CN111007455A

CN111007455A - Positioning system and method, database and neural network model training method

Info

Publication number: CN111007455A
Application number: CN201911253079.8A
Authority: CN
Inventors: 张苏; 黄珊
Original assignee: Individual
Current assignee: Individual
Priority date: 2019-10-16
Filing date: 2019-12-09
Publication date: 2020-04-14
Anticipated expiration: 2039-12-09
Also published as: CN111007455B

Abstract

The invention provides a positioning system and a method, a database and a neural network model training method, wherein the positioning system can train a neural network model through one or more groups of second measurement information which are acquired by an inertial measurement unit IMU and used as historical measurement information and one or more groups of second position information which are acquired by an ultra-wideband UWB unit and used as historical position information, so that first measurement information acquired by the inertial measurement unit IMU and first position information corresponding to a target are further acquired through the neural network model, and the target object is positioned. Therefore, the invention can solve the problem that the positioning effect of UWB positioning in the related technology is easy to be interfered by the influence of environment shielding or multipath effect, so as to achieve the effect of improving the precision of UWB positioning.

Description

Positioning system and method, database and neural network model training method

Technical Field

The invention relates to the field of navigation, in particular to a positioning system and method, a database and a neural network model training method.

Background

An Ultra Wide Band (UWB) technology is a wireless carrier communication technology using a frequency bandwidth of 1GHz or more. UWB technology does not use sinusoidal carriers, but rather uses nanosecond-level non-sinusoidal narrow pulses to transmit data, and thus occupies a large spectrum, and despite the use of wireless communication, the data transmission rate can reach several hundred megabits per second or more. Signals can be transmitted over a very wide bandwidth using UWB technology, which is specified by the Federal Communications Commission (FCC) in the united states as: and the bandwidth of more than 500MHz is occupied in the frequency band of 3.1-10.6 GHz.

The UWB technology has the advantages of insensitivity to channel fading, low power spectral density of transmitted signals, low interception rate, low system complexity, capability of providing positioning accuracy of several centimeters and the like, so that the UWB technology can realize accurate positioning in an indoor scene.

Fig. 1 is a schematic diagram of an indoor UWB positioning system provided according to the related art, and as shown in fig. 1, the indoor UWB positioning system generally includes a positioning base station and a positioning tag, where the base station unit is a pre-arranged unit having fixed coordinates, and in general, at least 4 base station units can complete positioning of the tag UWB unit. In the positioning process of the UWB indoor positioning system, a positioning base station or a positioning tag may initiate a ranging request actively, and further determine the position of the positioning tag through a Time of flight (TOF) ranging manner or a Time Difference of Arrival (TDOA) ranging manner, thereby implementing positioning.

In the indoor positioning process of the current UWB technology, because the environment occlusion or multipath effect in the positioning scene may cause great interference to the positioning effect, fig. 2 is an environment occlusion schematic diagram of UWB indoor positioning provided according to the related art, as shown in fig. 2, in the working process of the UWB indoor positioning system, when there is occlusion between the positioning base station and the positioning tag, such as a wall, etc., then the signal transmission between the positioning base station and the positioning tag is interfered to cause the positioning accuracy to decrease.

In the related art, the method of increasing the distribution number or density of the base stations is adopted to reduce the influence of environmental occlusion or multipath effect; however, the layout difficulty and the equipment cost in the process of increasing the base station are greatly increased.

In view of the above problem in the related art that the positioning effect of UWB positioning is easily affected by environmental occlusion or multipath effect to cause interference, no effective solution has been proposed in the related art.

Disclosure of Invention

The embodiment of the invention provides a positioning system and method, a database and a neural network model training method, which at least solve the problem that the positioning effect of UWB positioning in the related technology is easy to be interfered by the influence of environmental shielding or multipath effect.

According to an embodiment of the present invention, there is provided a positioning system including:

the inertial measurement unit IMU is configured to acquire first measurement information and one or more groups of second measurement information, wherein the first measurement information is real-time measurement information of a target object, and the second measurement information is historical measurement information;

the ultra-wideband UWB unit is configured to acquire one or more groups of second position information, wherein the second position information is historical position information;

the resolving unit is configured to determine first position information according to the first measurement information and a preset neural network model, and position a target object according to the first position information; wherein the neural network model is trained according to the one or more sets of second measurement information and the one or more sets of second location information.

There is also provided, in accordance with another embodiment of the present invention, a database including:

one or more sets of second measurement information, one or more sets of second location information, and a correspondence between the one or more sets of second measurement information and the one or more sets of second location information;

wherein the one or more sets of second measurement information are acquired by one or more Inertial Measurement Units (IMUs), and the one or more sets of second location information are acquired by one or more ultra-wideband UWB units.

According to another embodiment of the present invention, there is also provided a positioning method including:

acquiring first measurement information and one or more groups of second measurement information; the first measurement information is real-time measurement information of a target object, and the one or more groups of second measurement information are historical measurement information;

determining first position information according to the first measurement information and a preset neural network model, and positioning the target object according to the first position information;

the neural network model is obtained by training one or more groups of second measurement information and one or more groups of second position information, and the one or more groups of second position information are historical position information.

According to another embodiment of the present invention, there is also provided a neural network model training method, including:

acquiring one or more groups of second measurement information, wherein the one or more groups of second measurement information are acquired through an Inertial Measurement Unit (IMU);

acquiring one or more groups of second position information, wherein the one or more groups of second position information are acquired through an ultra-wideband UWB unit;

and training a preset neural network model according to the one or more groups of second measurement information and the one or more groups of second position information to obtain the trained neural network model.

According to another embodiment of the present invention, there is also provided a positioning apparatus including:

the measurement module is used for acquiring first measurement information and one or more groups of second measurement information; the first measurement information is real-time measurement information of a target object, and the one or more groups of second measurement information are historical measurement information;

the resolving module is used for determining first position information according to the first measurement information and a preset neural network model and positioning the target object according to the first position information;

According to another embodiment of the present invention, there is also provided a neural network model training apparatus including:

the first acquisition module is used for acquiring one or more groups of second measurement information, wherein the one or more groups of second measurement information are acquired through an inertial measurement unit IMU;

the second acquisition module is used for acquiring one or more groups of second position information, wherein the one or more groups of second position information are acquired through the ultra-wideband UWB unit;

and the training module is used for training a preset neural network model according to the one or more groups of second measurement information and the one or more groups of second position information to obtain the trained neural network model.

According to another embodiment of the present invention, a computer-readable storage medium is also provided, in which a computer program is stored, wherein the computer program is configured to perform the steps of any of the above-described method embodiments when executed.

According to another embodiment of the present invention, there is also provided an electronic device, including a memory in which a computer program is stored and a processor configured to execute the computer program to perform the steps in any of the above method embodiments.

According to the invention, as the training of the neural network model is carried out by one or more groups of second measurement information which are acquired by the inertial measurement unit IMU and serve as historical measurement information and one or more groups of second position information which are acquired by the ultra-wideband UWB unit and serve as historical position information, the first measurement information acquired by the inertial measurement unit IMU and the first position information corresponding to the target can be further acquired by the neural network model, so that the target object can be positioned. Therefore, the invention can solve the problem that the positioning effect of UWB positioning in the related technology is easy to be interfered by the influence of environment shielding or multipath effect, so as to achieve the effect of improving the precision of UWB positioning.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:

fig. 1 is an operation diagram of a UWB indoor positioning system provided according to the related art;

FIG. 2 is an environmental occlusion diagram of UWB indoor positioning provided according to the related art;

FIG. 3 is a functional schematic diagram of a positioning system provided in accordance with an embodiment of the present invention;

FIG. 4 is a schematic diagram of the operation of a positioning system provided in accordance with an embodiment of the present invention;

FIG. 5 is a schematic diagram (one) of an interaction of a positioning system provided in accordance with an embodiment of the present invention;

FIG. 6 is a schematic diagram of an interaction of a positioning system according to an embodiment of the present invention;

FIG. 7 is an interaction diagram of a positioning system provided in accordance with an embodiment of the present invention;

FIG. 8 is a schematic diagram of a database provided in accordance with an embodiment of the present invention;

fig. 9 is a flowchart of a positioning method provided according to an embodiment of the present invention;

FIG. 10 is a flow chart of a neural network model training method provided in accordance with an embodiment of the present invention;

FIG. 11 is a block diagram of a positioning apparatus provided in accordance with an embodiment of the present invention;

fig. 12 is a block diagram of a neural network model training apparatus according to an embodiment of the present invention.

Detailed Description

The invention will be described in detail hereinafter with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.

Example 1

The embodiment provides a positioning system, fig. 3 is a functional schematic diagram of the positioning system provided according to the embodiment of the present invention, and as shown in fig. 3, the positioning system in the embodiment includes:

an Inertial Measurement Unit (IMU) 102 configured to obtain first Measurement information and one or more sets of second Measurement information, where the first Measurement information is real-time Measurement information of a target object, and the second Measurement information is historical Measurement information;

an ultra-wideband UWB unit 104 configured to acquire one or more sets of second location information, wherein the second location information is historical location information;

the resolving unit 106 is configured to determine first position information according to the first measurement information and a preset neural network model, and position the target object according to the first position information; the neural network model is obtained by training one or more groups of second measurement information and one or more groups of second position information.

Generally, the IMU includes a plurality of acceleration sensors and angular velocity sensors (or gyroscopes) to measure the acceleration and angular velocity of the target object in space. The IMU may be carried on the location tag, that is, the IMU may be carried on the target object as a part of the location tag, or may be carried on the target object independently of the location tag, which is not limited in the present invention.

The first measurement information obtained by the IMU is real-time measurement information of the target object, that is, the first measurement information indicates real-time measurement information measured by the IMU in the positioning system where the target object is located when the target object is currently positioned. The second measurement information obtained by the IMU is historical measurement information, that is, the second measurement information is historical measurement information obtained by the IMU in the past. The second position information acquired by the UWB unit indicates that the second position information is historical position information acquired by the UWB in the past.

It should be further noted that the second position information may specify position information obtained by positioning the position system without being affected by environmental shielding or multipath effects or being affected within a system error tolerance range, that is, the second position information may be obtained by directly performing ranging and positioning by UWB. For example, in the case that the positioning system is not affected by environmental occlusion or multipath effect, the UWB may directly perform ranging and positioning processing on the object in the system to obtain the position information thereof, i.e., the second position information; meanwhile, the IMU carried by the subject may synchronously acquire measurement information of the subject, i.e., the second measurement information, but in this case, the second measurement information does not participate in the positioning of the subject, and is only used to cooperate with the second location information to perform the training of the neural network model.

On the other hand, the second location information may also be location information determined by the solution unit according to the measurement information of the IUM and the neural network model in this embodiment. For example, at a certain time, the calculating unit determines the first location information of the target object according to the first measurement information of the IUM and the neural network model, and then, with respect to a later time, the first location information may also be used as historical location information, that is, the second location information to participate in the training of the neural network model.

It should be further noted that the second measurement information is not limited to the historical measurement information of the target object, nor to the historical measurement information obtained by the IMU in the positioning system in which the target object is currently positioned, and specifically, the second measurement information may be the historical measurement information measured by the IMU in another positioning system different from the IMU in the positioning system in which the target object is currently positioned, which is different from the reference object of the target object. Correspondingly, the second position information is not limited to the historical position information of the target object, nor to the historical position information obtained by the UWB unit in the positioning system in which the current target object is positioned, and specifically, the second position information may be a reference object different from the target object, a positioning system different from the current area of the target object, or the historical position information measured by the UWB unit included in the positioning system in other areas. In short, the second measurement information and the second position information are not limited to those obtained by the current positioning system, and may be obtained by other historical positioning systems.

In the positioning system of this embodiment, the neural network model obtained by training according to the second measurement information and the second location information may indicate a mapping relationship between the measurement information obtained by the IMU and the location information obtained by the corresponding UWB. Therefore, if the UWB unit cannot effectively locate the target object due to environmental shielding or multipath effect at a certain time, the calculating unit may input the first measurement information indicating the current real-time measurement information of the target object, which is measured by the IMU, into the neural network model, and obtain the location information corresponding to the first measurement information according to the mapping relationship between the measurement information and the location information.

It should be further noted that the position information in this embodiment may be distance information (relative to the positioning base station) or coordinate information.

The calculating unit may be set in the positioning tag, or may use a computing device, such as a PC, in a scene where the positioning system is located to perform calculating processing, or may use a server set in the cloud to perform calculating processing, which is not limited in this invention. The neural network model may be stored in the solution unit, or may be independently stored in another computer-readable storage medium, which is not limited in this respect.

Through the positioning system in the embodiment, the neural network model can be trained through one or more groups of second measurement information which is acquired by the inertial measurement unit IMU and serves as historical measurement information and one or more groups of second position information which is acquired by the ultra-wideband UWB unit and serves as historical position information, so that the first measurement information acquired by the inertial measurement unit IMU and the first position information corresponding to the target can be further acquired through the neural network model, and the target object can be positioned. Therefore, the positioning system in the above embodiment can solve the problem that the positioning effect of UWB positioning in the related art is easily interfered by environmental shielding or multipath effect, so as to achieve the effect of improving the accuracy of UWB positioning.

Specifically, when the positioning system is not influenced by environmental shielding or the like at the historical time, the ranging of the UWB unit is not influenced, so that the ranging can accurately determine the position information of the object, i.e., the second position information, and the measurement information obtained by the IMU is also accurate (the IMU is not influenced by environmental shielding or the like), i.e., the second measurement information; therefore, the second measurement information can correspond to an accurate second position information. The position information corresponding to the measurement information obtained by IMU measurement can be obtained by the neural network model trained by the method. And at the current moment, when the UWB unit cannot accurately perform ranging positioning due to the influence of environmental shielding and the like, the measurement information of the object at the current moment can be obtained through the IMU, and the corresponding position information is further obtained through calculation according to the neural network model so as to perform positioning processing.

It should be further noted that the positioning system in this embodiment may also perform positioning processing according to a UWB positioning manner that is conventional in the related art. Whether the UWB unit is influenced during ranging, namely whether the first measurement information obtained by IMU measurement and the neural network model need to be adopted for positioning or not, and the detection of the signal of the positioning base station can be judged according to the positioning label.

In addition, when the UWB unit is affected by environmental occlusion or multipath effects, it may not result in a complete failure of the ranging process in the positioning of the UWB unit, that is, there is a situation that the ranging process of the UWB unit is still partially effective.

In an optional embodiment, the IMU includes at least one of: an acceleration sensor, an angular velocity sensor, and a geomagnetic sensor; wherein the content of the first and second substances,

the acceleration sensor is configured to acquire first acceleration information and second acceleration information, wherein the first acceleration information is real-time acceleration information of a target object, and the second acceleration information is historical acceleration information;

the angular velocity sensor is configured to acquire first angular velocity information, or the angular velocity sensor is configured to acquire the first angular velocity information and second angular velocity information; the first angular velocity information is real-time angular velocity information of a target object, and the second angular velocity information is historical angular velocity information;

the geomagnetic sensor is configured to acquire first geomagnetic information, or the geomagnetic sensor is configured to acquire the first geomagnetic information and second geomagnetic information; the first geomagnetic information is real-time geomagnetic information of the target object, and the second geomagnetic information is historical geomagnetic information.

It should be further noted that the first acceleration information and the second acceleration information obtained by the acceleration sensor are both used for indicating the acceleration of the measurement object; the first angular velocity information and the second angular velocity information obtained by the angular velocity sensor are both used for indicating the angular velocity of the measurement object; the first geomagnetic information and the second geomagnetic information obtained by the geomagnetic sensor are used for indicating geomagnetic information, such as a geomagnetic vector, of a position where the measurement object is located. The angular velocity sensor and the geomagnetic sensor can acquire different objects in different working modes, for example, the angular velocity sensor can only acquire first angular velocity information without acquiring second angular velocity information to train a neural network model, or acquire the second angular velocity information to train the neural network model while acquiring the first angular velocity information to position, and the geomagnetic sensor is similar to the geomagnetic sensor; this will be explained in the following alternative embodiments, which will not be described in detail here.

In an optional embodiment, the first measurement information comprises at least first acceleration information, and the second measurement information comprises at least second acceleration information;

the resolving unit is further configured to determine first speed information according to the first acceleration information and the neural network model, and determine first position information according to the first speed information and the first angular velocity information to locate the target object.

It should be further noted that, in the above-mentioned alternative embodiment, in the case that the first measurement information at least includes the first acceleration information, and the second measurement information at least includes the second acceleration information, the mapping relationship between the second measurement information and the second position information in the neural network model is implemented based on the velocity information; specifically, the second measurement information is an acceleration, i.e., a rate corresponding to the second measurement information can be obtained by a calculation method, and correspondingly, the second position information can also be converted into a rate corresponding to the second position information, so that the neural network model can be trained based on a mapping relationship between the two rates. On this basis, when the first measurement information is the first acceleration information, the first acceleration information may be input to the neural network model, the first acceleration information is converted into the corresponding velocity, and the velocity corresponding to the corresponding position information, that is, the first velocity information in the optional embodiment, is determined according to the mapping relationship.

The first speed information is used for indicating the current speed of the target object, on the basis, the vector speed of the target object can be further determined according to the first angular speed information obtained by the IMU, and on the basis, the real-time speed of the target object can be obtained and the target object can be positioned.

In an optional embodiment, the system further includes a filtering unit, where the filtering unit is configured to perform complementary filtering processing according to the first geomagnetic information and the first angular velocity information to obtain first heading information;

the resolving unit is further configured to determine first position information according to the first speed information and the first heading information so as to locate the target object.

It should be further noted that, the complementary filtering processing is performed according to the first geomagnetic information and the first angular velocity information, so as to determine a heading information, so as to further determine a moving direction of the target object, and thus, the target object is located by combining the first speed information. The complementary filtering described above can be implemented by the Mahony algorithm.

In an optional embodiment, the first measurement information includes at least first acceleration information and first angular velocity information, and the second measurement information includes at least second acceleration information and second angular velocity information;

the resolving unit 106 is further configured to determine first relative inertia information according to the first acceleration information and the first angular velocity information, determine first velocity information according to the first relative inertia information and the neural network model, and determine first position information according to the first velocity information to position the target object;

the first relative inertia information is used for indicating the speed information of the target user in a first coordinate, and the first coordinate is the station center coordinate of the target user.

It should be further noted that, in the above-mentioned alternative embodiment, in the case that the first measurement information at least includes first acceleration information and first angular velocity information, and the second measurement information at least includes second acceleration information and second angular velocity information, the mapping relationship between the second measurement information and the second position information in the neural network model is implemented based on the velocity information in the first coordinate; specifically, the second measurement information is acceleration and angular velocity, and thus, one piece of inertia information indicating the corresponding velocity information in the first coordinate, which is the center coordinates with the measurement target as the origin, can be determined. The neural network model can be trained on the basis of the speed information indicated by the inertia information and the speed information corresponding to the corresponding second position information so as to obtain the mapping relation of the neural network model.

On this basis, when the IMU acquires the inertial information corresponding to the first measurement information, the corresponding velocity information may be acquired according to the neural network model to serve as the first velocity information, and further, a possible motion position and a possible motion direction of the target object at the current time, that is, a motion state of the target object, may be determined. Based on this, the target object may be located at the current time by combining the previous motion path of the target object or the ranging information of other positioning base stations, so as to determine the first location information. In the actual calculation process, the speed information can also be directly subjected to integration processing to obtain corresponding position information.

It should be further noted that, since the angular velocity information obtained by the angular velocity sensor in the IMU is based on the relative coordinate system of the sensor itself, i.e. the coordinates of the center of gravity with the target object as the origin, the first coordinate is a relative coordinate system, and the corresponding inertial information obtained according to the first measurement information is the first relative inertial information in the above-mentioned alternative embodiment.

In an optional embodiment, the first measurement information further includes first geomagnetic information, and the second measurement information further includes second geomagnetic information;

the resolving unit 106 is further configured to determine first relative inertial information according to the first acceleration information and the first angular velocity information, and convert the first relative inertial information according to the first geomagnetic information to obtain first absolute inertial information;

determining first speed information according to the first absolute inertial information and the neural network model, and determining first position information according to the first speed information to position a target object;

the first absolute inertial information is used for indicating the speed information of the target user in a second coordinate, and the second coordinate is a geocentric coordinate.

It should be further noted that, in the above alternative embodiment, geomagnetic information is introduced into the first measurement information and the second measurement information, so for the neural network model, the second measurement information referred to in the training stage is actually obtained from the acceleration information and the angular velocity information, and then the corresponding relative inertial information is converted by the geomagnetic information to determine a new piece of inertial information, that is, absolute inertial information; specifically, after introducing the geomagnetic information, the geomagnetic information may be used as a conversion coefficient (the coefficient may be a geomagnetic vector, i.e., an angle between the object and the north magnetic direction) to convert the relative inertial information, so as to obtain the absolute inertial information, where the absolute inertial information is used to indicate corresponding speed information in geocentric coordinates, specifically, northeast coordinates of the local location where the positioning system is located, i.e., the second coordinates. The neural network model can be trained on the basis of the speed information indicated by the absolute inertia information and the speed information corresponding to the corresponding second position information so as to obtain the mapping relation of the neural network model.

On this basis, when the IMU acquires the absolute inertia information corresponding to the first measurement information, the corresponding velocity information may be acquired according to the neural network model to serve as the first velocity information, and further, a possible motion position and a possible motion direction of the target object at the current time, that is, a motion state of the target object, may be determined. Based on this, the target object may be located at the current time by combining the previous motion path of the target object or the ranging information of other positioning base stations, so as to determine the first location information. In the actual calculation process, the speed information can also be directly subjected to integration processing to obtain corresponding position information.

In addition, the correspondence relationship may be established without using coordinate information, and the correspondence may be performed directly based on the speed information, specifically, the calculation unit may be configured to:

determining measured velocity information from the first acceleration information and the first angular velocity information,

and determining first speed information according to the measured speed information and the neural network model, and determining first position information according to the first speed information so as to position the target object.

The measured speed information is speed information obtained by calculating according to first acceleration information and first angular speed information of the target object measured by the IMU.

In an optional embodiment, the neural network model comprises a neural network model weight, wherein the neural network model weight is used for indicating a mapping relationship between the second measurement information and the corresponding one or more sets of second rate information;

determining the weight of the neural network model according to the regression relationship between the input samples and the output samples of the neural network model, wherein the input samples are one or more groups of second measurement information, and the output samples are one or more groups of second rate information;

wherein the second rate information is used to indicate historical rate information, and one or more sets of rate information are obtained according to one or more sets of second location information.

It should be further noted that the training of the neural network model is applicable to the case where the first measurement information is the first acceleration information, and the second measurement information is the second acceleration information. As described in the foregoing alternative embodiment, the mapping relationship between the second measurement information and the second location information in the neural network model is implemented based on the rate information; specifically, after the UWB unit acquires the second position information, the second position information may be converted to obtain corresponding rate information, that is, the second rate information in the above-mentioned alternative embodiment, and correspondingly, the second acceleration information acquired by the IMU may also be converted into rate information in a calculation manner, so as to be mutually corresponding to the second rate information. And determining the corresponding relation, namely determining a neural network weight in the neural network model, wherein the neural network weight can indicate the mapping relation between the second acceleration information and the second rate information, and further indicate the mapping relation between the second measurement information and the second rate information.

In this alternative embodiment, the neural network model may adopt a BP neural network model, or an equivalent neural network model; the structure and training process of the BP neural network model are known to those skilled in the art and are not described herein.

In an optional embodiment, the solution unit 106 is further configured to:

taking the first acceleration information as an input parameter of a neural network model, acquiring a corresponding output parameter according to the neural network model, and taking the output parameter as first speed information;

and determining first position information according to the first speed information and the first angular speed information so as to position the target object.

In an optional embodiment, the neural network model comprises a neural network model weight, wherein the neural network model weight is used for indicating a mapping relationship between the second measurement information and the corresponding one or more sets of second speed information;

determining the weight of the neural network model according to the regression relationship between the input samples and the output samples of the neural network model, wherein the input samples are one or more groups of second measurement information, and the output samples are one or more groups of second speed information;

wherein the second speed information is used for indicating historical speed information, and one or more groups of speed information are obtained according to one or more groups of second position information.

It should be further noted that the training of the neural network model is applicable to the case where the first measurement information is the first acceleration information, the first angular velocity information, and the first geomagnetic information, and the second measurement information is the second acceleration information, the second angular velocity information, and the second geomagnetic information. As described in the foregoing alternative embodiment, the mapping relationship between the second measurement information and the second location information in the neural network model is implemented based on the speed information; specifically, after the IMU acquires the second acceleration information, the second angular velocity information, and the second geomagnetic information, the second acceleration information, the second angular velocity information, and the second geomagnetic information may be converted into second absolute inertia information to indicate velocity information of the object in the geocentric coordinates; further, the second absolute inertia information is associated with the velocity information corresponding to the second position information acquired by the UWB unit, so that the correspondence between the second measurement information and the second position information can be determined. And determining the corresponding relation, namely determining a neural network weight in the neural network model, wherein the neural network weight can indicate the mapping relation between the second absolute inertia information and the speed information corresponding to the second position information, and further indicate the mapping relation between the second measurement information and the second position information.

It should be further noted that the second speed information may be obtained by performing a calculation process on the second position information, for example, by performing a derivation process on the second position information.

In an alternative embodiment, the calculation unit 106 is configured to:

taking the first acceleration information, the first angular velocity information and the first geomagnetic information as input parameters of a neural network model, obtaining corresponding output parameters according to the neural network model, and taking the output parameters as first velocity information;

and determining first position information according to the first speed information, and positioning the target object according to the first position information.

In an alternative embodiment, the one or more sets of second measurement information include: one or more sets of second measurement information corresponding to the target object and/or one or more sets of second measurement information corresponding to the reference object;

the one or more sets of second location information include: one or more sets of second position information corresponding to the target object, and/or one or more sets of second position information corresponding to the reference object.

It should be further noted that the target object is a target object in the positioning system in this embodiment, and the reference object may be the target object or another object other than the target object. For example, in the same positioning system, the object a, the object B, and the object C are respectively positioned at different times in the past, and the object a, the object B, and the object C can be respectively used as reference objects to obtain one or more sets of second measurement information and one or more sets of second position information corresponding to the object a, the object B, and the object C, thereby implementing training of the neural network model.

Assuming that the object D is located in the positioning system at the current time, that is, the object D is used as a target object, at this time, the trained neural network model can be used for the location processing of the target object.

Furthermore, the reference object is not limited to the same positioning system, and different positioning systems distributed in different areas can participate in the training of the neural network model together. For example, a positioning system M in beijing may obtain one or more sets of second measurement information of the object M at different times through the IMU, and obtain one or more sets of second position information of the object M at different times through the UWB unit; meanwhile, the positioning system N in Shanghai city may acquire one or more sets of second measurement information, at which the object N is positioned at different times, through the IMU, and acquire one or more sets of second location information, at which the object N is positioned at different times, through the UWB unit. The second measurement information and the second location information acquired by the positioning system M, and the second measurement information and the second location information acquired by the positioning system N may be collected together, for example, uploaded to a cloud server to train a neural network model together.

Assuming that the object O located in the guangzhou city is located in the positioning system O, that is, the object O is used as a target object, the trained neural network model can be used for the positioning process of the target object.

Since the processing accuracy of the neural network model increases as the number of training samples increases, in the above alternative embodiment, the accuracy of the neural network model can be significantly improved by no longer limiting the training samples of the neural network model to the target object.

Meanwhile, the training of the neural network model is not limited to the target object, so that the neural network model can be trained before a specific positioning system works. Assuming that the UWB unit cannot effectively perform positioning in the positioning system due to environmental occlusion or multipath effect in the initial stage of positioning the target object, the target object may be positioned by using the IMU in cooperation with the neural network model.

In an optional embodiment, the solution unit 106 is further configured to:

and acquiring third position information of the target object through the UWB unit, and positioning the target object according to the third position information.

It should be further noted that, the third position information indicates that the UWB unit directly performs the ranging and positioning process on the target object, that is, the positioning system in this embodiment may not perform the positioning process through the first measurement information measured by the IMU and the neural network model, but perform the positioning process through the conventional UWB unit.

The operation of the positioning system in this embodiment is further described below by way of specific embodiments.

Detailed description of the preferred embodiment 1

Fig. 4 is a schematic diagram illustrating an operation of a positioning system according to an embodiment of the present invention, where the positioning system includes an IMU including an acceleration sensor, an angular velocity sensor, and a geomagnetic sensor, and a UWB unit, as shown in fig. 4.

In the working process of the positioning system, at the first time, the IMU acquires the acceleration of the target object, and the UWB unit acquires the distance measurement value (i.e., the position information in the above embodiment) of the target object, and trains the acceleration and the distance measurement value as the input sample and the output sample of the neural network model. Specifically, the neural network model is a mapping relationship between the acceleration and the rate corresponding to the range value, which is determined based on a regression relationship between the rate corresponding to the acceleration and the rate corresponding to the range value.

At the second moment (the first moment is a historical moment relative to the second moment), the UWB unit has a blind area due to the influence of environmental occlusion or multipath factors, i.e., the data portion obtained by the UWB unit is invalid, and thus an accurate ranging value cannot be obtained. At this time, the current acceleration of the target object can be obtained through the IMU, the speed information corresponding to the acceleration is determined through the neural network model, meanwhile, the course information of the target object is obtained through the angular velocity sensor and the geomagnetic sensor in the IMU through complementary filtering, and the vector speed information of the target object can be determined by integrating the speed information and the course information of the target object.

The possible motion state of the target object can be determined based on the vector velocity information of the target object, and at this time, the motion state of the target object and normal information which can be acquired by UWB are fused, specifically, the fusion processing is performed on the motion state of the target object and the normal information, such as a motion path or a motion state before the target object, or a coordinate position or a distance of the target object, and specifically, the fusion processing may be particle filtering or kalman filtering, that is, the current position of the target object can be correspondingly obtained, and then positioning processing is implemented.

It should be further noted that, in the above embodiments, the subject of the neural network model training may be different, and the following further describes the process of the neural network model training and the positioning system for positioning the target object through a plurality of embodiments.

Specific example 2

Fig. 5 is an interaction schematic diagram (i) of the positioning system according to the specific embodiment of the present invention, as shown in fig. 5, in a working process of the positioning system, a corresponding solution engine (i.e., a solution unit in the above embodiment) obtains a ranging value or a position coordinate of a positioning base station, so as to solve a second motion state of a target object, and sends the second motion state of the target object to a positioning tag carried by the target object. The positioning label can acquire corresponding measurement information according to the second motion state sent by the resolving engine and the IMU carried by the positioning label, and then training of the neural network model is completed.

At a later time, the positioning tag can rely on corresponding measurement information obtained by the carried IMU, so that the first motion state of the target object can be determined according to the trained neural network model. The positioning label further sends the first motion state to a resolving engine, and the resolving engine determines and selects a second motion state or a first motion state of the target object at the current moment as a motion state of the target object, namely speed information of the target object according to the motion mode of the target object at the previous moment, so that the target object is positioned.

Specific example 3

Fig. 6 is an interaction schematic diagram (ii) of the positioning system according to the specific embodiment of the present invention, as shown in fig. 6, in a working process of the positioning system, a corresponding solution engine (i.e., a solution unit in the foregoing embodiment) acquires a ranging value or a position coordinate of a positioning base station, so as to solve a second motion state of a target object, and at the same time, a positioning tag sends corresponding measurement information acquired according to an IMU carried by the positioning tag to the solution engine, so that the solution engine trains a neural network model according to the second motion state and the measurement information.

After the calculation engine finishes the training of the neural network model, the weight of the neural network model can be sent to the positioning label, namely, the calculation engine directly informs the relationship between the measurement information of the positioning label and the corresponding motion state. At a later moment, the positioning tag can acquire the first motion state of the target object according to the measurement information at the current moment and the weight value of the neural network model. The positioning tag sends the first motion state to a resolving engine, and the resolving engine determines and selects a second motion state or a first motion state of the target object at the current moment as a motion state of the target object, namely speed information of the target object, according to the motion mode of the target object at the previous moment, so that the target object is positioned.

Specific example 3

Fig. 7 is an interaction schematic diagram (iii) of the positioning system according to the specific embodiment of the present invention, as shown in fig. 7, in the working process of the positioning system, a corresponding solution engine (i.e., a solution unit in the above embodiment) acquires a ranging value or a position coordinate of a positioning base station, so as to solve a second motion state of a target object, and at the same time, a positioning tag sends corresponding measurement information acquired according to an IMU carried by the positioning tag to the solution engine, so that the solution engine trains a neural network model according to the second motion state and the measurement information.

At a later moment, the positioning tag can send the measurement information of the current moment to the resolving engine, so that the resolving engine can obtain a corresponding first motion state according to the measurement information of the current moment and the trained neural network model on the one hand, and can also obtain a second motion state of the target object through the ranging value of the positioning base station obtained at the current moment. The resolving engine further determines and selects a second motion state or a first motion state of the target object at the current moment as a motion state of the target object, namely speed information of the target object, according to the motion mode of the target object at the previous moment, so that the positioning processing of the target object is completed.

Example 2

Fig. 8 is a schematic diagram of a database provided according to an embodiment of the present invention, and as shown in fig. 8, the database in the embodiment includes:

a database, comprising:

and acquiring one or more sets of second measurement information by one or more Inertial Measurement Units (IMUs), and acquiring one or more sets of second position information by one or more ultra-wideband UWB units.

It should be further noted that the database in this embodiment indicates a database in which the second measurement information, the second location information, and the corresponding relationship between the second measurement information and the second location information are stored. The corresponding relationship between the second measurement information and the second position information may be obtained by a neural network training mode, or may be obtained by a fitting mode. The database in this embodiment may be stored in a server or a terminal in a scene where a certain positioning system is located, or may be stored in a cloud server, which is not limited in this disclosure.

It should be further noted that, in the database, one or more groups of second measurement information may be obtained by one or more IMUs, which specifically indicates that the second measurement information in the database may be measurement information of the same object or different objects obtained by the same IMU, or measurement information of different objects obtained by multiple IMUs respectively; correspondingly, one or more groups of second position information are acquired by one or more UWB units, and the second position information in the specific indication database may be position information of the same object or different objects acquired by the same UWB, or position information of different objects acquired by a plurality of UWB units respectively. The IMU and the UWB unit in this embodiment both refer to the IMU and the UWB unit in the positioning system shown in embodiment 1, that is, while a certain IMU acquires a set of second measurement information in this embodiment, the UWB unit located in the same positioning system as the IMU also acquires a set of corresponding second location information, and uploads the second location information to the database in this embodiment synchronously.

In an alternative embodiment, the database further comprises: a preset neural network model;

the database is further configured to determine a mapping relationship between the second measurement information and second location information corresponding to the second measurement information according to the neural network model.

It should be further noted that, in the above alternative embodiment, the mapping relationship between the second measurement information and the second location information corresponding to the second measurement information is determined by means of training of a neural network model. According to the difference of the second measurement information, the neural network model may adopt different training modes, and specifically, the training mode of the neural network model in this optional embodiment corresponds to the training mode of the neural network model in embodiment 1, and therefore, details are not described here again.

Example 3

The embodiment provides a positioning method, and fig. 9 is a schematic diagram of the positioning method provided according to the embodiment of the present invention, as shown in fig. 9, the positioning method in the embodiment includes:

s302, the IMU acquires first measurement information and one or more groups of second measurement information; the first measurement information is real-time measurement information of a target object, and one or more groups of second measurement information are historical measurement information;

s304, the resolving unit determines first position information according to the first measurement information and a preset neural network model, and positions the target object according to the first position information;

The technical features and technical effects of the positioning method in this embodiment are all corresponding to those of the positioning system in embodiment 1, and therefore are not described herein again.

determining first position information according to the first measurement information and a preset neural network model, wherein the first position information comprises the following steps:

determining first speed information according to the first acceleration information and the neural network model;

and acquiring first angular velocity information, and determining first position information according to the first velocity information and the first angular velocity information.

In an optional embodiment, the method further comprises: acquiring first geomagnetic information, and performing complementary filtering processing according to the first geomagnetic information and the first angular velocity information to acquire first heading information;

determining first position information according to the first rate information and the first angular velocity information, including:

and determining first position information according to the first speed information and the first heading information.

determining first relative inertia information according to the first acceleration information and the first angular velocity information, determining first velocity information according to the first relative inertia information and the neural network model, and determining first position information according to the first velocity information to position the target object;

determining first position information according to the first measurement information and a preset neural network model, and further comprising:

determining first relative inertia information according to the first acceleration information and the first angular velocity information, and converting the first relative inertia information according to the first geomagnetic information to obtain first absolute inertia information; determining first speed information according to the first absolute inertial information and the neural network model, and determining first position information according to the first speed information to position a target object;

In an alternative embodiment, determining the first rate information from the first acceleration information and the neural network model comprises:

and taking the first acceleration information as an input parameter of the neural network model, acquiring a corresponding output parameter according to the neural network model, and taking the output parameter as first speed information.

In an optional embodiment, determining the first location information according to the first measurement information and a preset neural network model includes:

In an optional embodiment, the method further comprises:

Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.

Example 4

Fig. 10 is a flowchart of a neural network model training method according to an embodiment of the present invention, and as shown in fig. 10, the neural network model training method in this embodiment includes:

s402, acquiring one or more groups of second measurement information, wherein the one or more groups of second measurement information are acquired through an Inertial Measurement Unit (IMU);

s404, acquiring one or more groups of second position information, wherein the one or more groups of second position information are acquired through an ultra-wideband UWB unit;

s406, training the preset neural network model according to the one or more groups of second measurement information and the one or more groups of second position information to obtain the trained neural network model.

It should be further noted that, in the foregoing embodiment, the IMU and the UWB unit are the IMU and the UWB unit in the positioning system shown in embodiment 1, that is, in this embodiment, while one IMU acquires a set of second measurement information, the UWB unit located in the same positioning system as the IMU also acquires a set of corresponding second location information, and uploads the second location information to the database in this embodiment synchronously. In the step S406, the process of training the preset neural network model according to one or more sets of the second measurement information and one or more sets of the second location information is to use the second measurement information and the second location information, which are obtained at the same time by the IMU and the UWB unit belonging to the same positioning system, as the training samples of the neural network model, that is, in the process of training the neural network model, when a set of the second measurement information is input, a set of the second location information corresponding to the second measurement information is also correspondingly input to complete the training.

It should be further noted that the execution subject of the steps S402 to S406 is a processing unit, such as a calculation engine, storing the subject of the neural network model.

In an optional embodiment, training the preset neural network model according to the one or more sets of second measurement information and the one or more sets of second location information includes:

taking one or more groups of second measurement information as input samples of the neural network model, and taking one or more groups of second position information as output samples of the neural network model;

determining a neural network model weight according to a regression relationship between input samples and output samples of the neural network model, wherein the neural network model weight is used for indicating a mapping relationship between second measurement information and second position information corresponding to the second measurement information;

and training the neural network model according to the weight of the neural network model.

It should be further noted that the regression relationship between the input samples and the output samples of the neural network model can be determined by fitting or the like. The neural network model can adopt a BR neural network model.

In an optional embodiment, the second measurement information at least includes: second acceleration information;

determining a neural network model weight according to a regression relationship between input samples and output samples of the neural network model, including:

acquiring second speed information corresponding to the second position information according to the second position information;

and determining the weight value of the neural network model according to the regression relation between the second acceleration information and the second speed information.

It should be further explained that the second speed information, i.e. the speed information obtained after the second position information is converted; the neural network model weight is determined according to the regression relationship between the second acceleration information and the second rate information, and the second acceleration information may also be converted into corresponding rate information (for example, by integration processing) to implement the correspondence with the second rate information, i.e., the training of the neural network model based on the rate information may be completed.

In an optional embodiment, the second measurement information comprises: second acceleration information and second angular velocity information;

determining corresponding second relative inertia information according to the second acceleration information and the second angular velocity information, and acquiring second velocity information corresponding to the second position information according to the second position information; the second relative inertia information is used for indicating the speed information of the target object in a first coordinate, and the first coordinate is a station center coordinate of the target object;

and determining the weight value of the neural network model according to the regression relation between the second relative inertia information and the second speed information.

It should be further noted that the second relative inertia information indicates the relative inertia information of the object at the historical time, which is determined according to the second acceleration information and the second angular velocity information, specifically, the station center coordinate corresponding to the object at the historical time, that is, the velocity information in the first coordinate. And determining the weight of the neural network model according to the regression relationship between the second relative inertia information and the second speed information, so as to complete the training of the neural network model based on the relative coordinate system.

In an optional embodiment, the second measurement information further includes: second geomagnetic information;

determining corresponding second absolute inertia information according to second acceleration information, second angular velocity information and second geomagnetic information, wherein the second absolute inertia information is used for indicating velocity information of the target user in a second coordinate, and the second coordinate is a geocentric coordinate;

and determining the weight value of the neural network model according to the regression relationship between the second absolute inertia information and the second speed information.

It should be further noted that the second absolute inertia information indicates absolute inertia information of the object at the historical time, which is determined according to the second acceleration information, the second angular velocity information, and the second geomagnetic information, and specifically is geocentric coordinates corresponding to the object at the historical time, that is, velocity information in the second coordinates. And determining the weight of the neural network model according to the regression relationship between the second absolute inertia information and the second speed information, so as to complete the training of the neural network model based on the absolute coordinate system.

Example 5

The present embodiment provides a positioning device, which is used to implement the above embodiments and preferred embodiments, and the description of the positioning device is omitted for brevity. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.

Fig. 11 is a block diagram of a positioning apparatus according to an embodiment of the present invention, and as shown in fig. 11, the positioning apparatus in this embodiment includes:

a measurement module 502, configured to obtain first measurement information and one or more sets of second measurement information; the first measurement information is real-time measurement information of a target object, and one or more groups of second measurement information are historical measurement information;

the resolving module 504 is configured to determine first position information according to the first measurement information and a preset neural network model, and locate a target object according to the first position information;

Other technical features and technical effects of the positioning apparatus in this embodiment correspond to those of the positioning method in embodiment 3, and therefore are not described herein again.

It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.

Example 6

The present embodiment provides a neural network model training apparatus, which is used to implement the foregoing embodiments and preferred embodiments, and the details of which have been already described are not repeated. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.

Fig. 12 is a block diagram of a neural network model training device according to an embodiment of the present invention, and as shown in fig. 12, the neural network model training device in this embodiment includes:

a first obtaining module 602, configured to obtain one or more sets of second measurement information, where the one or more sets of second measurement information are obtained through an inertial measurement unit IMU;

a second obtaining module 604, configured to obtain one or more sets of second location information, where the one or more sets of second location information are obtained through an ultra wideband UWB unit;

the training module 606 is configured to train the preset neural network model according to the one or more sets of the second measurement information and the one or more sets of the second location information, so as to obtain a trained neural network model.

Other technical features and technical effects of the neural network model training device in this embodiment correspond to those of the neural network model training method in embodiment 4, and therefore are not described herein again.

Example 7

Embodiments of the present invention also provide a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to perform the steps of any of the above-mentioned method embodiments when executed.

Alternatively, in the present embodiment, the above-mentioned computer-readable storage medium may be configured to store a computer program for executing the steps of:

s1, obtaining measurement information of the inertial measurement unit IMU for measuring the target object, and obtaining the motion state of the target object according to the measurement information and a preset neural network model;

the neural network model is obtained by training historical measurement information of the target object measured by the IMU and the historical motion state of the target object.

Optionally, in this embodiment, the computer-readable storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.

Example 8

s1, acquiring historical measurement information of the inertial measurement unit IMU for measuring the target object;

s2, acquiring the historical motion state of the target object;

and S3, training the preset neural network model according to the historical measurement information and the historical motion state to obtain the trained neural network model.

Example 9

Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.

Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.

Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:

Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again.

Example 10

s2, acquiring the historical motion state of the target object;

It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A positioning system, comprising:

2. The system of claim 1, wherein the IMU includes at least one of: an acceleration sensor, an angular velocity sensor, and a geomagnetic sensor; wherein the content of the first and second substances,

the acceleration sensor is configured to acquire first acceleration information and second acceleration information, wherein the first acceleration information is real-time acceleration information of the target object, and the second acceleration information is historical acceleration information;

the angular velocity sensor is configured to acquire first angular velocity information, or the angular velocity sensor is configured to acquire first angular velocity information and second angular velocity information; the first angular velocity information is real-time angular velocity information of the target object, and the second angular velocity information is historical angular velocity information;

3. The system of claim 2, wherein the first measurement information includes at least the first acceleration information and the second measurement information includes at least the second acceleration information;

4. The system according to claim 3, further comprising a filtering unit configured to perform complementary filtering processing according to the first geomagnetic information and the first angular velocity information to obtain first heading information;

the resolving unit is further configured to determine the first position information according to the first speed information and the first heading information so as to locate the target object.

5. A database, comprising:

6. A method of positioning, comprising:

7. A neural network model training method is characterized by comprising the following steps:

8. A positioning device, comprising:

9. A neural network model training device, comprising: