an absolute position on the map;

[0015] S4. Throwing a beacon device according to the absolute position.

[0016] Preferably, determining the location information of the beacon device according to the location movement data includes:

[0017] Based on the location movement data and the environment map, the pre-trained neural network is used to obtain an estimated value of the beacon device location;

[0018] The Kalman filter is used to predict and update the estimated value of the beacon device position to obtain the position information of the beacon device.

[0019] And calibrate the beacon placement identification position on the environmental map according to the position information of the beacon device.

[0020] Preferably, sending the optically encoded beacon device location information to the terminal to be located comprises:

[0021] The beacon device location information and the environmental map fragment information are packaged and sent.

[0022] Preferably, the terminal to be located performs positioning according to the location information of the beacon device, including:

[0023] Perform self-positioning based on the relative position of the inertial navigation data of the terminal to be positioned and the position information of the beacon device;

[0024] and updating the position of the terminal in the environment map according to its own positioning;

[0025] When the positioning terminal moves in the space environment, it continuously receives data packets from the beacon device and repeats the above positioning process in combination with its own inertial navigation data to position itself.

[0026] On the other hand, the present application provides a beacon-based positioning method under denied conditions, which is implemented based on a beacon-based positioning system under denied conditions as described above, and the positioning step includes:

[0027] Dropping beacon devices at preset positions;

[0028] Record the position movement data of the beacon device during the casting process;

[0029] determining location information of the beacon device based on the location movement data;

[0030] The location information of the beacon device is sent to the terminal to be located, so that the terminal to be located performs positioning according to the location information of the beacon device.

[0031] The present invention provides a beacon-based positioning system and positioning method under denied conditions. Compared with the prior art, the present application adopts a drone for on-site scanning and beacon dropping, thereby improving positioning accuracy and efficiency; by combining deep learning algorithms and inertial navigation measurement technology, the calculation accuracy of beacon dropping position information is improved; further based on the beacon position information, the user device is assisted in self-positioning, thereby improving the stability and reliability of positioning.

[0032] The present invention can realize accurate positioning of user equipment under denied conditions, and provides an accurate position information calibration function for detecting unknown closed environments under denied conditions of communication and satellite navigation.

[0033] The present invention is a little bit in that:

[0034] 1. Rapid deployment: Combined with SLAM mapping technology, there is no need to preset the environment map in advance;

[0035] 2. Accurate calculation: Integrate deep learning algorithms to correct inertial navigation data and reduce drift errors;

[0036] 3. Efficient transmission: Provide reliable data communication through optical links to avoid wireless signal interference problems;

[0037] 4. Strong adaptability: suitable for unknown confined spaces or environments where communication and navigation signals are denied. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0039] Figure 1 It is a schematic diagram of the structure of the positioning system based on beacons under the denial condition of the present invention;

[0040] Figure 2 Schematic diagram of SLAM mapping and beacon rapid calibration for unmanned platforms;

[0041] Figure 3 This is a schematic diagram of the position correction of the beacon device after it is thrown;

[0042] Figure 4 Schematic diagram of light transmission after the beacon device is thrown. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] The embodiment of the present invention discloses a beacon-based positioning system under denied conditions, which mainly integrates deep learning algorithms to calculate beacon location information, and sends it to user devices through optical communication, which is used to calibrate the location information of subsequent user devices in unknown spaces under denied conditions. Compared with the original VLP, this application can effectively improve the positioning accuracy in denied environments and achieve centimeter-level positioning.

[0045] The system includes a beacon device and a terminal to be located; Figure 1 ;

[0046] The beacon device includes an inertial navigation module, an information processing module and an optical communication module; the combination of the above three modules enables the positioning system provided by the present application to maintain high positioning robustness in a variety of harsh environments, thereby achieving continuous and stable navigation services.

[0047] The inertial navigation module is used to record the position movement data of the beacon device during the casting process and upload it to the information processing module to provide support for the precise positioning of subsequent equipment. The position movement data includes the acceleration and angular velocity of the movement. Inertial navigation does not rely on external signals and has strong autonomy. It can provide reliable navigation information in GPS-denied areas or complex electromagnetic environments.

[0048] An information processing module is used to determine the location information of the beacon device according to the position movement data, provide location information for the subsequent terminal to be located in an unknown space under a denied condition, and further perform optical encoding;

[0049] The optical communication module is used to provide an efficient and low-interference data transmission channel to send the optically encoded beacon device location information to the terminal to be located; the terminal to be located receives and confirms its own position based on the location information of the beacon device, thereby realizing its own positioning.

[0050] In one embodiment, an unmanned platform is used to cast a beacon device, wherein the beacon device has a casting shell that matches the casting device on the unmanned platform, so that the vehicle can cast the beacon device conveniently. The casting process is as follows:

[0051] S1. The unmanned platform (drone) conducts on-site scanning of the casting environment and builds an environmental map;

[0052] S2, identify the beacon placement mark, and calculate the relative position of the mark based on the environment map and the unmanned platform posture;

[0053] S3, converting the relative position into an absolute position on the map;

[0054] S4. Throwing a beacon device according to the absolute position.

[0055] This application uses unmanned platform SLAM mapping to quickly identify and calibrate the beacon placement location.

[0056] In an optional implementation, the beacon location identification process refers to Figure 2 The unmanned platform first starts the SLAM algorithm to complete the initial self-positioning. Then, it uses sensors such as lidar or cameras to scan the surrounding environment and build an environmental map in real time based on the sensor data. It detects and identifies beacons through sensors. According to the SLAM map and the platform posture, the relative position of the beacon is calculated. The relative position of the beacon is converted to the absolute position of the map, and the beacon point is marked on the map. The completed environmental map and beacon calibration results are exported.

[0057] In one embodiment, the beacon device is modified through deep learning processing based on the position movement data, as shown in the schematic diagram. Figure 3 ; The process includes:

[0058] Based on the location movement data and the environment map, the pre-trained neural network CNN is used to obtain an estimated value of the beacon device location;

[0059] Using a Kalman filter to predict and update the estimated value of the beacon device position to obtain the position information of the beacon device;

[0060] And calibrate the beacon placement identification position on the environmental map according to the position information of the beacon device.

[0061] In this embodiment, the position of the beacon is accurately calculated by combining the Kalman filter and the deep learning algorithm to improve the positioning accuracy, especially to reduce the drift error and nonlinear error in a dynamic environment.

[0062] Specifically, this embodiment uses a deep learning network (DNN) to extract features from sensor data (IMU data, SLAM mapping data) and outputs a preliminary position information estimate; the deep neural network (DNN) fits complex function mappings through a hierarchical structure, which can be used to regress the relationship between inertial navigation data and beacon position information. By using inertial navigation measurements (acceleration, angular velocity, position offset) as input, the DNN can predict the preliminary position of the beacon and significantly improve the accuracy and robustness of the positioning and tracking system based on inertial navigation sensors.

[0063] The inertial navigation module can provide important data about the device's orientation. Using deep learning to extract useful features, learn the error patterns of the inertial navigation module, and compensate for them can achieve more accurate attitude estimation of the beacon.

[0064] Define the sensor input data as X t (IMU acceleration, angular velocity, SLAM mapping information) to generate a preliminary position estimate It is expressed as:

[0065]

[0066] in, is the position information output by the deep learning network (e.g., 3D coordinates [x t ,y t , z t ]); f DNN It is a deep neural network function whose structure is obtained through training.

[0067] The Kalman filter is used to optimize this estimate, i.e., by combining the initial estimate output by the deep learning network with the state prediction model of the Kalman filter to further reduce the error;

[0068] Assume that the state of the system is the position and velocity of the beacon, that is:

[0069]

[0070] Among them, x t ,y t , z t is the position of the beacon, v x , v y , v z is the speed of the beacon.

[0071] In the prediction stage, the Kalman filter predicts the current state based on the state estimation at the previous moment and the system model. The formula is expressed as:

[0072]

[0073] P t|t-1 =FP t-1 F T +Q

[0074] in:

[0075] is the predicted state (position and velocity);

[0076] F is the state transition matrix, describing the dynamics of the system;

[0077] B is the control matrix, describing the impact of external control inputs;

[0078] u t is an external control signal (such as a control instruction);

[0079] P t|t-1 is the predicted covariance matrix, indicating the magnitude of the estimation error;

[0080] Q is the process noise covariance matrix, describing the uncertainty in the system model.

[0081] Furthermore, the Kalman filter performs a weighted update on the current position information based on the model of the dynamic system and the measurement data, thereby obtaining a more accurate beacon position.

[0082] In the update phase, the Kalman filter performs a weighted update based on the output Pt of the deep learning network and the predicted state:

[0083]

[0084] S t =HP t|t-1 H T +R

[0085]

[0086] P t =(1-K t H)P t|t-1

[0087] in:

[0088] y t is the difference between observation and prediction;

[0089] z t is the output of the deep learning network (i.e., the current position information estimate);

[0090] H is the observation matrix, which represents the relationship between the deep learning output and the system state;

[0091] R is the observation noise covariance matrix;

[0092] K t is the Kalman gain, which controls the weighting ratio between prediction and measurement data;

[0093] is the updated state estimate;

[0094] P t is the updated covariance matrix.

[0095] By iteratively executing the above process, the Kalman filter and deep learning network are combined to correct the estimated value at each update, ultimately obtaining more accurate beacon location information.

[0096] In one embodiment, the optical communication module is a laser communication module, which is used to establish communication between the beacon device and the unmanned platform, achieve efficient data packet transmission by modulating the optical signal, and then send the optically encoded beacon device location information to the terminal to be located; the present application can achieve real-time, low-latency data transmission through the high bandwidth of the optical link.

[0097] In this embodiment, the beacon device location information and the environment map fragment information are packaged and sent. The environment map fragment information can be used to identify the ID of the connected beacon device and display the located user terminal, so as to facilitate the implementation of subsequent tasks such as navigation.

[0098] Furthermore, the terminal to be located receives the location information of the beacon device, demodulates and processes it to achieve positioning, and updates the task execution progress and environmental map, that is, updates the latest accurate location information to the casting task and map data, making it more accurate in location. For the specific process, refer to Figure 4 .

[0099] Perform self-positioning based on the relative position of the inertial navigation data of the terminal to be positioned and the position information of the beacon device;

[0100] And update the position of the terminal in the environment map according to its own positioning.

[0101] When the positioning terminal moves in the space environment, it continuously receives data packets from the beacon device and repeats the above positioning process in combination with its own inertial navigation data to position itself.

[0102] In an exemplary embodiment, the specific positioning process is as follows:

[0103] (1) Unmanned platform SLAM mapping: Unmanned platforms (such as drones or mobile robots) are equipped with SLAM modules, which first map the unknown environment in real time. The SLAM system uses lidar, cameras, or other sensors to construct a three-dimensional map of the environment.

[0104] (2) Rapid beacon calibration: After the unmanned platform completes the environment mapping, the SLAM system is used to calibrate the relative position of the beacon in real time. The position of the beacon is calculated through the sensors of the unmanned platform (such as IMU, lidar or camera), and its three-dimensional coordinates are quickly calibrated in the map.

[0105] (3) After calibration, the beacon device is ready to be dropped: After the environment is mapped and the beacon position is calibrated, the beacon device is ready to be dropped. The unmanned platform determines the exact location of the beacon and, through further mobile trajectory planning, accurately drops the beacon device to the target area.

[0106] (4) Deep learning to calculate position information: The IMU measurement data of the beacon device and the map data obtained by the SLAM system are regularly transmitted to the information processing module. The input sensor data and environmental map data are used by deep learning algorithms (such as neural networks or LSTM, etc.) to calculate the precise position of the beacon in the environment by learning the trained model. The deep learning model extracts features based on the sensor data, fuses motion information (such as acceleration, angular velocity) with map fragment information (such as current environmental position, feature identifiers, etc.), and finally estimates the three-dimensional position information of the beacon.

[0107] The position information of the beacon is further corrected using a deep learning algorithm. For example, the error of the deep learning output can be corrected by Kalman filtering, and the noise and motion model of the inertial measurement unit can be integrated to further improve the accuracy of the position information.

[0108] (5) Optical communication transmission location information: Data packet generation and optical communication transmission

[0109] After calculating the location information, the beacon device encapsulates the location information and other calibration data (such as map fragment information, relative movement information, etc.) into a data packet. The data packet includes:

[0110] Map fragment information: partial information of the environment map, used for further precise positioning.

[0111] Drop location information: initial location data of the beacon drop.

[0112] Relative movement information: the relative position change between the beacon and the environment.

[0113] Position information estimate: The final position information calculated by the deep learning algorithm.

[0114] (6) Establishment of optical communication link: The beacon device and the user equipment establish communication through an optical link. The optical link can use laser or visible light communication technology, which has strong anti-interference ability, especially in an environment where the radio spectrum is denied, and can effectively avoid communication obstruction. The beacon device transmits the data packet to the user equipment through laser or other optical communication methods.

[0115] (7) Positioning data fusion: The user device uses the received beacon location information and fuses its own sensor (such as IMU) data to perform position calibration. Specifically, the user device corrects the position based on the beacon information and corrects the current position of the user device through a fusion algorithm (Kalman filter or particle filter).

[0116] In another embodiment, a beacon-based positioning method under denied conditions is provided. The method is implemented based on the beacon-based positioning system under denied conditions as described above, and the positioning step includes:

[0117] Dropping beacon devices at preset positions;

[0118] Record the position movement data of the beacon device during the casting process;

[0119] determining location information of the beacon device based on the location movement data;

[0120] The location information of the beacon device is sent to the terminal to be located, so that the terminal to be located performs positioning according to the location information of the beacon device.

[0121] Since the implementation process of the positioning method in this embodiment is consistent with the positioning process of the positioning system, it will not be repeated here.

[0122] Compared with the prior art, the advantages of this application include:

[0123] 1. Rapid deployment: Combined with SLAM mapping technology, there is no need to preset the environment map in advance.

[0124] 2. Accurate calculation: Integrate deep learning algorithms to correct inertial navigation data and reduce drift errors.

[0125] 3. Efficient transmission: Provide reliable data communication through optical links to avoid wireless signal interference problems.

[0126] 4. Strong adaptability: suitable for unknown confined spaces or environments where communication and navigation signals are denied.

[0127] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0128] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A beacon-based positioning system under denial conditions, characterized in that: It includes a beacon device and a terminal to be positioned; the beacon device includes an inertial navigation module, an information processing module and an optical communication module; wherein, An inertial navigation module is used to record the position movement data of the beacon device during the casting process; An information processing module, used to determine the position information of the beacon device according to the position movement data and perform optical encoding; The optical communication module is used to send the optically encoded location information of the beacon device to the terminal to be located; the terminal to be located performs positioning according to the location information of the beacon device.

2. The positioning system according to claim 1, characterized in that: Position movement data includes acceleration and angular velocity of movement.

3. The positioning system according to claim 1, characterized in that: Use an unmanned platform to drop the beacon device. The dropping process is as follows: S1, scan the casting environment and build an environment map; S2, identify the beacon placement mark, and calculate the relative position of the mark based on the environment map and the unmanned platform posture; S3, converting the relative position into an absolute position on the map; S4. Throwing a beacon device according to the absolute position.

4. The positioning system according to claim 3, characterized in that: Determine the location information of the beacon device based on the location movement data, including: Based on the location movement data and the environment map, the pre-trained neural network is used to obtain an estimated value of the beacon device location; The Kalman filter is used to predict and update the estimated value of the beacon device position to obtain the position information of the beacon device.

5. The positioning system according to claim 1, characterized in that: The optically encoded beacon device location information is sent to the terminal to be located, including: The beacon device location information and the environmental map fragment information are packaged and sent.

6. The positioning system according to claim 5, characterized in that: The terminal to be located performs positioning according to the location information of the beacon device, including: Perform self-positioning based on the relative position of the inertial navigation data of the terminal to be positioned and the position information of the beacon device; And update the position of the terminal in the environment map according to its own positioning.

7. A beacon-based positioning method under denial conditions, characterized in that: Based on the beacon-based positioning system under denial conditions according to any one of claims 1 to 6, the steps include: Dropping beacon devices at preset positions; Record the position movement data of the beacon device during the casting process; Determine location information of the beacon device based on the location movement data; The location information of the beacon device is sent to the terminal to be located, so that the terminal to be located performs positioning according to the location information of the beacon device.

8. The positioning method according to claim 7, characterized in that: A beacon device is provided for dropping a beacon at a preset position, comprising: S1, scan the casting environment and build an environment map; S2, identify the beacon placement mark, and calculate the relative position of the mark based on the environment map and the unmanned platform posture; S3, converting the relative position into an absolute position on the map; S4. Throwing a beacon device according to the absolute position.

9. The positioning method according to claim 7, characterized in that: Determine the location information of the beacon device based on the location movement data, including: Based on the location movement data and the environment map, the pre-trained neural network is used to obtain an estimated value of the beacon device location; The Kalman filter is used to predict and update the estimated value of the beacon device position to obtain the position information of the beacon device.

Images