CN111458679A - Auxiliary positioning method, device, robot and computer readable storage medium - Google Patents
Auxiliary positioning method, device, robot and computer readable storage medium Download PDFInfo
- Publication number
- CN111458679A CN111458679A CN202010570714.1A CN202010570714A CN111458679A CN 111458679 A CN111458679 A CN 111458679A CN 202010570714 A CN202010570714 A CN 202010570714A CN 111458679 A CN111458679 A CN 111458679A
- Authority
- CN
- China
- Prior art keywords
- wifi
- robot
- network model
- global positioning
- grid
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Remote Sensing (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Radar, Positioning & Navigation (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to an auxiliary positioning method, an auxiliary positioning device, a robot and a computer readable storage medium, wherein the robot acquires WIFI information transmitted by a plurality of WIFI transmitters in an environment in real time through a WIFI receiver; when the number of the currently acquired WIFI identifications is determined to be larger than or equal to the number threshold value and the original global positioning mode fails, the mode for global positioning is switched, the currently acquired WIFI information is input into a pre-trained network model, and the position corresponding to the maximum probability value predicted by the network model is determined as the current position of the self. Namely, when the reliability of the original global positioning mode is low, the WIFI is adopted to carry out auxiliary positioning. Because the reliability of the original global positioning mode at the current moment is lower, and at the moment, the reliability of positioning by adopting the WIFI is higher than that of the original global positioning mode at the current moment, the error rate of the robot in global positioning is favorably reduced.
Description
Technical Field
The application belongs to the field of positioning, and particularly relates to an auxiliary positioning method, an auxiliary positioning device, a robot and a computer readable storage medium.
Background
With the development of science and technology, the robot can realize autonomous or semi-autonomous operation.
Because the working environment of the robot is affected and disturbed more by the outside, the working environment is more complicated and the working environment changes at any time, if the robot is to independently complete the navigation task in the indoor environment, the robot is required to be capable of determining the global position of the robot in the environment, namely, the robot is capable of independently performing global positioning. Global positioning means that the robot senses information through a sensor (such as a laser emitter, a camera and the like) owned by the robot to determine the pose without any prior knowledge (which is entered into the robot in advance) of the initial pose.
In existing solutions, robots typically perform global localization or localization based on monocular vision by using a particle filtering method based on the monte carlo algorithm. However, the existing global positioning algorithms have certain defects. For example, when the map is large, the number of particles that need to be generated by the particle filter algorithm based on the monte carlo algorithm is relatively large, so that the calculation amount is large, which is not favorable for realizing accurate positioning. When monocular vision is used for positioning, a vision system is needed, the cost and the calculation burden of the robot are increased, and in addition, if the processed image is complex, the calculation pressure is further increased, so that the positioning accuracy is reduced.
When the global positioning accuracy at some time is too low, the reliability of the positioning result obtained by the robot is low, and finally, a global positioning error is caused.
Disclosure of Invention
In view of the above, an object of the present application is to provide an auxiliary positioning method, an auxiliary positioning device, a robot, and a computer-readable storage medium, which are used to switch to another global positioning mode when an original global positioning mode of the robot has low reliability, so as to assist the original global positioning mode in positioning, and reduce an error rate of the robot in global positioning.
The embodiment of the application is realized as follows:
in a first aspect, an embodiment of the present application provides an auxiliary positioning method, which is applied to a robot that operates in an environment provided with a plurality of WIFI transmitters, the robot including a WIFI receiver, and the method including: the WIFI receiver collects WIFI information transmitted by the plurality of WIFI transmitters in real time, and the WIFI information is used for representing a WIFI identifier of the received WIFI signal and a signal intensity value of the WIFI signal corresponding to the WIFI identifier; when the number of the currently acquired WIFI identifications is determined to be larger than or equal to a number threshold value and an original global positioning mode fails, inputting the currently acquired WIFI information into a pre-trained network model; and determining the position corresponding to the maximum probability value predicted by the network model as the current position of the self. Namely, when the reliability of the original global positioning mode is low, the WIFI is adopted to carry out auxiliary positioning. Because the reliability of the original global positioning mode at the current moment is low, if the original global positioning mode is continuously adopted, the robot positioning error can be caused, and at the moment, the reliability of positioning by adopting the WIFI is higher than that of the original global positioning mode at the current moment, so that the error rate of the robot in the global positioning process can be reduced.
With reference to the embodiment of the first aspect, in a possible implementation manner, before the inputting the currently acquired WIFI information into a pre-trained network model, the method further includes: acquiring a positioning evaluation factor in real time, wherein the positioning evaluation factor is used for representing the credibility of the original global positioning mode; and when the positioning evaluation factor is smaller than an evaluation threshold value, determining that the original global positioning mode is invalid.
With reference to the embodiment of the first aspect, in a possible implementation manner, when the original global positioning manner is global positioning performed by a monte carlo-based particle filter algorithm, the obtaining a positioning evaluation factor in real time includes: acquiring a variance value of the particle filter algorithm in real time, and determining the variance value as the positioning evaluation factor; or, acquiring the laser matching degree of the particle filter algorithm in real time, and determining the laser matching degree as the positioning evaluation factor.
With reference to the embodiment of the first aspect, in a possible implementation manner, before the inputting the currently acquired WIFI information into a pre-trained network model, the method further includes: constructing a scene map according to a pre-stored map construction algorithm and pre-acquired composition data; dividing the scene map into grids with preset sizes, and determining grid identification and coordinate ranges for each grid; forming a corresponding mapping relation between the WIFI information acquired when the WIFI information travels to the coordinate range corresponding to each grid and the corresponding grid identification for storage; and when the number of the WIFI identifications included in the WIFI information corresponding to each grid identification is determined to be larger than or equal to the number threshold, inputting the mapping relation into a pre-stored support vector machine for training to obtain a network model which takes the WIFI information as input and the probability value of the grid identification as output.
With reference to the embodiment of the first aspect, in a possible implementation manner, before the inputting the mapping relationship into a pre-stored support vector machine for training, the method further includes: when the number of the WIFI identifications included in the WIFI information corresponding to at least one grid identification is determined to be smaller than the number threshold value, the WIFI information is stored, and new WIFI information is collected in a coordinate range corresponding to the grid corresponding to the at least one grid identification.
With reference to the embodiment of the first aspect, in one possible implementation manner, the method further includes: when the number of the currently acquired WIFI identifications is determined to be larger than or equal to the number threshold value and the original global positioning mode is effective, updating the mapping relation according to the currently acquired WIFI information; and when the difference between the updated mapping relation and the original mapping relation is determined, retraining the support vector machine based on the updated mapping relation, and updating the network model by using the latest network model obtained after training.
With reference to the embodiment of the first aspect, in a possible implementation manner, before the determining the location corresponding to the maximum probability value predicted by the network model as the current location of the mobile terminal itself, the method further includes: and determining that the difference between the maximum probability value predicted by the network model and the second-order probability value is greater than a preset probability threshold.
In a second aspect, an embodiment of the present application provides an auxiliary positioning device, which is applied to a robot operating in an environment provided with a plurality of WIFI transmitters, the robot including a WIFI receiver, the device including: the device comprises an acquisition module, an input module and a determination module. The acquisition module is used for acquiring WIFI information transmitted by the plurality of WIFI transmitters in real time through the WIFI receiver, and the WIFI information is used for representing a WIFI identifier of the received WIFI signal and a signal intensity value of the WIFI signal corresponding to the WIFI identifier; the input module is used for inputting the currently acquired WIFI information into a pre-trained network model when the number of the currently acquired WIFI identifications is determined to be larger than or equal to a number threshold value and an original global positioning mode fails; and the determining module is used for determining the position corresponding to the maximum probability value predicted by the network model as the current position of the self.
With reference to the second aspect, in a possible implementation manner, the apparatus further includes an obtaining module, configured to obtain, in real time, a positioning evaluation factor, where the positioning evaluation factor is used to characterize a reliability of the original global positioning mode; the determining module is further configured to determine that the original global positioning mode is invalid when the positioning evaluation factor is smaller than an evaluation threshold.
With reference to the second aspect, in a possible implementation manner, the obtaining module is configured to obtain a variance value of the particle filtering algorithm in real time, and determine the variance value as the positioning evaluation factor; or, acquiring the laser matching degree of the particle filter algorithm in real time, and determining the laser matching degree as the positioning evaluation factor.
With reference to the second aspect, in a possible implementation manner, the apparatus further includes a construction module, configured to construct a scene map according to a pre-stored map construction algorithm and pre-acquired composition data; the segmentation module is used for segmenting the scene map into grids with preset sizes and determining grid identification and coordinate ranges for each grid; the storage module is used for forming a corresponding mapping relation between the acquired WIFI information and the corresponding grid identification when the WIFI information advances to the coordinate range corresponding to each grid for storage; and the training module is used for inputting the mapping relation into a pre-stored support vector machine for training when the number of the WIFI identifications included in the WIFI information corresponding to each grid identification is determined to be greater than or equal to the number threshold value, so as to obtain a network model which takes the WIFI information as input and the probability value of the grid identification as output.
With reference to the second aspect, in a possible implementation manner, the determining module is further configured to store the WIFI information when it is determined that the number of the WIFI identifiers included in the WIFI information corresponding to at least one grid identifier is smaller than the number threshold, and acquire new WIFI information in a coordinate range corresponding to a grid corresponding to the at least one grid identifier.
With reference to the second aspect, in a possible implementation manner, the apparatus further includes an updating module, configured to update the mapping relationship according to the currently acquired WIFI information when it is determined that the number of the currently acquired WIFI identifiers is greater than or equal to the number threshold and an original global positioning manner is valid, and the training module is further configured to retrain the support vector machine based on the updated mapping relationship and update the network model with an updated network model obtained after training when it is determined that the updated mapping relationship is different from the original mapping relationship.
With reference to the second aspect, in a possible implementation manner, the determining module is further configured to determine that a difference between a maximum probability value predicted by the network model and a second-order probability value is greater than a preset probability threshold.
In a third aspect, an embodiment of the present application further provides a robot including: a memory and a processor, the memory and the processor connected; the memory is used for storing programs; the processor calls a program stored in the memory to perform the method of the first aspect embodiment and/or any possible implementation manner of the first aspect embodiment.
In a fourth aspect, the present application further provides a non-transitory computer-readable storage medium (hereinafter, referred to as a computer-readable storage medium), on which a computer program is stored, where the computer program is executed by a computer to perform the method in the foregoing first aspect and/or any possible implementation manner of the first aspect.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts. The foregoing and other objects, features and advantages of the application will be apparent from the accompanying drawings. Like reference numerals refer to like parts throughout the drawings. The drawings are not intended to be to scale as practical, emphasis instead being placed upon illustrating the subject matter of the present application.
Fig. 1 shows a schematic structural diagram of a robot provided in an embodiment of the present application.
Fig. 2 shows one of flowcharts of an auxiliary positioning method provided in an embodiment of the present application.
Fig. 3 shows a second flowchart of an auxiliary positioning method according to an embodiment of the present application.
Fig. 4 is a schematic diagram illustrating a map divided into grids according to an embodiment of the present application.
Fig. 5 shows a block diagram of an auxiliary positioning device according to an embodiment of the present application.
Icon: 100-a robot; 110-a processor; 120-a memory; 130-a WIFI receiver; 400-auxiliary positioning means; 410-an acquisition module; 420-an input module; 430-determination module.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, relational terms such as "first," "second," and the like may be used solely in the description herein to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Further, the term "and/or" in the present application is only one kind of association relationship describing the associated object, and means that three kinds of relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone.
In addition, the defects existing in the global positioning of the robot in the prior art (due to the low reliability, the global positioning error is caused) are the result obtained after the applicant has practiced and studied carefully, and therefore, the discovery process of the above defects and the solution proposed by the embodiments of the present application to the above defects in the following text should be considered as the contribution of the applicant to the present application.
In order to solve the above problem, embodiments of the present application provide an auxiliary positioning method and apparatus, a robot, and a computer-readable storage medium, where when an original global positioning mode of the robot is low in reliability, the robot is switched to another global positioning mode, so as to assist the original global positioning mode in positioning, which is beneficial to reducing an error rate of the robot in global positioning.
The technology can be realized by adopting corresponding software, hardware and a combination of software and hardware. The following describes embodiments of the present application in detail.
First, a robot 100 for implementing the auxiliary positioning method and apparatus according to the embodiment of the present application is described with reference to fig. 1.
Among them, the robot 100 may include: processor 110, memory 120, WIFI receiver 130.
It should be noted that the components and configuration of the robot 100 shown in fig. 1 are exemplary only, and not limiting, and that the robot 100 may have other components and configurations as desired.
Processor 110, memory 120, WIFI receiver 130, and other components that may be present in robot 100 are electrically connected to each other, directly or indirectly, to enable the transmission or interaction of data. For example, processor 110, memory 120, WIFI receiver 130, and other components that may be present may be electrically connected to each other via one or more communication buses or signal lines.
The WIFI receiver 130 is configured to collect a WIFI signal transmitted by a WIFI transmitter in an environment, so as to obtain WIFI information corresponding to the WIFI signal, where the WIFI information includes a WIFI identifier and a signal strength indicator (RSSI).
And the WIFI signals transmitted by different WIFI transmitters are preset to correspond to different WIFI identifications. That is, different WIFI receivers 130 receive the same WIFI identifier of the WIFI signal transmitted by the same WIFI transmitter.
Wherein, under the fixed prerequisite in position of certain WIFI transmitter, after it launches the WIFI signal, the RSSI that corresponds with this WIFI signal that WIFI receiver 130 for gathering this WIFI signal obtained in the position of difference is different. Generally, the farther away from the WIFI transmitter, the smaller the RSSI obtained.
The memory 120 is used for storing a program, for example, a program corresponding to an auxiliary positioning method appearing later or an auxiliary positioning device appearing later. Optionally, when the memory 120 stores the auxiliary positioning device, the auxiliary positioning device includes at least one software function module that can be stored in the memory 120 in the form of software or firmware (firmware).
Alternatively, the software function module included in the auxiliary positioning device may also be solidified in an Operating System (OS) of the robot 100.
The processor 110 is adapted to execute executable modules stored in the memory 120, such as software functional modules or computer programs comprised by the auxiliary positioning device. When the processor 110 receives the execution instruction, it may execute the computer program, for example, to perform: the WIFI receiver collects WIFI information transmitted by a plurality of WIFI transmitters in real time, and the WIFI information is used for representing a WIFI identifier of a received WIFI signal and a signal intensity value of the WIFI signal corresponding to the WIFI identifier; when the number of the currently acquired WIFI identifications is determined to be larger than or equal to a number threshold value and an original global positioning mode fails, inputting the currently acquired WIFI information into a pre-trained network model; and determining the position corresponding to the maximum probability value predicted by the network model as the current position of the self.
Of course, the method disclosed in any of the embodiments of the present application can be applied to the processor 110, or implemented by the processor 110.
The following will describe the assisted positioning method provided by the present application.
Referring to fig. 2, an embodiment of the present invention provides an auxiliary positioning method applied to the robot 100. The robot 100 operates in an environment provided with a plurality of WIFI transmitters, and can acquire WIFI information transmitted by each WIFI transmitter in real time through the WIFI receiver 130 provided by the robot.
The steps involved will be described below in conjunction with fig. 2.
Step S110: the WIFI information transmitted by the plurality of WIFI transmitters is collected in real time through the WIFI receiver, and the WIFI information is used for representing the WIFI identification of the received WIFI signal and the signal intensity value of the WIFI signal corresponding to the WIFI identification.
As mentioned above, WIFI receiver 130 may collect WIFI signals transmitted by WIFI transmitters in the environment to obtain WIFI information corresponding to the WIFI signals, where the WIFI information includes a WIFI identifier and an RSSI.
Step S120: and when the number of the currently acquired WIFI identifications is determined to be larger than or equal to a number threshold value and the original global positioning mode fails, inputting the currently acquired WIFI information into a pre-trained network model.
In the embodiment of the present application, a global positioning mode is preset in the robot 100, which is referred to as an original global positioning mode. The original global positioning mode can be a Monte Carlo-based particle filter algorithm, monocular vision-based positioning and other existing global positioning modes.
Because in some special cases (for example, for a particle filter algorithm, when a map corresponding to the robot 100 is large when the robot 100 is active, or for example, for monocular vision positioning, when the similarity of each direction of the map corresponding to the robot 100 when the robot 100 is active is high), the accuracy of the positioning result obtained by the robot 100 may be low due to inherent characteristics of the original global positioning method, so that the reliability of the positioning result obtained by the robot 100 is further low, and finally the global positioning of the robot 100 is wrong.
In the embodiment of the present application, in order to reduce the global positioning error rate of the robot 100, in addition to the original global positioning mode, a global positioning mode based on WIFI is also built in the robot 100, and is used to assist the robot 100 in global positioning when the original global positioning mode has low reliability (i.e., fails).
In the embodiment of the application, the reliability of the original global positioning mode is judged by obtaining the evaluation factor A. Specifically, the robot 100 may obtain a positioning evaluation factor a in real time, where the positioning evaluation factor a is used to represent the reliability of the original global positioning mode. Further, the evaluation threshold a0 is previously stored in the robot 100. After the robot 100 acquires the positioning evaluation factor a in real time, a may be compared with a0, and when it is determined that the positioning evaluation factor a is smaller than the evaluation threshold a0, it is determined that the original global positioning mode is disabled.
It should be noted that the evaluation threshold a0 is configured by the administrator in advance according to the original global positioning method built in the robot 100, and when the original global positioning method is different, the size of the evaluation threshold a0 may also be different accordingly.
In addition, when the original global positioning modes are different, the modes for acquiring the corresponding evaluation factors a are also different. For example, in some embodiments, when the original global positioning mode is a monte carlo-based particle filter algorithm, the variance value of the particle filter algorithm may be obtained in real time, and the variance value is determined as the positioning evaluation factor a. Wherein the variance value is an average of a sum of squares of differences between the calculation result of each particle and an average value of the settlement results of all the particles in the particle filter algorithm. For another example, in some embodiments, when the original global positioning mode is a monte carlo-based particle filter algorithm, the laser matching degree (the matching degree between the laser point position of the optimal robot position calculated by the particle filter algorithm and the obstacle on the actual map) of the result obtained by the particle filter algorithm may be obtained in real time, and the laser matching degree is determined as the positioning evaluation factor a.
After the robot 100 determines that the original global positioning mode is invalid, it may be determined whether to adopt a global positioning mode based on WIFI to determine the current global positioning based on the number B of WIFI identifiers in the currently acquired WIFI information.
In some embodiments, when the robot 100 determines that the number B of WIFI identifications in the currently acquired WIFI information is greater than or equal to the number threshold B0, the currently acquired WIFI information may be input into a pre-trained network model to determine a current global positioning using a global positioning method based on WIFI. The number of the WIFI identifications is guaranteed to avoid insufficient sample data caused by too small number of the WIFI identifications, and further avoid errors caused by insufficient number of the samples.
It is worth pointing out that the pre-trained network model takes WIFI information as input, and takes probability values of the current position of the robot 100 corresponding to each grid on the scene map as output.
Of course, before inputting the currently collected WIFI information into the pre-trained network model, the robot 100 needs to store the network model for subsequent use. The network model may be obtained by training the support vector machine by other third-party devices, or may be obtained by training the support vector machine by the robot 100 itself. The embodiment of the application does not limit who trains the network model.
The process of training the support vector machine to obtain the network model will be described below by taking the robot 100 itself as an example, please refer to fig. 3, and the process may include the following steps.
Step A110: and constructing a scene map according to a map construction algorithm stored in advance and composition data acquired in advance.
Alternatively, a map construction algorithm, such as the open source composition algorithm cartographer, may be stored in advance in the robot 100. Further, the robot 100 may acquire composition data from a laser emitting device, an odometer device, or the like provided on the robot itself, or may directly acquire composition data stored in advance by a manager. The composition data is used to characterize the environmental characteristics of the scene in which the robot 100 is currently operating.
On the basis, the robot 100 may construct a scene map according to composition data and a map construction algorithm. Since the content of this part is the prior art, it is not described herein again.
Step A120: and dividing the scene map into grids with preset sizes, and determining grid identification and coordinate ranges for each grid.
After the scene map is constructed, map parameters corresponding to the scene map can be obtained, for example, the map parameters include a size parameter of the map, a lower left corner coordinate parameter of the map, a resolution of the map, and the like.
After the scene map and the corresponding map parameters are obtained, please refer to fig. 4, the scene map may be divided into grids of a preset size according to the range covered by the scene map and the map parameters, and a unique grid identification ID is determined for each grid. Because the map parameters of the scene map are acquired in advance, the coordinate range of the area where each grid is located can be determined. In fig. 4, (a, b) represents the coordinates of the lower left corner, and (c, d) represents the coordinates of the upper right corner.
The size of each grid may control the positioning accuracy of the robot 100 in global positioning based on WIFI, for example, in some embodiments, the size of the grid is 1m × 1 m.
Step A130: and forming a corresponding mapping relation between the acquired WIFI information and the corresponding grid identification for storage when the WIFI information travels to the coordinate range corresponding to each grid.
After the coordinate range of the area where each grid is located is obtained, the robot 100 may form a corresponding mapping relationship between the acquired WIFI information and the corresponding grid identifier when the robot travels to the coordinate range corresponding to each grid, and store the mapping relationship.
As mentioned above, the WIFI information includes the WIFI identifier of the received WIFI signal and the signal strength value of the WIFI signal corresponding to the WIFI identifier, so that the WIFI information and the corresponding mesh identifier form a corresponding mapping relationship, that is, the mesh identifier-WIFI identifier-RSSI form a mapping relationship.
It is worth pointing out that when the robot 100 travels to a range where a certain mesh is located, multiple WIFI signals may be received at the same time, at this time, the WIFI information collected by the robot 100 includes multiple sets of WIFI identifiers and RSSIs, and each set of WIFI identifier and RSSI corresponds to a different WIFI signal.
For convenience of description, a set of WIFI identification and RSSI is referred to as one sample. Accordingly, when the robot 100 acquires a plurality of samples within a range of a certain grid, each sample forms a mapping relationship with the grid identifier of the grid.
It can be understood that, at this time, the original global positioning mode is in an effective state, the robot 100 performs global positioning on itself in the original global positioning mode to obtain current positioning information, and then compares the current positioning information with the coordinate range of the area where each grid is located, so as to determine which grid range the robot is currently located in, i.e., determine the grid identifier of the grid where the robot is currently located.
Step A140: and when the number of the WIFI identifications included in the WIFI information corresponding to each grid identification is determined to be larger than or equal to the number threshold, inputting the mapping relation into a pre-stored support vector machine for training to obtain a network model which takes the WIFI information as input and the probability value of the grid identification as output.
After the mapping relation of each grid is obtained, if it is judged that the number (i.e., the number of samples) of the WIFI identifiers included in the WIFI information corresponding to each grid identifier is greater than or equal to the number threshold B0, inputting all the mapping relations into a support vector machine for training, and obtaining a network model which takes the WIFI information as input and the probability value of each grid identifier as output.
Of course, there may be a case where the number of WIFI identifiers included in the WIFI information corresponding to some mesh identifiers is smaller than the number threshold B0, that is, the number of samples in some meshes is insufficient. Because the reliability of the trained network model is not high when the samples are insufficient, when the robot 100 determines that the number of the WIFI identifiers included in the WIFI information corresponding to at least one grid identifier is smaller than the number threshold, the WIFI information of the grid is stored, and new WIFI information is repeatedly collected in the grid, so that the samples of the grid can reach the number threshold.
Step S130: and determining the position corresponding to the maximum probability value predicted by the network model as the current position of the self.
As can be seen from the foregoing, the result output by the network model is the probability of the robot 100 in each grid, and then, in some special cases, there may be a case where the probability difference between the maximum probability and the second largest (i.e., the second largest) probability output by the network model is small. In this case, it is described that the probability that the robot 100 is located between the grid corresponding to the maximum probability and the grid corresponding to the second maximum probability is high, and if the position of the grid corresponding to the maximum probability is determined as the current position of the robot 100, the erroneous determination rate increases to some extent.
To solve this problem, in some alternative embodiments, the robot 100 may determine the position corresponding to the maximum probability value as the current position of the robot 100 only when it is determined that the difference between the maximum probability value predicted by the network model and the probability value of the next-highest probability value is greater than a preset probability threshold.
Furthermore, in some alternative embodiments, the location of WIFI transmitters in the environment may move. In order to avoid a positioning error caused by the position movement of the WIFI transmitter, in some embodiments, the robot 100 may update the original mapping relationship according to the currently acquired WIFI information when it is determined that the number of the currently acquired WIFI identifiers is greater than or equal to the number threshold and the original global positioning mode is valid. When the robot 100 determines that the updated mapping relationship is different from the original mapping relationship, it is determined that the position of the WIFI transmitter may be changed, and at this time, the robot 100 may retrain the support vector machine based on the updated mapping relationship and update the network model obtained before with the latest network model obtained after training.
According to the auxiliary positioning method provided by the embodiment of the application, the robot acquires WIFI information transmitted by a plurality of WIFI transmitters in an environment in real time through the WIFI receiver, and the WIFI information is used for representing a WIFI identifier of a received WIFI signal and a signal intensity value of the WIFI signal corresponding to the WIFI identifier; when the robot determines that the number of the currently acquired WIFI identifications is larger than or equal to a number threshold value and an original global positioning mode fails, switching a mode for global positioning, inputting the currently acquired WIFI information into a pre-trained network model, and determining a position corresponding to a maximum probability value predicted by the network model as a current position of the robot. Namely, when the reliability of the original global positioning mode is low, the WIFI is adopted to carry out auxiliary positioning. Because the reliability of the original global positioning mode at the current moment is low, if the original global positioning mode is continuously adopted, the robot positioning error can be caused, and at the moment, the reliability of positioning by adopting the WIFI is higher than that of the original global positioning mode at the current moment, so that the error rate of the robot in the global positioning process can be reduced.
As shown in fig. 5, an auxiliary positioning apparatus 400 is further provided in an embodiment of the present application, where the auxiliary positioning apparatus 400 may include: an acquisition module 410, an input module 420, and a determination module 430.
The acquisition module 410 is configured to acquire, by the WIFI receiver, WIFI information transmitted by the multiple WIFI transmitters in real time, where the WIFI information is used to characterize a WIFI identifier of a received WIFI signal and a signal strength value of a WIFI signal corresponding to the WIFI identifier;
an input module 420, configured to input the currently acquired WIFI information into a pre-trained network model when it is determined that the number of the currently acquired WIFI identifiers is greater than or equal to a number threshold and an original global positioning mode is invalid;
a determining module 430, configured to determine a location corresponding to the maximum probability value predicted by the network model as a current location of itself.
In a possible implementation manner, the apparatus further includes an obtaining module, configured to obtain, in real time, a positioning evaluation factor, where the positioning evaluation factor is used to characterize a reliability of the original global positioning mode; the determining module 430 is further configured to determine that the original global positioning method is invalid when the positioning evaluation factor is smaller than an evaluation threshold.
In a possible implementation manner, the obtaining module is configured to obtain a variance value of the particle filtering algorithm in real time, and determine the variance value as the positioning evaluation factor; or, acquiring the laser matching degree of the particle filter algorithm in real time, and determining the laser matching degree as the positioning evaluation factor.
In a possible implementation manner, the device further comprises a construction module, configured to construct a scene map according to a map construction algorithm stored in advance and composition data acquired in advance; the segmentation module is used for segmenting the scene map into grids with preset sizes and determining grid identification and coordinate ranges for each grid; the storage module is used for forming a corresponding mapping relation between the acquired WIFI information and the corresponding grid identification when the WIFI information advances to the coordinate range corresponding to each grid for storage; and the training module is used for inputting the mapping relation into a pre-stored support vector machine for training when the number of the WIFI identifications included in the WIFI information corresponding to each grid identification is determined to be greater than or equal to the number threshold value, so as to obtain a network model which takes the WIFI information as input and the probability value of the grid identification as output.
In a possible implementation manner, the determining module 430 is further configured to store the WIFI information when it is determined that the number of the WIFI identifiers included in the WIFI information corresponding to at least one grid identifier is smaller than the number threshold, and acquire new WIFI information in a coordinate range corresponding to a grid corresponding to the at least one grid identifier.
In a possible implementation manner, the apparatus further includes an updating module, configured to update the mapping relationship according to the currently acquired WIFI information when it is determined that the number of the currently acquired WIFI identifiers is greater than or equal to the number threshold and an original global positioning manner is valid, and the training module is further configured to retrain the support vector machine based on the updated mapping relationship and update the network model with a latest network model obtained after training when it is determined that the updated mapping relationship is different from the original mapping relationship.
In a possible implementation manner, the determining module 430 is further configured to determine that a difference between the maximum probability value predicted by the network model and the next maximum probability value is greater than a preset probability threshold.
The implementation principle and the resulting technical effect of the auxiliary positioning device 400 provided in the embodiment of the present application are the same as those of the aforementioned method embodiment, and for the sake of brief description, no mention is made in the device embodiment, and reference may be made to the corresponding contents in the aforementioned method embodiment.
In addition, an embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a computer, the steps included in the above-mentioned assisted positioning method are performed.
In summary, according to the auxiliary positioning method, the auxiliary positioning device, the robot and the computer-readable storage medium provided by the embodiments of the present invention, the robot acquires, in real time, WIFI information transmitted by a plurality of WIFI transmitters in an environment through a WIFI receiver, where the WIFI information is used to characterize a WIFI identifier of a received WIFI signal and a signal strength value of the WIFI signal corresponding to the WIFI identifier; when the robot determines that the number of the currently acquired WIFI identifications is larger than or equal to a number threshold value and an original global positioning mode fails, switching a mode for global positioning, inputting the currently acquired WIFI information into a pre-trained network model, and determining a position corresponding to a maximum probability value predicted by the network model as a current position of the robot. Namely, when the reliability of the original global positioning mode is low, the WIFI is adopted to carry out auxiliary positioning. Because the reliability of the original global positioning mode at the current moment is low, if the original global positioning mode is continuously adopted, the robot positioning error can be caused, and at the moment, the reliability of positioning by adopting the WIFI is higher than that of the original global positioning mode at the current moment, so that the error rate of the robot in the global positioning process can be reduced.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a notebook computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application.
Claims (10)
1. An assisted positioning method applied to a robot, wherein the robot runs in an environment provided with a plurality of WIFI transmitters, the robot comprises a WIFI receiver, and the method comprises the following steps:
the WIFI receiver collects WIFI information transmitted by the plurality of WIFI transmitters in real time, and the WIFI information is used for representing a WIFI identifier of the received WIFI signal and a signal intensity value of the WIFI signal corresponding to the WIFI identifier;
when the number of the currently acquired WIFI identifications is determined to be larger than or equal to a number threshold value and an original global positioning mode fails, inputting the currently acquired WIFI information into a pre-trained network model;
and determining the position corresponding to the maximum probability value predicted by the network model as the current position of the self.
2. The method of claim 1, wherein prior to said entering the currently collected WIFI information into a pre-trained network model, the method further comprises:
acquiring a positioning evaluation factor in real time, wherein the positioning evaluation factor is used for representing the credibility of the original global positioning mode;
and when the positioning evaluation factor is smaller than an evaluation threshold value, determining that the original global positioning mode is invalid.
3. The method according to claim 2, wherein when the original global localization mode is a monte carlo-based particle filter algorithm for global localization, the obtaining the localization evaluation factor in real time comprises:
acquiring a variance value of the particle filter algorithm in real time, and determining the variance value as the positioning evaluation factor; alternatively, the first and second electrodes may be,
and acquiring the laser matching degree of the particle filter algorithm in real time, and determining the laser matching degree as the positioning evaluation factor.
4. The method of any one of claims 1-3, wherein prior to said entering the currently collected WIFI information into a pre-trained network model, the method further comprises:
constructing a scene map according to a pre-stored map construction algorithm and pre-acquired composition data;
dividing the scene map into grids with preset sizes, and determining grid identification and coordinate ranges for each grid;
forming a corresponding mapping relation between the WIFI information acquired when the WIFI information travels to the coordinate range corresponding to each grid and the corresponding grid identification for storage;
and when the number of the WIFI identifications included in the WIFI information corresponding to each grid identification is determined to be larger than or equal to the number threshold, inputting the mapping relation into a pre-stored support vector machine for training to obtain a network model which takes the WIFI information as input and the probability value of the grid identification as output.
5. The method of claim 4, wherein prior to said inputting said mapping into a pre-saved support vector machine for training, said method further comprises:
when the number of the WIFI identifications included in the WIFI information corresponding to at least one grid identification is determined to be smaller than the number threshold value, the WIFI information is stored, and new WIFI information is collected in a coordinate range corresponding to the grid corresponding to the at least one grid identification.
6. The method of claim 4, further comprising:
when the number of the currently acquired WIFI identifications is determined to be larger than or equal to the number threshold value and the original global positioning mode is effective, updating the mapping relation according to the currently acquired WIFI information;
and when the difference between the updated mapping relation and the original mapping relation is determined, retraining the support vector machine based on the updated mapping relation, and updating the network model by using the latest network model obtained after training.
7. The method of claim 4, wherein before determining the location corresponding to the maximum probability value predicted by the network model as being itself at the current location, the method further comprises:
and determining that the difference between the maximum probability value predicted by the network model and the second-order probability value is greater than a preset probability threshold.
8. An auxiliary positioning device, applied to a robot operating in an environment provided with a plurality of WIFI transmitters, the robot comprising a WIFI receiver, the device comprising:
the acquisition module is used for acquiring WIFI information transmitted by the plurality of WIFI transmitters in real time through the WIFI receiver, and the WIFI information is used for representing a WIFI identifier of the received WIFI signal and a signal intensity value of the WIFI signal corresponding to the WIFI identifier;
the input module is used for inputting the currently acquired WIFI information into a pre-trained network model when the number of the currently acquired WIFI identifications is determined to be larger than or equal to a number threshold value and an original global positioning mode fails;
and the determining module is used for determining the position corresponding to the maximum probability value predicted by the network model as the current position of the self.
9. A robot, comprising: a memory and a processor, the memory and the processor connected;
the memory is used for storing programs;
the processor calls a program stored in the memory to perform the method of any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored which, when executed by a computer, performs the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010570714.1A CN111458679B (en) | 2020-06-22 | 2020-06-22 | Auxiliary positioning method, device, robot and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010570714.1A CN111458679B (en) | 2020-06-22 | 2020-06-22 | Auxiliary positioning method, device, robot and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111458679A true CN111458679A (en) | 2020-07-28 |
| CN111458679B CN111458679B (en) | 2020-12-04 |
Family
ID=71683916
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010570714.1A Active CN111458679B (en) | 2020-06-22 | 2020-06-22 | Auxiliary positioning method, device, robot and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111458679B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104105196A (en) * | 2013-04-09 | 2014-10-15 | 广东美晨通讯有限公司 | Positioning method and system based on radio frequency fingerprint |
| US20150334677A1 (en) * | 2014-05-16 | 2015-11-19 | Qualcomm Incorporated, Inc. | Leveraging wireless communication traffic opportunistically |
| CN106899991A (en) * | 2017-03-08 | 2017-06-27 | 哈尔滨工业大学深圳研究生院 | Adaptive optimal ad hoc network method based on multirobot and gaussian signal model |
| CN106937377A (en) * | 2015-12-29 | 2017-07-07 | 中国移动通信集团公司 | A kind of method, device and equipment that classification positioning is realized for monitoring objective |
| CN111044974A (en) * | 2020-03-18 | 2020-04-21 | 腾讯科技（深圳）有限公司 | Indoor positioning method and device based on WiFi signal and storage medium |
-
2020
- 2020-06-22 CN CN202010570714.1A patent/CN111458679B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104105196A (en) * | 2013-04-09 | 2014-10-15 | 广东美晨通讯有限公司 | Positioning method and system based on radio frequency fingerprint |
| US20150334677A1 (en) * | 2014-05-16 | 2015-11-19 | Qualcomm Incorporated, Inc. | Leveraging wireless communication traffic opportunistically |
| CN106937377A (en) * | 2015-12-29 | 2017-07-07 | 中国移动通信集团公司 | A kind of method, device and equipment that classification positioning is realized for monitoring objective |
| CN106899991A (en) * | 2017-03-08 | 2017-06-27 | 哈尔滨工业大学深圳研究生院 | Adaptive optimal ad hoc network method based on multirobot and gaussian signal model |
| CN111044974A (en) * | 2020-03-18 | 2020-04-21 | 腾讯科技（深圳）有限公司 | Indoor positioning method and device based on WiFi signal and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111458679B (en) | 2020-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11318952B2 (en) | Feedback for an autonomous vehicle | |
| US11188089B2 (en) | Localization for autonomous vehicles using gaussian mixture models | |
| CN110806215B (en) | Vehicle positioning method, device, equipment and storage medium | |
| CN109443345B (en) | Positioning method and system for monitoring navigation | |
| CN110900602A (en) | Positioning recovery method and device, robot and storage medium | |
| CN115617217B (en) | Vehicle state display method, device, equipment and readable storage medium | |
| CN112445222A (en) | Navigation method, navigation device, storage medium and terminal | |
| CN112817026A (en) | Method, device and equipment for determining pose of moving object and storage medium | |
| CN114547223A (en) | Trajectory prediction method, and trajectory prediction model training method and device | |
| CN112466147A (en) | Multi-sensor-based library position detection method and related device | |
| US11080562B1 (en) | Key point recognition with uncertainty measurement | |
| CN113923775B (en) | Method, device, equipment and storage medium for evaluating quality of positioning information | |
| CN114528941A (en) | Sensor data fusion method and device, electronic equipment and storage medium | |
| JP2019191498A (en) | Map creation device | |
| CN111458679B (en) | Auxiliary positioning method, device, robot and computer readable storage medium | |
| CN113177980A (en) | Target object speed determination method and device for automatic driving and electronic equipment | |
| CN112577500A (en) | Positioning and map construction method and device, robot and computer storage medium | |
| US20230123671A1 (en) | Localization and mapping | |
| US11370415B2 (en) | Systems and methods for adaptive user input boundary support for remote vehicle motion commands | |
| DE102014017179B4 (en) | Method for operating a navigation system of a motor vehicle using an operating gesture | |
| CN113325415A (en) | Fusion method and system for vehicle radar data and camera data | |
| KR101847113B1 (en) | Estimation method and apparatus for information corresponding camera orientation by using image | |
| CN112799418B (en) | Control method, control device, remote control equipment and readable storage medium | |
| Carvalho et al. | Particle swarm localization for mobile robots using a 2D laser sensor | |
| CN117451034B (en) | Autonomous navigation method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Room 201, building 4, courtyard 8, Dongbeiwang West Road, Haidian District, Beijing Patentee after: Beijing Yunji Technology Co.,Ltd. Address before: Room 201, building 4, courtyard 8, Dongbeiwang West Road, Haidian District, Beijing Patentee before: BEIJING YUNJI TECHNOLOGY Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |