WO2025030506A1 - A differenced measurement for ai/ml positioning model input - Google Patents
A differenced measurement for ai/ml positioning model input Download PDFInfo
- Publication number
- WO2025030506A1 WO2025030506A1 PCT/CN2023/112305 CN2023112305W WO2025030506A1 WO 2025030506 A1 WO2025030506 A1 WO 2025030506A1 CN 2023112305 W CN2023112305 W CN 2023112305W WO 2025030506 A1 WO2025030506 A1 WO 2025030506A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- trp
- differenced
- measurement
- pdp
- path timing
- Prior art date
Links
- 238000005259 measurement Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 claims description 15
- 238000004891 communication Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 abstract description 7
- 238000013480 data collection Methods 0.000 abstract description 5
- 238000010801 machine learning Methods 0.000 description 13
- 238000013473 artificial intelligence Methods 0.000 description 11
- LKKMLIBUAXYLOY-UHFFFAOYSA-N 3-Amino-1-methyl-5H-pyrido[4,3-b]indole Chemical compound N1C2=CC=CC=C2C2=C1C=C(N)N=C2C LKKMLIBUAXYLOY-UHFFFAOYSA-N 0.000 description 4
- 102100031413 L-dopachrome tautomerase Human genes 0.000 description 4
- 101710093778 L-dopachrome tautomerase Proteins 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013499 data model Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Definitions
- This present disclosure relates generally to wireless communications, and more specifically, to techniques of positioning a user equipment (UE) with Artificial Intelligence (AI) /Machine Learning (ML) .
- UE user equipment
- AI Artificial Intelligence
- ML Machine Learning
- AI/ML based positioning includes training data collection, model training, model inference and model performance monitoring.
- the model input is directly related to the positioning performance and signaling overhead throughout the model lifecycle management.
- the reporting format of model input data is an important topic in AI/ML positioning.
- Time domain channel impulse responses CIRs
- PDPs power delay profiles
- DPs delay profiles
- CIR contains the information of timing of path delay, power of path, and phase of path.
- PDP contains the information of power and timing delay of path.
- DP is a degenerated version of PDP, where the path power is not provided.
- UE user equipment
- PRU Positioning Reference Unit
- TRP Transmission-Reception Point
- Network will send the reference TRP information to UE/PRU for data collection or model inference.
- CIR, PDP, and DP measurements all include time delays of multiple paths.
- UE reports RSTD (Reference Signal Time Difference) measurements, that is, UE only reports the first path timing difference between the target TRP and the reference TRP.
- RSTD Reference Signal Time Difference
- the one or more aspects comprise the features hereinafter fully described and particularly pointed out in the claims.
- the following description and the annexed figures set forth in detail certain illustrative features of the one or more aspects. These features are indicative, however, of but a few of the various ways in which the principles of various aspects may be employed, and this description is intended to include all such aspects and their equivalents.
- Figure 1 illustrates indoor factory deployment scenario.
- Figure 2 illustrates the high-level process of differenced CIR/PDP/DP measurement.
- Figure 3 illustrates an example of timing of differenced CIR/PDP/DP.
- FIG 1 shows an example of indoor factory deployment scenario.
- TRPs in indoor factory and the location of all TRPs are fixed.
- UEs are random distributed in the factory.
- PRUs as special UEs are deployed in known location for AI/ML training data collection.
- TRP will send positioning reference signal (PRS) to UE/PRU.
- PRS positioning reference signal
- UE/PRU will estimate the channel delay profiles between TRP and UE/PRU based on received PRS.
- CIRs/PDPs/DPs are also three input types for AI/ML positioning model.
- the timing delay of differenced CIR/PDP/DP measurement extends the first path timing difference between the target TRP and reference TRP to the multi-path timing difference relative to the first path delay of the signal from the reference TRP.
- FIG. 2 The process of differenced CIR/PDP/DP measurement is shown in Figure 2.
- Network will send a reference TRP information to UE/PRU and let the UE/PRU know which TRP is the reference TRP.
- Network will also send positioning reference signal (PRS) to UE/PRU.
- PRS positioning reference signal
- UE/PRU will measure CIR/PDP/DP between UE/PRU and reference TRP.
- Figure 3 shows an example of the differenced timing of CIR/PDP/DP with Nt time domain samples.
- the differenced timing of the first path for reference TRP will be obtained by subtracting its own delay, so it is 0.
- the differenced timing of first path of other TRP is obtained by subtracting the first path delay of reference TRP, which is the same as the existing RSTD measurement.
- the timing of other paths will be calculated by taking the difference from the first path delay of the same channel or the channel of reference TRP.
- the first Nt2 delay profile of TRP2 should be shift to the end of the total delay profile.
- the differenced CIR/PDP/DP measurement of other TRPs is calculated based on the reference TRP. After get CIR/PDP/DP of all TRPs, these measurement results can be used as AI/ML model input.
- PRU will report the differenced measurement results to network. Different PRU may have different reference TRP. Training entity will use these training data to train the model.
- UE will also measure the differenced CIR/PDP/DP as model input. If it is UE-based positioning, UE will use these model input and trained model for UE positioning. If it is UE-assisted positioning and AI/ML model is in network side, UE will report the differenced measurement results to network, and network will use the measurement results as model input.
- Combinations such as “at least one of A, B, or C, ” “one or more of A, B, or C, ” “at least one of A, B, and C, ” “one or more of A, B, and C, ” and “A, B, C, or any combination thereof” include any combination of A, B, and/or C, and may include multiples of A, multiples of B, or multiples of C.
- combinations such as “at least one of A, B, or C, ” “one or more of A, B, or C, ” “at least one of A, B, and C, ” “one or more of A, B, and C, ” and “A, B, C, or any combination thereof” may be A only, B only, C only, A and B, A and C, B and C, or A and B and C, where any such combinations may contain one or more member or members of A, B, or C.
Landscapes
- Mobile Radio Communication Systems (AREA)
Abstract
This disclosure describes a differenced CIR/PDP/DP measurement as model input for AI/ML based positioning, which can be seen as an extension of existing RSTD measurement. Specifically, differenced CIR/PDP/DP measurement can be obtained by replacing the timing delay of each TRP measurement with the timing difference between each TRP and the reference TRP measurement, the reference TRP information is provided to the Positioning Reference Unit (PRU) or User Equipment (UE) by the network. The first path timing of differenced CIR/PDP/DP measurement for the reference TRP is zero. During training data collection stage, Network sends a reference TRP information to PRU, PRU will measure CIR/PDP/DP based on the reference TRP timing and report the differenced measurement to network. Additionally, during inference stage, UE will measure CIR/PDP/DP based on reference TRP timing, and the differenced measurement can be directly used as model input for UE-side model or be reported to NW for NW-side model.
Description
This present disclosure relates generally to wireless communications, and more specifically, to techniques of positioning a user equipment (UE) with Artificial Intelligence (AI) /Machine Learning (ML) .
3GPP (The 3rd Generation Partnership Project) approved a study item on AI/ML for positioning accuracy enhancement. AI/ML based positioning includes training data collection, model training, model inference and model performance monitoring. The model input is directly related to the positioning performance and signaling overhead throughout the model lifecycle management. The reporting format of model input data is an important topic in AI/ML positioning.
The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects, and is intended to neither identify key or critical elements of all aspects nor delineate the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later.
Time domain channel impulse responses (CIRs) , power delay profiles (PDPs) and delay profiles (DPs) are model input types for AI/ML positioning. CIR contains the information of timing of path delay, power of path, and phase of path. PDP contains the information of power and timing delay of path. DP is a degenerated version of PDP, where the path power is not provided. UE (user equipment) /PRU (Positioning Reference Unit) will measure CIR/PDP/DP of the channel between UE/PRU and TRP (Transmission-Reception Point) . Network will send the reference TRP information to UE/PRU for data collection or model inference. CIR, PDP, and DP measurements all include time delays of multiple paths. In the existing specification, UE reports RSTD (Reference Signal Time Difference) measurements, that is, UE only reports the first path timing difference between the target TRP and the reference TRP. In this disclosure, we extend the report of first path timing difference to the multi-path timing difference, and in this way the complete timing delay of differenced CIR/PDP/DP can be obtained.
To the accomplishment of the foregoing and related ends, the one or more aspects comprise the features hereinafter fully described and particularly pointed out in the claims. The following description and the annexed figures set forth in detail certain illustrative features of the one or more aspects. These features are indicative, however, of but a few of the various ways in which the principles of various aspects may be employed, and this description is intended to include all such aspects and their equivalents.
Figure 1 illustrates indoor factory deployment scenario.
Figure 2 illustrates the high-level process of differenced CIR/PDP/DP measurement.
Figure 3 illustrates an example of timing of differenced CIR/PDP/DP.
The detailed description set forth below in connection with the appended drawings is intended as a description of various configurations and is not intended to represent the only configurations in which the concepts described herein may be practiced. The detailed description includes specific details for the purpose of providing a thorough understanding of various concepts. However, it will be apparent to those skilled in the art that these concepts may be practiced without these specific details. In some instances, well known structures and components are shown in block diagram form in order to avoid obscuring such concepts.
Several aspects of telecommunication systems will now be presented with reference to various apparatus and methods. These apparatus and methods will be described in the following detailed description and illustrated in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively referred to as “elements” ) . These elements may be implemented using electronic hardware, computer software, or any combination thereof. Whether such elements are implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system.
Figure 1 shows an example of indoor factory deployment scenario. There are some TRPs in indoor factory and the location of all TRPs are fixed. UEs are random distributed in the factory. PRUs as special UEs are deployed in known location for AI/ML training data collection.
For AI/ML based positioning, when AI/ML model is deployed in UE/PRU side, TRP will send positioning reference signal (PRS) to UE/PRU. UE/PRU will estimate the channel delay profiles between TRP and UE/PRU based on received PRS. These measured channel delay profiles are CIRs/PDPs/DPs, which are also three input types for AI/ML positioning model.
Compared with the existing RSTD measurement, the timing delay of differenced CIR/PDP/DP measurement extends the first path timing difference between the target TRP and reference TRP to the multi-path timing difference relative to the first path delay of the signal from the reference TRP.
The process of differenced CIR/PDP/DP measurement is shown in Figure 2. Network will send a reference TRP information to UE/PRU and let the UE/PRU know which TRP is the reference TRP. Network will also send positioning reference signal (PRS) to UE/PRU. UE/PRU will measure CIR/PDP/DP between UE/PRU and reference TRP. Figure 3 shows an example of the differenced timing of CIR/PDP/DP with Nt time domain samples. The differenced timing of the first path for reference TRP will be obtained by subtracting its own delay, so it is 0. The differenced timing of first path of other TRP is obtained by subtracting the first path delay of reference TRP, which is the same as the existing RSTD measurement. The timing of other paths will be calculated by taking the difference from the first path delay of the same channel or the channel of reference TRP.
UE/PRU will also measure CIR/PDP/DP between UE/PRU and other TRPs. For example, if the first path timing delay of TRP1 is later than that of the reference TRP, and the offset between TRP1 and reference TRP is Nt1. Then the timing of the first path delay of TRP1 should be Nt1. The power of first Nt1 time domain samples are zero and the number of time domain samples is still Nt. The time domain samples from t=0 to t=Nt-1 will be CIR/PDP/DP measurement results for TRP1. If the first path delay of TRP2 is early than that of reference TRP, and the offset between TRP2 and reference TRP is Nt2. Then the first Nt2 delay profile of TRP2 should be shift to the end of the total delay profile. The number of time domain samples is still Nt and the shifted time domain samples from t=0 to t=Nt-1 will be CIR/PDP/DP measurement results for TRP2. The differenced CIR/PDP/DP measurement of other TRPs is calculated based on the reference TRP. After get CIR/PDP/DP of all TRPs, these measurement results can be used as AI/ML model input.
During training data collection stage, PRU will report the differenced measurement results to network. Different PRU may have different reference TRP. Training entity will use these training data to train the model.
During test stage, UE will also measure the differenced CIR/PDP/DP as model input. If it is UE-based positioning, UE will use these model input and trained model for UE positioning. If it is UE-assisted positioning and AI/ML model is in network side, UE will report the differenced measurement results to network, and network will use the measurement results as model input.
The previous description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be readily apparent
to those skilled in the art, and the generic principles defined herein may be applied to other aspects. Thus, the claims are not intended to be limited to the aspects shown herein, but is to be accorded the full scope consistent with the language claims, wherein reference to an element in the singular is not intended to mean “one and only one” unless specifically so stated, but rather “one or more. ” The word “exemplary” is used herein to mean “serving as an example, instance, or illustration. ” Any aspect described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other aspects. Unless specifically stated otherwise, the term “some” refers to one or more. Combinations such as “at least one of A, B, or C, ” “one or more of A, B, or C, ” “at least one of A, B, and C, ” “one or more of A, B, and C, ” and “A, B, C, or any combination thereof” include any combination of A, B, and/or C, and may include multiples of A, multiples of B, or multiples of C. Specifically, combinations such as “at least one of A, B, or C, ” “one or more of A, B, or C, ” “at least one of A, B, and C, ” “one or more of A, B, and C, ” and “A, B, C, or any combination thereof” may be A only, B only, C only, A and B, A and C, B and C, or A and B and C, where any such combinations may contain one or more member or members of A, B, or C. All structural and functional equivalents to the elements of the various aspects described throughout this disclosure that are known or later come to be known to those of ordinary skill in the art are expressly incorporated herein by reference and are intended to be encompassed by the claims. Moreover, nothing disclosed herein is intended to be dedicated to the public regardless of whether such disclosure is explicitly recited in the claims. The words “module, ” “mechanism, ” “element, ” “UE, ” and the like may not be a substitute for the word “means. ” As such, no claim element is to be construed as a means plus function unless the element is expressly recited using the phrase “means for. ”
While aspects of the present disclosure have been described in conjunction with the specific embodiments thereof that are proposed as examples, alternatives, modifications, and variations to the examples may be made. Accordingly, embodiments as set forth herein are intended to be illustrative and not limiting. There are changes that may be made without departing from the scope of the claims set forth below.
Claims (9)
- A method of wireless communication of a user equipment (UE) , comprising:receiving the reference TRP information from network;receiving the reference signal for positioning from network;measuring the channel delay profiles between UE and reference TRP;measuring the channel delay profiles between UE and other TRPs;generating the differenced measurement results of all TRPs;reporting the differenced measurement results to network; andinferencing, to get model output based on the differenced measurement results and the trained model.
- The method of claim 1, wherein the channel delay profile can be CIR, PDP, or DP which includes the timing of multi-path.
- The method of claim 1, wherein in the generating the differenced measurement results consists of shifting the received channel delay profiles from all TRPs by a common offset equal to the first path timing of the signal from the reference TRP.
- The method of claim 1, wherein the differenced measurement contains the multi-path timing difference, that is, a first path timing difference and other path timing differences.
- The method of claim 4, wherein the first path timing difference is the same as the existing RSTD measurement.
- The method of claim 4, wherein the first path timing difference for reference TRP is zero.
- The method of claim 4, wherein the other path timing difference can be the difference between other path timing of the signal from a target TRP and the first path timing of the signal from a reference TRP.
- The method of claim 4, wherein the other path timing difference can be the difference between other path timing of the signal from a TRP and the first path timing of the signal from the same TRP.
- The method of claim 1, wherein the UE can be a PRU.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2023/112305 WO2025030506A1 (en) | 2023-08-10 | 2023-08-10 | A differenced measurement for ai/ml positioning model input |
US18/795,123 US20250052878A1 (en) | 2023-08-10 | 2024-08-05 | Method And Apparatus For A Positioning Model Using Relative Time Input In Mobile Communications |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2023/112305 WO2025030506A1 (en) | 2023-08-10 | 2023-08-10 | A differenced measurement for ai/ml positioning model input |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2025030506A1 true WO2025030506A1 (en) | 2025-02-13 |
Family
ID=94533294
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2023/112305 WO2025030506A1 (en) | 2023-08-10 | 2023-08-10 | A differenced measurement for ai/ml positioning model input |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2025030506A1 (en) |
-
2023
- 2023-08-10 WO PCT/CN2023/112305 patent/WO2025030506A1/en unknown
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8340022B2 (en) | Wireless location determination system and method | |
US20220229143A1 (en) | Line of sight detection based on channel impulse response reported | |
US11867826B2 (en) | Position determination system having a deconvolution decoder using a joint SNR-time of arrival approach | |
US20240196361A1 (en) | Method of positioning a node in a cellular network | |
CN101541078A (en) | Method, system and device for estimating TDOA | |
CN114363949B (en) | Abnormal data detection method for UWB positioning system | |
US20240319310A1 (en) | Methods and Apparatuses for Positioning in a Wireless Communications Network | |
KR102416604B1 (en) | Mehtod and device for precise positioning for wireless communication system | |
WO2025030506A1 (en) | A differenced measurement for ai/ml positioning model input | |
US20240097811A1 (en) | Method for identifying and diagnosing failures in pairwise time synchronization and frequency calibration in a mesh network | |
Schmidt et al. | On the effective length of channel impulse responses in UWB single anchor localization | |
US12156052B2 (en) | Method for identifying and diagnosing failures in pairwise time synchronization and frequency calibration in a mesh network | |
Huerta et al. | Mobile tracking using UKF, time measures and LOS-NLOS expert knowledge | |
WO2025025062A1 (en) | A method for ai/ml positioning based on dynamic trp activation | |
Hartmann et al. | Ranging errors in UWB networks and their detectability | |
WO2024197735A1 (en) | Model performance monitor mechanism for ai/ml assisted positioning | |
WO2024145925A1 (en) | Model performance monitor mechanism for ai/ml positioning | |
WO2025020076A1 (en) | Ue capability report for ai/ml positioning | |
WO2025025064A1 (en) | A report format of ai/ml positioning for measurement signalling overhead reduction | |
WO2024148576A1 (en) | Scenario monitor mechanism for ai/ml positioning | |
WO2024065731A1 (en) | Mechanism for integer cycle report based on carrier phase in ofdm systems | |
WO2024092771A1 (en) | Model pool at location management function for direct ai/ml positioning | |
WO2024164116A1 (en) | Auxiliary positioning reference units mechanism for ai/ml positioning | |
Ciurana et al. | Multipath profile discrimination in TOA-based WLAN ranging with link layer frames | |
Giunta et al. | Sensor Failure Detection for TDOA-based Localization Systems |