Closed scene positioning method and system based on UWB technology

Abstract

The invention discloses a closed scene positioning method and system based on a UWB technology, and belongs to the technical field of wireless communication, and the method comprises the steps: obtaining high-precision map information of a closed scene, UWB base station position information and environment complexity information; dividing the high-precision map information into a plurality of sub-regions based on the UWB base station position information; inputting the UWB base station position information and the environment complexity information into a weight generation model to obtain a first weight coefficient, a second weight coefficient and a third weight coefficient output by the weight generation model; obtaining first signal flight time information, first signal intensity information and first signal arrival angle information sent by the UWB target label; and based on the first signal flight time information, the first signal intensity and the first signal arrival angle, determining first distance information, first distance range information, first distance angle information and a target sub-region where the UWB target tag is located. According to the invention, the target position can be determined more accurately under different environmental conditions.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technology, and in particular to a closed scene positioning method and system based on UWB technology. Background Art

[0002] With the rapid development of the Internet of Things and smart devices, positioning technology has been widely used in many fields, especially in closed scenarios such as warehouses, factories, and mining areas. As a high-precision wireless positioning technology, UWB technology transmits extremely short pulse signals to achieve accurate distance measurement, thereby providing sub-meter positioning accuracy. This technology not only has the characteristics of strong anti-multipath interference and low power consumption, but also can meet the application requirements with high real-time and precision requirements.

[0003] The traditional UWB positioning method currently used in mining scenarios mainly measures the UWB signal flight time (TOF) to obtain the distance between the UWB tag and the UWB base station, thereby realizing the positioning of the UWB tag. However, the UWB signal is easily affected by physical obstacles such as metal obstacles and walls, resulting in signal attenuation or reflection, which affects the positioning accuracy. In mining scenarios, there are usually large terrain fluctuations in mining areas, such as open-pit mines and hillsides. This terrain change will affect the propagation path of the UWB signal. In addition, there are a large number of heavy mining equipment, ore piles and waste piles everywhere in the mining area, which will also affect the positioning monitoring of the UWB signal. Therefore, when using UWB for traditional positioning in mining scenarios, its accuracy is easily affected, which in turn affects the positioning accuracy. Summary of the invention

[0004] The purpose of the present invention is to solve the problems in the prior art and to propose a closed scene positioning method and system based on UWB technology.

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

[0006] A closed scene positioning method based on UWB technology includes the following steps:

[0007] Obtain high-precision map information of closed scenes, UWB base station location information, and environmental complexity information;

[0008] Based on the UWB base station location information, the high-precision map information is divided into a plurality of sub-areas; each of the sub-areas includes at least one UWB base station;

[0009] The UWB base station location information and environmental complexity information are input into a weight generation model to obtain a first weight coefficient, a second weight coefficient and a third weight coefficient output by the weight generation model; the environmental complexity information refers to information that affects the propagation and positioning degree of the UWB signal; the weight generation model is trained based on sample data and its corresponding weight coefficient label data, the first weight coefficient is the weight coefficient of the signal flight time information, the second weight coefficient is the weight coefficient of the signal strength information, and the third weight information is the weight coefficient of the signal arrival angle information;

[0010] Acquire first signal flight time information, first signal strength information, and first signal arrival angle information sent by the UWB target tag;

[0011] Based on the first signal flight time information, the first signal strength and the first signal arrival angle, respectively determine the first distance information, the first distance range information, the first distance angle information and the target sub-area where the UWB target tag is located; the target sub-area is any sub-area among the multiple sub-areas;

[0012] Based on the first weight coefficient, the second weight coefficient and the third weight coefficient of the target sub-area, respectively calculating weighted second distance information, second distance range information and second distance angle information;

[0013] Perform EKF positioning calculation on the second distance length information, the second distance range information and the second distance angle information to obtain the position information of the UWB target tag.

[0014] According to a closed scene positioning method based on UWB technology provided by the present invention, the environmental complexity information includes environmental scene topography information, signal shielding area information, multipath effect area information and electromagnetic interference area information.

[0015] A closed scene positioning method based on UWB technology provided by the present invention includes:

[0016] The steps of training to obtain the weight generation model include:

[0017] Obtain historical UWB base station location information and historical environment complexity information;

[0018] Perform grid processing on the historical UWB base station location information to obtain grid distribution feature information;

[0019] Perform spectrum analysis and extraction on the historical environment complexity information to obtain spectrum feature information;

[0020] Extract spatial features from historical UWB base station location information to obtain spatial texture feature information;

[0021] Inputting the grid distribution feature information into a first neural network model for training to obtain a first output result output by the first neural network model;

[0022] Inputting the spectrum feature information into a second neural network model for training to obtain a second output result output by the second neural network model;

[0023] Inputting the spatial texture feature information into a third neural network model for training to obtain a third output result output by the third neural network model;

[0024] Based on a preset loss function, determining a first loss value of the first output result, a second loss value of the second output result, and a third loss value of the third output result;

[0025] The parameters of the weight generation model to be adjusted are adjusted based on the first loss value, the second loss value, and the third loss value to obtain the weight generation model.

[0026] According to a closed scene positioning method based on UWB technology provided by the present invention, the preset loss function is:

[0027]

[0028] Among them, L j represents the basic loss function under the j-th environment type, γ j represents the weight coefficient related to the jth environment type; C i represents the environmental complexity constraint, μ i represents the weight coefficient of the constraint item; m represents the number of environment types; p represents the number of environment complexity constraints.

[0029] According to a closed scene positioning method based on UWB technology provided by the present invention, the first distance information, the first distance range information, the first distance angle information and the target sub-area where the UWB target tag is located are determined based on the first signal flight time information, the first signal strength and the first signal arrival angle, respectively, including:

[0030] Based on the first signal flight time information TOF1, the first distance information d_TOF1 is calculated by a first preset formula;

[0031] Based on the second signal strength RSSI1, the first distance range information d_RSSI1 is calculated by a second preset formula;

[0032] Based on the first signal arrival angle, determining first distance angle information of the UWB target tag relative to the base station;

[0033] The target sub-area where the UWB target tag is located is determined according to the UWB base station location information of the received first signal flight time, the first signal strength and the first signal arrival angle.

[0034] According to a closed scene positioning method based on UWB technology provided by the present invention, the first preset formula is as follows:

[0035] Where c is the speed of light,

[0036] The second preset formula is as follows:

[0037] RSSI1(d)=P_t-PL(d)-X_σ

[0038] PL(d)=10n log10(d)+C

[0039] Among them, RSSI1(d) is the signal strength received at distance d, P_t represents the UWB base station transmission power, PL(d) represents the path loss, X_σ represents the shadow fading component, n represents the path loss index, and C represents the environment-related constant.

[0040] According to a closed scene positioning method based on UWB technology provided by the present invention, when calculating the first distance range information d_RSSI1, X_σ is a random variable and obeys the normal distribution N(0, σ 2 ), so the range of the first distance range information d_RSSI1 finally obtained is [d_RSSI1 min ,d_RSSI1 max ],in:

[0041] RSSI1(d)=P_t-(10n log10(d min )+C)-X_σ

[0042] RSSI1(d)=P_t-(10n log10(d max )+C)+X_σ

[0043] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the closed scene positioning method based on UWB technology as described above are implemented.

[0044] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the closed scene positioning method based on UWB technology are implemented as described above.

[0045] Compared with the prior art, the present invention has the following advantages:

[0046] The present invention provides a closed scene positioning method and system based on UWB technology. The method divides the high-precision map information of the closed scene into multiple sub-areas. In each sub-area, weights are dynamically and automatically assigned to the flight time information, signal strength information and signal arrival angle information received by the UWB base station according to the UWB base station position information and environmental complexity information, and can be dynamically adjusted to ensure the accuracy of weight allocation. The flight time information, signal strength information and signal arrival angle information after weight allocation are then EKF positioned to obtain the position information of the UWB target tag. The different characteristics of the UWB signal are fully utilized in the UWB target tag positioning process, and the problem that a single TOF measurement is easily affected by interference and errors in a complex environment is overcome. The target position can be determined more accurately under different environmental conditions and the fluctuation of the positioning error is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 A schematic diagram of a closed scene positioning method based on UWB technology provided in an embodiment of the present invention;

[0049] Figure 2 A schematic diagram of the structure of a closed scene positioning system based on UWB technology provided by an embodiment of the present invention;

[0050] Figure 3 This is a schematic diagram of the structure of the electronic device proposed by the present invention. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0052] Combine the following Figure 1 - Figure 3 The present invention describes a closed scene positioning method and system based on UWB technology.

[0053] Figure 1FIG. 1 is a flow chart of a closed scene positioning method based on UWB technology provided by the present invention. Figure 1 As shown, the method includes:

[0054] Step 101, obtain high-precision map information of the closed scene, UWB base station location information and environmental complexity information; environmental complexity information refers to information that affects the propagation and positioning of UWB signals.

[0055] When obtaining high-precision map information, two-dimensional plane information in the closed scene can be obtained through special surveying and mapping equipment or existing architectural design drawings and other data sources, and then three-dimensional structural information in the scene can be obtained using laser scanning technology. At the same time, in the process of obtaining high-precision map information, the UWB base station location information and environmental complexity information in the closed scene are also obtained. Among them, the UWB base station location information includes the precise location coordinates of each base station, the identification number of the base station, the transmission power of the base station, the antenna characteristics and other parameter information, and the environmental complexity information includes environmental scene topography information, signal blocking area information, multipath effect area information and electromagnetic interference area information. At the same time, in the process of using laser scanning technology to obtain a three-dimensional scene, the position and shape of walls, pillars, obstacles, etc. in the environmental complexity information can also be scanned to analyze the possible reflection and blocking conditions of the signal. At the same time, combined with the wireless signal propagation model, the signal propagation characteristics of different areas are pre-evaluated, such as the strength of the multipath effect, the degree of signal attenuation, etc., and the environmental complexity information is quantitatively evaluated by comprehensively processing the above information. After obtaining high-precision map information, UWB base station location information and environmental complexity information, a three-dimensional scene map of the mining area is obtained through comprehensive processing of the above information, and real-time positioning is performed based on the movable obstacles in the mining area, so as to adjust the real-time position of the movable obstacles in real time, and then make real-time adjustments to the environmental complexity information in different areas.

[0056] Step 102: Based on the UWB base station location information, the high-precision map information is divided into multiple sub-areas; each sub-area includes at least one UWB base station.

[0057] The sub-area division process is mainly to facilitate more accurate positioning of UWB target tags in closed scenes. In the sub-area division process, a preliminary division is first performed based on the spatial geometry to obtain multiple grid-shaped sub-areas, which are then divided again according to the location of the UWB base station. Each sub-area contains at least one UWB base station, and the number of UWB base stations between adjacent sub-areas is as similar as possible, so that each sub-area has its own unique environmental characteristics and UWB base station coverage, which facilitates the subsequent optimization of the positioning algorithm for different sub-areas.

[0058] In addition, in addition to meeting the above-mentioned division conditions, on this basis, areas with similar environmental complexity are divided into the same sub-area as much as possible. For example, in one embodiment, an area with a strong multipath effect and severe signal obstruction is divided into a sub-area, so that the weight coefficient adjustment strategy can be targeted within the sub-area; and an area that is relatively open and has better signal propagation conditions is divided into another sub-area.

[0059] Step 103, input the UWB base station location information and environmental complexity information into the weight generation model to obtain the first weight coefficient, the second weight coefficient and the third weight coefficient output by the weight generation model; the weight generation model is trained based on the sample data and its corresponding weight coefficient label data, the first weight coefficient is the weight coefficient of the signal flight time information, the second weight coefficient is the weight coefficient of the signal strength information, and the third weight information is the weight coefficient of the signal arrival angle information.

[0060] Specifically, the steps of training the weight generation model include:

[0061] Obtain historical UWB base station location information and historical environment complexity information;

[0062] The historical UWB base station location information is gridded to obtain gridded distribution feature information; wherein the gridded distribution feature information includes the number of base stations in each site unit, the center of gravity coordinates of the central distribution, and the distance distribution information between the base station and the grid boundary.

[0063] Spectrum analysis is performed on the historical environment complexity information to obtain spectrum feature information; for example, analysis is performed on the changes in signal frequency components caused by signal multipath effects, the manifestation of electromagnetic interference on the spectrum, and other information, such as the energy distribution in different frequency bands, the spectrum peak position, etc.

[0064] The spatial features of the historical UWB base station location information are extracted to obtain spatial texture feature information; for example, the obstacle distribution and terrain undulations in the environment are regarded as a kind of spatial texture, and texture features such as texture roughness and directionality are extracted.

[0065] The grid distribution feature information is input into the first neural network model for training to obtain a first output result of the first neural network model; it represents a feature representation of the base station position relationship and a preliminary weight coefficient estimate.

[0066] The spectrum feature information is input into the second neural network model for training to obtain a second output result output by the second neural network model; this reflects the estimated weight coefficient of the impact of the environment on the signal at the spectrum level.

[0067] The spatial texture feature information is input into the third neural network model for training, and a third output result of the third neural network model is obtained; this reflects the preliminary judgment of the environmental spatial structure on the weight coefficient related to signal propagation.

[0068] Based on a preset loss function, a first loss value of the first output result, a second loss value of the second output result, and a third loss value of the third output result are determined; wherein the first loss value measures the error between the base station location-related weight coefficient predicted by the model and the actual expected weight coefficient, the second loss value reflects the deviation of the spectrum feature model in judging the weight of the environment's impact on the signal, and the third loss value reflects the inaccuracy of the spatial texture feature's prediction of the environmental structure-related weight coefficient.

[0069] The parameters of the weight generation model to be adjusted are adjusted based on the first loss value, the second loss value and the third loss value to obtain the weight generation model. The weighted fusion of the first neural network model, the second neural network model and the third neural network model is realized. In the process of parameter adjustment, the model parameters are updated according to the back propagation of the loss value, so that the model can more accurately allocate the weight coefficients of TOF, RSSI and AOA after comprehensively considering multiple factors such as the base station location, environmental spectrum and spatial texture, and finally obtain the target UWB positioning weight coefficient model, which can accurately output the weight coefficients of signal flight time, signal strength information and signal arrival angle information according to the input UWB base station location information and environmental complexity information data.

[0070] Furthermore, the preset loss function is:

[0071] ;

[0072] Among them, L j represents the basic loss function under the j-th environment type, γ j represents the weight coefficient related to the jth environment type; C i represents the environmental complexity constraint, μ i represents the weight coefficient of the constraint item; m represents the number of environment types; p represents the number of environment complexity constraints.

[0073] Step 104, obtaining first signal flight time information, first signal strength information, and first signal arrival angle information sent by the UWB target tag;

[0074] When locating and detecting UWB target tags, UWB target tags send signals to surrounding UWB base stations at preset time intervals or when triggered by specific events. After receiving the signal, the UWB base station uses a high-precision clock module to measure the signal flight time, and measures the signal strength through the signal receiving circuit, and finally uses the base station's antenna array and signal processing algorithm to calculate the signal arrival angle. The UWB base station then transmits the measured first signal flight time TOF1, first signal strength information RSSI1, and first signal arrival angle information AOA1 to the positioning data processing center of the mining area through a wired or wireless communication network. In the positioning data processing center, the signal information from multiple base stations is integrated and synchronously processed to ensure the consistency of the signal information of the same UWB target tag measured by different base stations in time and space.

[0075] Step 105, based on the first signal flight time information, the first signal strength and the first signal arrival angle, respectively determine the first distance information, the first distance range information, the first distance angle information and the target sub-area where the UWB target tag is located; the target sub-area is any sub-area among the multiple sub-areas;

[0076] The method comprises: obtaining first distance information d_TOF1 by calculating the first distance information d_TOF1 through a first preset formula based on the first signal flight time information TOF1;

[0077] Based on the second signal strength RSSI1, the first distance range information d_RSSI1 is calculated by a second preset formula;

[0078] Based on the first signal arrival angle, determining first distance angle information of the UWB target tag relative to the base station;

[0079] The target sub-area where the UWB target tag is located is determined based on the UWB base station location information of the received first signal flight time, first signal strength, and first signal arrival angle. When determining the target sub-area, if the base station receiving the strongest signal is located in a certain sub-area, and the signal strength and AOA information are consistent with the signal propagation model prediction results in the sub-area, it can be determined that the target tag is located in the sub-area. Then, the weight coefficient is automatically allocated based on the base station location information and environmental complexity information in the target sub-area.

[0080] The first preset formula is as follows:

[0081] Wherein, c represents the speed of light; for example, in one embodiment, if the measured TOF1=10 nanoseconds, then d_TOF1=3*10 8 *10*10 -9 / 2=1.5 meters, which means the one-way distance between the target tag and the base station is about 1.5 meters.

[0082] The second preset formula is as follows:

[0083] RSSI1(d)=P_t-PL(d)-X_σ

[0084] PL(d)=10n log10(d)+C

[0085] Among them, RSSI1(d) is the signal strength received at distance d, P_t represents the UWB base station transmission power, PL(d) represents the path loss, X_σ represents the shadow fading component, n represents the path loss index, and C represents the environment-related constant.

[0086] When calculating the first distance range information d_RSSI1, X_σ is a random variable and obeys the normal distribution N(0, σ 2 ), so the range of the first distance range information d_RSSI1 finally obtained is [d_RSSI1 min ,d_RSSI1 max ],in:

[0087] RSSI1(d)=P_t-(10n log10(d min )+C)-X_σ;

[0088] RSSI1(d)=P_t-(10n log10(d max )+C)+X_σ.

[0089] For example, in one embodiment, when RSSI1=-60 dBm, the calculated range of d_RSSI1 is between 3 and 5 meters, indicating that the target tag may be located at a position 3 to 5 meters away from the base station.

[0090] In addition, the first distance angle information AOA1 is determined according to the signal arrival angle. It includes a horizontal angle (θ_1) and a vertical angle (φ_1), and these angle information represent the direction of the target tag relative to the base station. For example, in one embodiment, the horizontal angle θ_1 = 30 degrees and the vertical angle φ_1 = 15 degrees, indicating that the target tag is located in the northeast direction of the base station and the vertical angle with the base station is 15 degrees.

[0091] Step 106, respectively calculating weighted second distance information, second distance range information, and second distance angle information based on the first weight coefficient, the second weight coefficient, and the third weight coefficient of the target sub-region;

[0092] The weighted second distance information d_TOF2=ω1*d_TOF1; the weighted second distance range information d_RSSI2=ω2*d_RSSI1; the weight coefficient of the weighted second distance angle information AOA2 is ω3, where ω1+ω2+ω3=1, and the second distance angle information AOA2 keeps the angle unchanged.

[0093] Step 107: Perform EKF positioning calculation on the second distance length information, the second distance range information, and the second distance angle information to obtain the position information of the UWB target tag.

[0094] When calculating the location information of the UWB target tag, an extended Kalman filter algorithm is used for calculation, such as in one embodiment:

[0095] First, define the state vector Where (x, y, z) is the location coordinate of the UWB target tag, The three-dimensional velocity coordinates of the UWB target tag in motion;

[0096] Define the UWB target tag to move at an approximately uniform speed in a short period of time, then the state transfer equation is X k+1 =F k X k +W k , where F k is the state transfer matrix, W k is the process noise vector, which obeys the zero-mean Gaussian distribution W k ~N(0,Q k ).

[0097] For the TOF (signal time of flight) characteristic, the measurement equation is:

[0098]

[0099] Where (x l ,y l , z l ) is the location coordinate of the base station involved in the calculation, v TOF is the measurement noise of the TOF feature, which follows a Gaussian distribution

[0100] For the RSSI (signal strength) feature, the measurement equation is similar to TOF:

[0101]

[0102] Where (x l ,y l , z l ) is the location coordinate of the base station involved in the calculation, v RSSIis the measurement noise of the RSSI feature and considering its distance range and uncertainty, its variance is large.

[0103] Corresponding to the AOA (signal arrival angle) characteristic, the measurement equation is:

[0104]

[0105] Among them, v θ and is the measurement noise characteristic of the AOA.

[0106] The weighted d TOF2 ,d RSSI2 The range information and AOA1 information construct the measurement vector z according to the measurement model k , combined with the state transfer model, through the prediction and update steps of the EKF:

[0107] Prediction steps:

[0108]

[0109] Update steps:

[0110]

[0111] in, represents the state estimation vector at time k, represents the predicted state estimation vector at the next moment (k+1); F k represents the state transfer matrix, which describes the transition relationship of the target state from time k to time k+1; Q k represents the process noise covariance matrix; P k Represents the state covariance matrix of the current time k; H represents the covariance matrix of the predicted state at the next moment (k+1); k represents the measurement matrix; R k represents the measurement noise covariance matrix; K k represents the Kalman gain.

[0112] After multiple iterative calculations, the location information of the UWB target tag is finally obtained. That is, the precise position coordinates (x, y, z) and speed information of the UWB target tag in three-dimensional space

[0113] The present invention provides a closed scene positioning method based on UWB technology. The method divides the high-precision map information of the closed scene into multiple sub-areas. In each sub-area, weights are dynamically and automatically assigned to the flight time information, signal strength information and signal arrival angle information received by the UWB base station according to the UWB base station position information and the environmental complexity information. The weights can be adjusted dynamically to ensure the accuracy of the weight assignment. The flight time information, signal strength information and signal arrival angle information after the weight assignment are then EKF positioned to obtain the position information of the UWB target tag. The different characteristics of the UWB signal are fully utilized in the UWB target tag positioning process, and the problem that a single TOF measurement is easily affected by interference and errors in a complex environment is overcome. The target position can be determined more accurately under different environmental conditions and the fluctuation of the positioning error can be reduced.

[0114] Figure 2 FIG. 1 is a schematic diagram of a closed scene positioning system based on UWB technology provided by the present invention. Figure 2 As shown, the system includes: a first acquisition unit 10: used to acquire high-precision map information of a closed scene; an area division unit 20: used to divide the high-precision map information into multiple sub-areas based on the UWB base station location information; each sub-area includes at least one UWB base station; a weight allocation unit 30: used to input the UWB base station location information and the environmental complexity information into the weight generation model to obtain the first weight coefficient, the second weight coefficient and the third weight coefficient output by the weight generation model; the environmental complexity information refers to the information that affects the propagation and positioning degree of the UWB signal; the weight generation model is trained based on the sample data and its corresponding weight coefficient label data, the first weight coefficient is the weight coefficient of the signal flight time information, the second weight coefficient is the weight coefficient of the signal strength information, and the third weight information is the weight coefficient of the signal arrival angle information; the second acquisition unit 40 : used to obtain the first signal flight time information, first signal strength information and first signal arrival angle information sent by the UWB target tag; the first calculation unit 50: used to determine the first distance information, the first distance range information, the first distance angle information and the target sub-area where the UWB target tag is located based on the first signal flight time information, the first signal strength and the first signal arrival angle; the target sub-area is any sub-area among the multiple sub-areas; the weighted allocation unit 60: used to calculate the weighted second distance information, the second distance range information and the second distance angle information based on the first weight coefficient, the second weight coefficient and the third weight coefficient of the target sub-area; the second calculation unit 70: used to perform EKF positioning calculation on the second distance length information, the second distance range information and the second distance angle information to obtain the position information of the UWB target tag.

[0115] Figure 3 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 3 As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute a closed scene positioning method based on UWB technology, the method comprising: obtaining high-precision map information of the closed scene;

[0116] Based on the location information of the UWB base station, the high-precision map information is divided into multiple sub-areas; each sub-area contains at least one UWB base station;

[0117] The UWB base station location information and environmental complexity information are input into the weight generation model to obtain the first weight coefficient, the second weight coefficient and the third weight coefficient output by the weight generation model; the environmental complexity information refers to the information that affects the propagation and positioning degree of the UWB signal; the weight generation model is trained based on the sample data and its corresponding weight coefficient label data, the first weight coefficient is the weight coefficient of the signal flight time information, the second weight coefficient is the weight coefficient of the signal strength information, and the third weight information is the weight coefficient of the signal arrival angle information; the first signal flight time information, the first signal strength information and the first signal arrival angle information sent by the UWB target tag are obtained; based on the first signal flight time information, the first signal strength and the first signal arrival angle, the first distance information, the first distance range information, the first distance angle information and the target sub-area where the UWB target tag is located are determined respectively; the target sub-area is any sub-area among the multiple sub-areas; based on the first weight coefficient, the second weight coefficient and the third weight coefficient of the target sub-area, the weighted second distance information, the second distance range information and the second distance angle information are calculated respectively; the second distance length information, the second distance range information and the second distance angle information are subjected to EKF positioning calculation to obtain the location information of the UWB target tag.

[0118] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0119] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by the computer, the computer can execute a closed scene positioning method based on UWB technology provided by the above methods, the method including: obtaining high-precision map information of the closed scene; based on the UWB base station location information, dividing the high-precision map information into multiple sub-areas; each of the sub-areas contains at least one UWB base station; inputting the UWB base station location information and environmental complexity information into a weight generation model to obtain a first weight coefficient, a second weight coefficient and a third weight coefficient output by the weight generation model; the environmental complexity information refers to information that affects the propagation and positioning degree of the UWB signal; the weight generation model is trained based on sample data and its corresponding weight coefficient label data, and the first weight coefficient is the signal flight time. The second weight coefficient is a weight coefficient for signal strength information, the third weight information is a weight coefficient for signal arrival angle information; obtain the first signal flight time information, the first signal strength information and the first signal arrival angle information sent by the UWB target tag; based on the first signal flight time information, the first signal strength and the first signal arrival angle, respectively determine the first distance information, the first distance range information, the first distance angle information and the target sub-area where the UWB target tag is located; the target sub-area is any sub-area among the multiple sub-areas; based on the first weight coefficient, the second weight coefficient and the third weight coefficient of the target sub-area, respectively calculate the weighted second distance information, the second distance range information and the second distance angle information; perform EKF positioning calculation on the second distance length information, the second distance range information and the second distance angle information to obtain the position information of the UWB target tag.

[0120] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform the above-mentioned closed scene positioning method and system based on UWB technology, the method comprising: obtaining high-precision map information of the closed scene;

[0121] Based on the UWB base station location information, the high-precision map information is divided into a plurality of sub-areas; each of the sub-areas includes at least one UWB base station;

[0122] The UWB base station location information and environmental complexity information are input into a weight generation model to obtain a first weight coefficient, a second weight coefficient and a third weight coefficient output by the weight generation model; the environmental complexity information refers to information that affects the propagation and positioning degree of the UWB signal; the weight generation model is trained based on sample data and its corresponding weight coefficient label data, the first weight coefficient is the weight coefficient of the signal flight time information, the second weight coefficient is the weight coefficient of the signal strength information, and the third weight information is the weight coefficient of the signal arrival angle information; the first signal flight time information, the first signal strength information and the first signal arrival angle information sent by the UWB target tag are obtained angle information; based on the first signal flight time information, the first signal strength and the first signal arrival angle, respectively determine the first distance information, the first distance range information, the first distance angle information and the target sub-area where the UWB target tag is located; the target sub-area is any sub-area among the multiple sub-areas; based on the first weight coefficient, the second weight coefficient and the third weight coefficient of the target sub-area, respectively calculate the weighted second distance information, the second distance range information and the second distance angle information; perform EKF positioning calculation on the second distance length information, the second distance range information and the second distance angle information to obtain the position information of the UWB target tag.

[0123] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0124] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0125] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A closed scene positioning method based on UWB technology, characterized in that: The following steps are involved: Obtain high-precision map information, UWB base station location information and environmental complexity information of the closed scene; the environmental complexity information refers to information that affects the propagation and positioning of UWB signals; Based on the UWB base station location information, the high-precision map information is divided into a plurality of sub-areas; each of the sub-areas includes at least one UWB base station; The UWB base station location information and environmental complexity information are input into a weight generation model to obtain a first weight coefficient, a second weight coefficient and a third weight coefficient output by the weight generation model; the weight generation model is trained based on sample data and its corresponding weight coefficient label data, the first weight coefficient is a weight coefficient for signal flight time information, the second weight coefficient is a weight coefficient for signal strength information, and the third weight information is a weight coefficient for signal arrival angle information; Acquire first signal flight time information, first signal strength information, and first signal arrival angle information sent by the UWB target tag; Based on the first signal flight time information, the first signal strength and the first signal arrival angle, respectively determine the first distance information, the first distance range information, the first distance angle information and the target sub-area where the UWB target tag is located; the target sub-area is any sub-area among the multiple sub-areas; Based on the first weight coefficient, the second weight coefficient and the third weight coefficient of the target sub-area, respectively calculating weighted second distance information, second distance range information and second distance angle information; Perform EKF positioning calculation on the second distance length information, the second distance range information and the second distance angle information to obtain the position information of the UWB target tag.

2. The closed scene positioning method based on UWB technology according to claim 1, characterized in that: The environmental complexity information includes environmental scene topography information, signal shielding area information, multipath effect area information and electromagnetic interference area information.

3. The closed scene positioning method based on UWB technology according to claim 1, characterized in that: The steps of training to obtain the weight generation model include: Obtain historical UWB base station location information and historical environment complexity information; Perform grid processing on the historical UWB base station location information to obtain grid distribution feature information; Perform spectrum analysis and extraction on the historical environment complexity information to obtain spectrum feature information; Extract spatial features from historical UWB base station location information to obtain spatial texture feature information; Inputting the grid distribution feature information into a first neural network model for training to obtain a first output result output by the first neural network model; Inputting the spectrum feature information into a second neural network model for training to obtain a second output result output by the second neural network model; Inputting the spatial texture feature information into a third neural network model for training to obtain a third output result output by the third neural network model; Based on a preset loss function, determining a first loss value of the first output result, a second loss value of the second output result, and a third loss value of the third output result; The parameters of the weight generation model to be adjusted are adjusted based on the first loss value, the second loss value, and the third loss value to obtain the weight generation model.

4. The closed scene positioning method based on UWB technology according to claim 3 is characterized in that: The preset loss function is: Among them, L j represents the basic loss function under the j-th environment type, γ j represents the weight coefficient related to the jth environment type; C i represents the environmental complexity constraint, μ i represents the weight coefficient of the constraint item; m represents the number of environment types; p represents the number of environment complexity constraints.

5. The closed scene positioning method based on UWB technology according to claim 1, characterized in that: The method of determining first distance information, first distance range information, first distance angle information, and a target sub-area where the UWB target tag is located based on the first signal flight time information, the first signal strength, and the first signal arrival angle, respectively, includes: Based on the first signal flight time information TOF1, the first distance information d_TOF1 is calculated by a first preset formula; Based on the second signal strength RSSI1, the first distance range information d_RSSI1 is calculated by a second preset formula; Based on the first signal arrival angle, determining first distance angle information of the UWB target tag relative to the base station; The target sub-area where the UWB target tag is located is determined according to the UWB base station location information of the received first signal flight time, the first signal strength and the first signal arrival angle.

6. The closed scene positioning method based on UWB technology according to claim 5 is characterized in that: The first preset formula is as follows: Where c is the speed of light, The second preset formula is as follows: RSSI1(d)=P_t-PL(d)-X_σ PL(d)=10n log10(d)+C Among them, RSSI1(d) is the signal strength received at distance d, P_t represents the UWB base station transmission power, PL(d) represents the path loss, X_σ represents the shadow fading component, n represents the path loss index, and C represents the environment-related constant.

7. The closed scene positioning method based on UWB technology according to claim 6, characterized in that: When calculating the first distance range information d_RSSI1, X_σ is a random variable and obeys the normal distribution N(0, σ 2 ), so the range of the first distance range information d_RSSI1 finally obtained is [d_RSSI1 min ,d_RSSI1 max ],in: RSSI1(d)=P_t-(10n log10(d min )+C)-X_σ RSSI1(d)=P_t-(10n log10(d max )+C)+X_σ。 8. A closed scene positioning system based on UWB technology, characterized in that: include: The first acquisition unit is used to acquire high-precision map information of closed scenes; An area division unit: used to divide the high-precision map information into a plurality of sub-areas based on the location information of the UWB base station; each of the sub-areas includes at least one UWB base station; A weight allocation unit is used to input the UWB base station location information and environmental complexity information into a weight generation model to obtain a first weight coefficient, a second weight coefficient and a third weight coefficient output by the weight generation model; the environmental complexity information refers to information that affects the propagation and positioning degree of the UWB signal; the weight generation model is trained based on sample data and its corresponding weight coefficient label data, the first weight coefficient is the weight coefficient of the signal flight time information, the second weight coefficient is the weight coefficient of the signal strength information, and the third weight information is the weight coefficient of the signal arrival angle information; A second acquisition unit: used to acquire the flight time information, the first signal strength information and the first signal arrival angle information of the first signal sent by the UWB target tag; A first calculation unit: used to determine first distance information, first distance range information, first distance angle information, and a target sub-area where the UWB target tag is located based on the first signal flight time information, the first signal strength, and the first signal arrival angle; the target sub-area is any sub-area in the multiple sub-areas; A weighted allocation unit: configured to respectively calculate weighted second distance information, second distance range information, and second distance angle information based on the first weight coefficient, the second weight coefficient, and the third weight coefficient of the target sub-region; The second calculation unit is used to perform EKF positioning calculation on the second distance length information, the second distance range information and the second distance angle information to obtain the position information of the UWB target tag.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of a closed scene positioning method based on UWB technology as described in any one of claims 1 to 7 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a closed scene positioning method based on UWB technology as described in any one of claims 1 to 7 are implemented.

Images