Devices and methods for automatically labelling high-accuracy indoor localization and determining location information

Abstract

A device, in a training phase, obtains Channel State Information (CSI) for one or more links between another device and at least one Access Point (AP), and in the training phase, estimates location information of the other device based on at least one geometric localization technique; and generates a database comprising CSI of the one or more links, each CSI being associated with an estimated location information. Further, a device, in a testing phase, obtains a database from another device, wherein the database comprises CSI of one or more links, each CSI being associated with an estimated location information, and in the testing phase, the device estimates CSI for one or more links between the device and at least one AP, and determine location information based on the estimated CSI of the one or more links and the database.

Claims

1. A server device, comprising: at least one processor; and a non-transitory computer readable storage medium storing a program that is executable by the at least one processor, the program comprising instructions to: in a training phase, obtain one or more samples of Channel State Information (CSI) for one or more links between another device and at least one Access Point (AP); obtain one or more estimates of location information of the another device based on at least one geometric localization technique, each estimate of location information corresponding to at least one sample of the one or more samples of CSI for the one or more links between the another device and the at least one AP; in the training phase, determine an accuracy parameter for each estimate of location information based on a predefined parameter; generate a database comprising the one or more samples of CSI of the one or more links, each sample of CSI being associated with at least one estimate of the one or more estimates of location information; and in the training phase, when a respective accuracy parameter is above a threshold value, update the generated database using the respective accurate parameter.

2. The server device according to claim 1, wherein the predefined parameter is one or more of: a predefined number of available channels; a high signal to noise ratio on a specific link between the another device and an AP of the at least one AP; or the another device comprising an alternative localization sensor operating in an target condition.

3. The server device according to claim 2, wherein the alternative localization sensor is based on one or more of: a Global Positioning System (GPS) sensor; or an indoor or outdoor visibility sensor.

4. The server device according to claim 1, wherein the program further comprises instructions to: in the training phase, when the respective accuracy parameter is above the threshold value, update the generated database using the respective accurate parameter at a specific time or at predetermined time intervals.

5. The server device according to claim 1, wherein the program further comprises instructions to: in the training phase, train a fingerprint technique based on the generated database.

6. The server device according to claim 5, wherein: the fingerprint technique is based on a neural network; and the program further comprises instructions to train the neural network based on feeding the neural network with the one or more samples of CSI for the one or more links, each sample of CSI being labeled with the associated at least one estimate of location information according to the database.

7. The server device according to claim 5, wherein the fingerprint technique is based on a deep learning method, and the deep learning method is based on: a linear regression algorithm; or a non-linear regression algorithm; or a nearest neighbor algorithm; or a variational auto-encoder using information bottleneck principle.

8. The server device according to claim 1, wherein the at least one geometric localization technique is based on one or more of: a Direction Of Arrival (DOA) localization technique; a Time Difference Of Arrival (TDOA) localization technique; or a Time Of Arrival (TOA) localization technique.

9. The server device according to claim 1, wherein the program further comprises instructions to: in a testing phase, perform the following: obtain at least one sample of CSI for one or more second links related to the another device; determine a quality parameter for the at least one sample of CSI for the one or more second links; and determine, upon receiving a request for localization, an estimate of location information according to the request, based on the at least one sample of CSI for the one or more second links and the quality parameter.

10. The server device according to claim 9, wherein: when the quality parameter is above a threshold value, the estimate of location information is determined based on using the at least one geometric localization technique; or when the quality parameter is smaller than the threshold value, the estimate of location information is determined based on a trained fingerprinting technique.

11. The server device according to claim 9, wherein the quality parameter for the at least one sample of CSI for the one or more second links is determined based on one or more of: a received signal strength; an average Signal to Interference plus Noise Ratio (SINR) of all subcarriers; a channel capacity; an Effective Exponential SNR Mapping (EESM) with Multiple Input Multiple Output (MIMO) extensions; or a statistical confidence interval.

12. The server device according to claim 1, wherein the one or more samples of CSI for the one or more links are determined based on: estimating a channel for consecutive data packets during a predefined time interval; or determining a series of vectors corresponding to a frequency response experienced by a set of successive data packets of a used wave-form.

13. The server device according to claim 1, wherein the program further comprises instructions to: in the training phase, perform the following: obtain, in parallel, a first estimate of location information of the another device based on the at least one geometric localization technique and a second estimate of location information of the another device based on a trained fingerprint technique; and update the generated database when an accuracy parameter for the second estimate of location information estimated based on the trained fingerprint technique indicates a better accuracy than an accuracy parameter for the first estimate of location information estimated based on the at least one geometric localization technique.

14. A method, comprising: in a training phase, obtaining one or more samples of Channel State Information (CSI) for one or more links between another device and at least one Access Point (AP); obtaining one or more estimates of location information of the another device based on at least one geometric localization technique, each estimate of location information corresponding to at least one sample of the one or more samples of CSI for the one or more links between the another device and the at least one AP; in the training phase, determining an accuracy parameter for each estimate of location information based on a predefined parameter; generating a database comprising the one or more samples of CSI of the one or more links, each sample of CSI being associated with at least one estimate of the one or more estimates of location information; and in the training phase, when a respective accuracy parameter is above a threshold value, update the generated database using the respective accurate parameter.

15. A device, comprising: at least one processor; and a non-transitory computer readable storage medium storing a program that is executable by the at least one processor, the program comprising instructions to: in a testing phase, obtain a database from another device, wherein the database comprises one or more samples of Channel State Information (CSI) of one or more links, each sample of CSI being associated with at least one estimate of one or more estimates of location information; estimate CSI samples for one or more links between the device and at least one Access Point (AP); determine a quality parameter for the estimated CSI samples; and determine a method of determining location information based on the estimated CSI samples of the one or more links, and the quality parameter of the estimated CSI samples.

16. The device according to claim 15, wherein the program further includes instructions to: in the testing phase, obtain a trained fingerprint technique from the another device; and wherein the one or more estimates of location information are determined based on the trained fingerprinting technique.

17. A method, comprising: in a testing phase, obtaining a database from another device, wherein the database comprises one or more samples of channel state information (CSI) of one or more links, each sample of CSI being associated with at least one estimate of one or more estimates of location information; estimating CSI samples for one or more links between a device and at least one Access Point (AP); determining a quality parameter for the estimated CSI samples; and determining a method of determining location information based on the estimated CSI samples of the one or more links, and the quality parameter of the estimated CSI samples.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

(1) The above described aspects and implementation forms of the present invention will be explained in the following description of specific embodiments in relation to the enclosed drawings, in which

(2) FIG. 1 schematically illustrates a device, particularly a server device for generating a database in a training phase, according to an embodiment of the invention.

(3) FIG. 2 schematically illustrates a device, particularly a mobile device for determining location information in a testing phase, according to an embodiment of the invention.

(4) FIG. 3 is a schematic view of the mobile device including a localization service in a radio access network, according to an embodiment of the invention.

(5) FIGS. 4a and 4b are schematic views of examples of processing methods in an off-line phase (FIG. 4a) and an online phase (FIG. 4b), according to an embodiment of the invention.

(6) FIG. 5 is a schematic view of channel state information processing.

(7) FIG. 6 is a schematic view of channel state information processing in a training mode.

(8) FIG. 7 is a flowchart of a method for a device particularly server device, according to an embodiment of the invention.

(9) FIG. 8 is a flowchart of a method for a device particularly mobile device, according to an embodiment of the invention.

DETAILED DESCRIPTION OF ILLUSTRATIVE EMBODIMENTS

(10) FIG. 1 schematically illustrates a device 100, particularly a server device, for generating a database 101 in a training phase, according to an embodiment of the invention.

(11) The device 100 may be, for example, a server device, configured to, in the training phase, obtain CSI 102, 103, for one or more links 121, 131 between another device 110 and at least one AP 120, 130.

(12) The device 100 is further configured to, in the training phase, estimate location information 112, 113 of the other device 110, particularly of a mobile device, based on at least one geometric localization technique.

(13) The device 100 is further configured to, in the training phase, generate a database 101 comprising CSI 102, 103 of the one or more links 121, 131, each CSI 102, 103 being associated with an estimated location information 112, 113.

(14) The device 100 may comprise a circuitry (not shown in FIG. 1). The circuitry may comprise hardware and software. The hardware may comprise analog or digital circuitry, or both analog and digital circuitry. In some embodiments, the circuitry comprises one or more processors and a non-volatile memory connected to the one or more processors. The non-volatile memory may carry executable program code which, when executed by the one or more processors, causes the device to perform the operations or methods described herein.

(15) FIG. 2 schematically illustrates a device 110, particularly a mobile device, for determining location information 112, 113 in a testing phase, according to an embodiment of the invention.

(16) The device 110 may be, for example, a mobile device, configured to, in the testing phase, obtain a database 101 from another device 100, wherein the database 101 comprises CSI 102, 103 of one or more links 121, 131, each CSI 102, 103 being associated with an estimated location information 112, 113.

(17) The device 110 is further configured to, in the testing phase, estimate CSI 102, 103 for one or more links 121, 131 between the device 110 and at least one Access Point (AP) 120, 130.

(18) The device 110 is further configured to, in the testing phase, determine location information 112, 113 based on the estimated CSI 102, 103 of the one or more links 121, 131 and the database 101.

(19) The device 110 may comprise a circuitry (not shown in FIG. 2). The circuitry may comprise hardware and software. The hardware may comprise analog or digital circuitry, or both analog and digital circuitry. In some embodiments, the circuitry comprises one or more processors and a non-volatile memory connected to the one or more processors. The non-volatile memory may carry executable program code which, when executed by the one or more processors, causes the device to perform the operations or methods described herein.

(20) FIG. 3 shows a schematic view of a mobile device 110 including a localization service in a radio access network, according to an embodiment of the invention. In the embodiment of FIG. 3, the device 110 is connected to a server device 100 in a wireless network, and the server device 100 is capable of providing a wireless data service.

(21) The server device 100 further has a localization service 301 and an application 302, which may be accessed by the mobile device 110. The server device 100 is connected to the wireless access network and may get the channel state information 102, 103 of the links 121, 131 between the mobile device 110 and each access point (AP) 120, 130, separately.

(22) The channel state information 102, 103 (e.g., in FIG. 3 is denoted CSI.sub.i for the i.sup.th) AP 120, 130 may include a channel estimate collected for consecutive packets during a predefined duration T. Moreover, with the OFDM(A) wave-forms, a CSI may be obtained based on a series of vectors corresponding to the frequency response experienced by a set of successive packets.

(23) FIG. 4a and FIG. 4b show schematic views of examples of processing methods 400A and 400B in an off-line phase (FIG. 4a) and in an online phase (FIG. 4b), respectively, according to an embodiment of the invention.

(24) The architecture is organized around two phases according to FIG. 4a and FIG. 4b. In FIG. 4a during an offline phase where labelled CSI are collected, and in FIG. 4b in an online phase where a fingerprinting technique, here exemplarily a neural network, is trained with the aforementioned labelled data is inferring location information based on the CSI.

(25) Moreover, when the traffic load is low, the network may run in a learning mode. In this case, CSI is collected from one or more mobile devices over several channels, regardless of whether they ask for a localization service or not. The network may employ resource allocation strategies that favour wide channels and trigger, when possible, a channel hopping scheme.

(26) With reference to FIG. 4a, the following steps may be performed, for example, by the device 100, which may be the server device, and/or by the device no, which may be the mobile device. Without limiting the present disclosure, in the following the method 400A is discussed based on being performed by the device 100, and the method 400B is discussed based on being performed by the device no.

(27) At 401a, the device 100 obtains CSI for different channels 121, 131.

(28) At 402a, the device 100 performs the CSI post-processing, for example, in order to determine, if the CSI have a good quality. Moreover, when it is determined No the device goes to step 403a, however, when it is determined Yes, the device goes to step 404a.

(29) At step 403a, the device 100 determines that the frequency hopping is finished.

(30) At step 404a, the device 100 performs a bandwidth concatenation, and it may provide the results to the training unit (e.g., the device may go to step 407a).

(31) At step 405a, the device 100 runs a time of arrival technique, in order to determine location information.

(32) At step 406a, the device 100 determines location information.

(33) At step 407a, the device 100 trains a fingerprint technique.

(34) At step 408a, the device 100 obtains a trained model.

(35) Moreover, the quality of each set of CSIs related to each device no may be evaluated. An example of a channel quality assessment procedure may be obtained based on various metrics that can be employed, separately or jointly, in order to assess the quality of the CSI. For example, the following metrics may be used: Received Signal Strength (obtained from the WiFi card), Average power over all subcarriers, 1/N .sub.k=1.sup.N|h.sub.k|.sup.2, where N is the number of subcarriers Channel capacity, e.g. according to .sub.k log.sub.2(1+.sup.2/|h.sub.k|.sup.2), where .sup.2 is the variance of the noise, Effective Exponential SNR Mapping (EESM) with multiple input multiple output extensions.

(36) Furthermore, the good quality CSIs may be employed to perform geometrical localization.

(37) Moreover, the method 400B may be performed by the device 110.

(38) At 401b, the device 110 obtains CSI for different communication channels 121, 131.

(39) At 402b, the device no performs the CSI post processing.

(40) At 403b, the device 110 uses the trained model.

(41) At 404b, the device no determines the location information.

(42) The obtained location information, along with the set of CSIs, are then sent to, e.g., a neural network as a training labelled data, according to the flowchart illustrated in FIG. 6. Moreover, when the network runs in normal mode, the localization requests may be treated according to the flowchart illustrated in FIG. 5.

(43) FIG. 5 is a schematic view of CSI processing.

(44) In the procedure 500 of FIG. 5, the following steps may be performed, for example, by the device 100 being the server device and/or by the device no being the mobile device. Without limiting the present disclosure, in the following the procedure 500 is discussed based on being performed by the device 100.

(45) At step 501, the device 100 performs the CSI quality assessment (determining accuracy parameter). Moreover, when it is determined that the CSI has a moderate or bad quality, the device 100 goes to step 502, in which the location is inferred using the pre-trained neural network. However, when it is determined that the CSI has a good quality, the device goes to step 503 where a geometrical localization technique is employed.

(46) Moreover, at step 504 the CSI is fed to the training set for late update of the neural network.

(47) For instance, when the set of collected CSIs has a good quality, at step 503, the localization service employs one or more geometrical techniques to localize the mobile device 100. When a request for localization is received, the localization service employs an interpolation scheme using the trained neural network to localize the mobile device no based on its set of CSIs.

(48) FIG. 6 shows a schematic view of CSI processing in a training mode.

(49) In the procedure 600 of FIG. 6, the following steps may be performed, for example, by the device 100 being the server device and/or by the device no being the mobile device. Without limiting the present disclosure, in the following the procedure 600 is discussed based on being performed by the device 100.

(50) At step 601, the device 100 determines if alternative or a geometric method is available. Moreover, when it determined Yes, the device goes to step 602, however, when it is determined No, the device 100 goes to step 603.

(51) At step 603, the device 100 trains the model (e.g., the fingerprint technique). Moreover, the trained model may further be used for determining a location information.

(52) At step 603, the device 100 uses the labeled data set in the database 101. Moreover, it may provide the labelled data set to the model to be trained.

(53) FIG. 7 shows a method 700 according to an embodiment of the invention for a device 100, particularly server device. The method 700 comprises, in a training phase, performing the following steps. The method 700 may be carried out by the device 100, as it described above.

(54) The method 700 comprises a step 701 of determining CSI 102, 103, for one or more links 121, 131 between another device 110 and at least one AP 120, 130.

(55) The method 700 further comprises a step 702 of estimating location information 112, 113 of the other device 110, particularly mobile device, based on at least one geometric localization technique.

(56) The method 700 further comprises a step 703 of generating a database 101 comprising CSI 102, 103 of the one or more links 121, 131, each CSI 102, 103 being associated with an estimated location information 112, 113.

(57) FIG. 8 shows a method 800 according to an embodiment of the invention for a device 110, particularly a mobile device, the method 800 comprising, in a testing phase, performing the following steps.

(58) The method 800 may be carried out by the device 110, as it described above.

(59) The method 800 comprises a step 801 of obtaining a database 101 from another device 100, wherein the database 101 comprises CSI 102, 103 of one or more links 121, 131, each CSI 102, 103 being associated with an estimated location information 112, 113.

(60) The method 800 further comprises a step 802 of estimating CSI 102, 103 for one or more links 121, 131 between the device 110 and at least one AP 120, 130.

(61) The method 800 further comprises a step 803 of determining location information 112, 113 based on the estimated CSI 102, 103 of the one or more links 121, 131 and the database 101.

(62) The present invention has been described in conjunction with various embodiments as examples as well as implementations. However, other variations can be understood and effected by those persons skilled in the art and practicing the claimed invention, from the studies of the drawings, this disclosure and the independent claims. In the claims as well as in the description the word comprising does not exclude other elements or steps and the indefinite article a or an does not exclude a plurality. A single element or other unit may fulfill the functions of several entities or items recited in the claims. The mere fact that certain measures are recited in the mutual different dependent claims does not indicate that a combination of these measures cannot be used in an advantageous implementation.