Search

EP-4736341-A1 - POSITIONING METHODS, ARCHITECTURES, APPARATUSES AND SYSTEMS FOR LEARNING-BASED NETWORK-USER EQUIPMENT BEAM ALIGNMENT

EP4736341A1EP 4736341 A1EP4736341 A1EP 4736341A1EP-4736341-A1

Abstract

In an embodiment, a method, implemented in a WTRU to perform beam alignment, comprises: receiving information indicating beam measurements period, and a recursive AIML model, and initial beam alignment parameters; and comprising information indicating configuration on reference signals, RS, resources for beam measurements. Recurrently, during the beam measurement period, the method comprises: determining, by the recursive AIML model, a data-driven sensing vector to adjust WTRU spatial filter parameters based on previous beam alignment parameters and previous beam measurements; and performing beam measurement on RS, to generate current beam alignment parameters. The method comprises determining a combining vector for adjustment of WTRU spatial filter parameter and a network beam forming vector based on the recurrently determined sensing vectors; transmitting, to the network, information indicating the network beamforming vector; and receiving data from the network using the adjusted WTRU spatial filter parameter.

Inventors

  • Tandler, Daniel
  • GAUGER, Marc
  • DORNER, SEBASTIAN
  • TEN BRINK, STEPHAN
  • TAN, AHMET SERDAR
  • MOURAD, ALAIN
  • SHOJAEIFARD, Arman

Assignees

  • InterDigital Patent Holdings, Inc.

Dates

Publication Date
20260506
Application Date
20240626

Claims (20)

  1. CLAIMS 1. A method, implemented in a wireless transmit/receive unit (WTRU), the method comprising: receiving at least a first message comprising information indicating a number of beam measurements, and indicating an Artificial Intelligence and Machine Learning (AIML) model, said at least first message further comprising configuration information for beam measurements on reference signals (RS) resources; determining, based on initial beamforming parameters, one or more first beam measurements on the RS resources; recurrently performing by the AIML model, up to the number of beam measurements: determining, based on previous one or more beam measurements, a sensing vector to adjust one or more beamforming parameters of the WTRU; performing one or more beam measurements on the RS resources using the determined sensing vector; determining, by the AIML model, based on the recurrently determined one or more sensing vectors, a network beamforming vector; and transmitting, to a network, a second message comprising information indicating the network beamforming vector.
  2. 2. The method of claim 1 comprising determining, by the AIML model, based on the recurrently determined one or more sensing vectors, a combining vector for adjustment of the one or more beamforming parameters of the WTRU.
  3. 3. The method of claim 2 comprising: receiving data from the network using the adjusted one or more beamforming parameters.
  4. 4. The method of claim 3, wherein prior receiving data from the network using the adjusted one or more beamforming parameters, the method comprising: receiving, from the network, a new RS resource; determining channel measurements on the new RS resource; and transmitting to the network, a channel state information report comprising the determined channel measurements.
  5. 5. The method of any of the claims 2 to 4, wherein the adjustment of the one or more beamforming parameters of the WTRU is a final adjustment.
  6. 6. The method of any of the preceding claims, wherein the one or more beamforming parameters comprises one or more WTRU spatial filter parameters.
  7. 7. The method of any of the preceding claims, wherein the information indicating configuration on reference signals (RS) resources for beam measurements is received via downlink control information or radio resource control signaling.
  8. 8. The method of any of the preceding claims, wherein the indication of the number of beam measurements comprises a number of sensing steps.
  9. 9. The method of any of the preceding claims, wherein the indication of the number of beam measurements comprises a sensing window.
  10. 10. The method of any of the preceding claims, wherein performing beam measurements on the RS resources comprises any of determining L1-RSRP, SINR, and network beam index.
  11. 11. The method of any of the preceding claims, wherein beam measurements are omitted in case of beam measurements are below a threshold value.
  12. 12. A wireless transmit/receive unit (WTRU) comprising circuitry, including a transmitter, a receiver, a processor and memory, configured to: receive at least a first message comprising information indicating a number of beam measurements, and indicating an Artificial Intelligence and Machine Learning (AIML) model, said at least first message further comprising configuration information for beam measurements on reference signals (RS) resources; determine, based on initial beamforming parameters, one or more first beam measurements on the RS resources; recurrently perform by the AIML model, up to the number of beam measurements: determine, based on previous one or more beam measurements, a sensing vector to adjust one or more beamforming parameters of the WTRU; perform one or more beam measurements on the RS resources using the determined sensing vector; determine, by the AIML model, based on the recurrently determined one or more sensing vectors, a network beamforming vector; and transmit, to a network, a second message comprising information indicating the network beamforming vector.
  13. 13. The WTRU of claim 12 comprising determining, by the AIML model, based on the recurrently determined one or more sensing vectors, a combining vector for adjustment of the one or more beamforming parameters of the WTRU.
  14. 14. The WTRU of claim 13 configured to: receive data from the network using the adjusted one or more beamforming parameters.
  15. 15. The WTRU of claim 14 configured to, prior to receive data from the network using the adjusted one or more beamforming parameters: receive, from the network, a new RS resource; determine channel measurements on the new RS resource; and transmit to the network, a channel state information report comprising the determined channel measurements.
  16. 16. The WTRU of any of the claims 13 to 15, wherein the adjustment of the one or more beamforming parameters of the WTRU is a final adjustment.
  17. 17. The WTRU of any of claims 12 to 16, wherein the one or more beamforming parameters comprises one or more WTRU spatial filter parameters.
  18. 18. The WTRU of any of claims 12 to 17, wherein the information indicating configuration on reference signals (RS) resources for beam measurements is received via downlink control information or radio resource control signaling.
  19. 19. The WTRU of any of claims 12 to 18, wherein the indication of the number of beam measurements comprises a number of sensing steps.
  20. 20. The WTRU of any of claims 12 to 19, wherein the indication of a number of beam measurements comprises a sensing window.

Description

POSITIONING METHODS, ARCHITECTURES, APPARATUSES AND SYSTEMS FOR LEARNING-BASED NETWORK-USER EQUIPMENT BEAM ALIGNMENT CROSS-REFERENCE TO RELATED APPLICATIONS [0001] The present application claims the benefit of EP Patent Application No.23181773.5 filed June 27th, 2023, which is incorporated herein by reference. FIELD OF THE INVENTION [0002] The present disclosure is generally directed to the fields of communications, software and encoding, including, for example, to methods, architectures, apparatuses, systems directed to learning-based user equipment sensing beam alignment. More particularly, the present disclosure relates to methods including configuration, training, inference and feedback aspects on the network and user equipment sensing and beam alignment controllers. BACKGROUND [0003] The need for highly directional transmissions using beamforming techniques to overcome the large pathloss at higher frequencies (such as FR2 and sub-THz/THz) may require systems operating at these frequencies to use large antenna arrays and use highly directive beamforming. The highly directive beamforming requires modifications to legacy initial access techniques to achieve beam alignment with pencil beams. [0004] In 3GPP systems today, codebook-based exhaustive search method for beam alignment is used where network and user equipment sweep all beams repeatedly while user equipment performs beam measurement on reference signal resources to find the best beams with the highest received signal strength, and reporting to the network. For systems with pencil beams, such as FR2 and sub-THz/THz, this technique may cause significant latency. [0005] There is a need to improve methods for beam alignment. SUMMARY [0006] In an embodiment, a method, implemented in a wireless transmit/receive unit, WTRU, to perform beam alignment, may comprise: receiving a first message comprising information indicating beam measurements period, a recursive AIML model, and initial beam alignment parameters; receiving a second message comprising information indicating configuration on reference signals, RS, resources for beam measurements. The method may recurrently comprise during the beam measurement period: determining, by the recursive AIML model, a data-driven sensing vector to adjust WTRU spatial filter parameters based on previous beam alignment parameters; performing beam measurement on RS, to generate current beam alignment parameters. The method may further comprise: determining a combining vector for final adjustment of WTRU spatial filter parameter and a network beam forming vector based on the recurrently determined sensing vectors; transmitting, to the network, a second message comprising information indicating the network beamforming vector; and receiving data from the network using the final adjusted WTRU spatial filter parameter. [0007] In another embodiment, a method, implemented in a wireless transmit/receive unit, WTRU, to perform beam alignment, may comprise receiving a first message comprising information indicating a maximum number of sensing steps, a recursive AIML model, and initial beam alignment parameters; receiving a second message comprising information indicating configuration on reference signals, RS, resources for beam measurements. On condition that a stopping criterion is not satisfied, the method may recurrently comprise: determining, by the recursive AIML model, a data-driven sensing vector to adjust WTRU spatial filter parameters based on previous beam alignment parameters; determining a combining vector and a network beam index based on previous beam alignment parameters; performing beam measurement on RS, to generate current beam alignment parameters; and determining the stopping criterion based on the determined combining vector. The method may further comprise: transmitting, to the network, a second message comprising information indicating the last determined network beam index; adjusting WTRU spatial filter parameters based on the last determined combining vector; and receiving data from the network using the adjusted WTRU spatial filter parameters. [0008] In another embodiment, a method implemented in a wireless transmit/receive unit, WTRU, to perform beam alignment, may comprise a step of receiving at least a first message comprising information indicating a number of beam measurements, and indicating an artificial intelligence and machine learning (AIML) model, said at least first message further comprising configuration information for beam measurements on reference signals (RS) resources. In an alternative, the WTRU may receive a first message comprising information indicating a number of beam measurements, and indicating an Artificial Intelligence and Machine Learning (AIML) model, and the WTRU may receive a second message comprising configuration information for beam measurements on reference signals (RS) resources. The method may comprise a step wherein of determining, based on initial beamforming p