ML-based measurements for uplink positioning
Aspects presented herein may enable an LMF to configure AI/ML-based techniques/measurements for a set of base stations/TRPs to improve the performance of UL-based positioning. In one aspect, a network entity transmits a configuration to at least one network node to configure the at least one network node to perform an UL-based positioning measurement with at least one ML model, where each of the at least one ML model is associated with a corresponding ML model ID in which the at least one network node uses for the UL-based positioning measurement, where the UL-based positioning measurement is for a set of SRSs from a UE. The network entity receives the UL-based positioning measurement for the set of SRSs from the at least one network node. The network entity estimates a position of the UE based on the UL-based positioning measurement for the set of SRSs.
1. An apparatus for wireless communication at a network entity, comprising:
a memory; and
at least one processor coupled to the memory and, based at least in part on information stored in the memory, the at least one processor is configured to:
transmit a configuration to at least one network node to configure the at least one network node to perform an uplink (UL)-based positioning measurement with at least one machine learning (ML) model, wherein each of the at least one ML model is associated with a corresponding ML model identification (ID) in which the at least one network node uses for the UL-based positioning measurement, wherein the UL-based positioning measurement is for a set of sounding reference signals (SRSs) from a user equipment (UE);
receive the UL-based positioning measurement for the set of SRSs from the at least one network node; and
estimate a position of the UE based on the UL-based positioning measurement for the set of SRSs.
2. The apparatus of claim 1 , wherein the configuration further configures the at least one network node to perform a feature extraction for the UL-based positioning measurement, wherein the at least one processor is further configured to:
receive a set of feature extractions for the UL-based positioning measurement from the at least one network node; and
combine the set of feature extractions, wherein the position of the UE is estimated further based on the combined set of feature extractions.
3. The apparatus of claim 2 , wherein the set of feature extractions is associated with at least one supported UL-based positioning measurement or at least one updated UL-based positioning measurement.
4. The apparatus of claim 1 , wherein the at least one processor is configured to:
receive an indication from the at least one network node for a capability to support the UL-based positioning measurement with the at least one ML model, wherein the configuration is configured to be transmitted to the at least one network node based on the indication.
5. The apparatus of claim 4 , wherein the at least one processor is configured to receive the indication from the at least one network node separately per positioning technique associated with the UL-based positioning measurement, per bandwidth used for the UL-based positioning measurement, or per ML model ID.
6. The apparatus of claim 1 , wherein the at least one processor is configured to transmit the configuration in a measurement request message, and wherein the corresponding ML model ID for each of the at least one ML model is an information element (IE) of the measurement request message.
7. The apparatus of claim 1 , wherein the UL-based positioning measurement corresponds to a default behavior if the UL-based positioning measurement is not associated with the at least one ML model or the corresponding ML model ID.
8. The apparatus of claim 1 , wherein the UL-based positioning measurement includes:
relative time of arrival (RTOA) measurement,
reception (Rx)-transmission (Tx) (Rx-Tx) time difference measurement,
angle of arrival (AoA) measurement, or
a combination thereof.
9. The apparatus of claim 1 , wherein the configuration includes a list of resources or resource sets associated with the at least one ML model.
10. The apparatus of claim 1 , wherein the configuration includes one or more conditions in which the at least one ML model is to be applied by the at least one network node.
11. The apparatus of claim 10 , wherein the one or more conditions include at least one of:
an availability of a number of available antenna panels,
a match with an area identifier (ID), or
an existence of an antenna panel configuration that supports the at least one ML model.
12. The apparatus of claim 1 , further comprising at least one of a transceiver or an antenna coupled to the at least one processor, wherein the at least one processor is further configured to:
transmit, via at least one of the transceiver or the antenna, the at least one ML model to the at least one network node.
13. The apparatus of claim 1 , wherein the network entity is a location server or a location management function (LMF) and the at least one network node includes a base station, a component of the base station, a transmission reception point (TRP), or a combination thereof.
14. A method of wireless communication at a network entity, comprising:
transmitting a configuration to at least one network node to configure the at least one network node to perform an uplink (UL)-based positioning measurement with at least one machine learning (ML) model, wherein each of the at least one ML model is associated with a corresponding ML model identification (ID) in which the at least one network node uses for the UL-based positioning measurement, wherein the UL-based positioning measurement is for a set of sounding reference signals (SRSs) from a user equipment (UE);
receiving the UL-based positioning measurement for the set of SRSs from the at least one network node; and
estimating a position of the UE based on the UL-based positioning measurement for the set of SRSs.
15. The method of claim 14 , wherein the configuration further configures the at least one network node to perform a feature extraction for the UL-based positioning measurement, the method further comprising:
receiving a set of feature extractions for the UL-based positioning measurement from the at least one network node; and
combining the set of feature extractions, wherein the position of the UE is estimated further based on the combined set of feature extractions.
16. An apparatus for wireless communication at a network node, comprising:
a memory; and
at least one processor coupled to the memory and, based at least in part on information stored in the memory, the at least one processor is configured to:
receive a configuration from a network entity to perform an uplink (UL)-based positioning measurement with at least one machine learning (ML) model, wherein each of the at least one ML model is associated with a corresponding ML model identification (ID) to be used for the UL-based positioning measurement, wherein the UL-based positioning measurement is for a set of sounding reference signals (SRSs) from a user equipment (UE);
perform the UL-based positioning measurement for the set of SRSs from the UE with the at least one ML model; and
transmit the UL-based positioning measurement for the set of SRSs to the network entity.
17. The apparatus of claim 16 , wherein the configuration further configures the network node to perform a feature extraction for the UL-based positioning measurement, wherein the at least one processor is further configured to:
extract at least one feature from the UL-based positioning measurement; and
transmit the at least one feature to the network entity.
18. The apparatus of claim 17 , wherein the feature extraction for the UL-based positioning measurement is associated with at least one supported UL-based positioning measurement or at least one updated UL-based positioning measurement.
19. The apparatus of claim 16 , wherein the at least one processor is further configured to:
transmit an indication to the network entity for a capability to support the UL-based positioning measurement with the at least one ML model, wherein the configuration is configured to be received from the network entity based on the indication.
20. The apparatus of claim 19 , wherein the at least one processor is configured to transmit the indication to the network entity separately per positioning technique associated with the UL-based positioning measurement, per bandwidth used for the UL-based positioning measurement, or per ML model ID.
21. The apparatus of claim 16 , wherein the configuration is configured to be received in a measurement request message, and wherein the corresponding ML model ID for each of the at least one ML model is an information element (IE) of the measurement request message.
22. The apparatus of claim 16 , wherein the at least one processor is further configured to:
perform the UL-based positioning measurement with a default behavior if the UL-based positioning measurement is not associated with the at least one ML model or the corresponding ML model ID.
23. The apparatus of claim 16 , wherein the UL-based measurement includes:
relative time of arrival (RTOA) measurement,
reception (Rx)-transmission (Tx) (Rx-Tx) time difference measurement,
angle of arrival (AoA) measurement, or
a combination thereof.
24. The apparatus of claim 16 , wherein the configuration includes a list of resources or resource sets associated with the at least one ML model.
25. The apparatus of claim 16 , wherein the configuration includes one or more conditions in which the at least one ML model is to be applied by the network node.
26. The apparatus of claim 25 , wherein the one or more conditions include at least one of:
an availability of a number of available antenna panels,
a match with an area identifier (ID), or
an existence of an antenna panel configuration that supports the at least one ML model.
27. The apparatus of claim 16 , further comprising at least one of a transceiver or an antenna coupled to the at least one processor, wherein the at least one processor is further configured to:
receive, via at least one of the transceiver or the antenna, the at least one ML model from the network entity, or from a model repository entity in a core network based on the corresponding ML model ID or a universal ML model ID associated with the at least one ML model.
28. The apparatus of claim 16 , wherein the network node is a base station, a component of the base station, or a transmission reception point (TRP), and the network entity is a location server or a location management function (LMF).
29. A method of wireless communication at a network node, comprising:
receiving a configuration from a network entity to perform an uplink (UL)-based positioning measurement with at least one machine learning (ML) model, wherein each of the at least one ML model is associated with a corresponding ML model identification (ID) to be used for the UL-based positioning measurement, wherein the UL-based positioning measurement is for a set of sounding reference signals (SRSs) from a user equipment (UE);
performing the UL-based positioning measurement for the set of SRSs from the UE with the at least one ML model; and
transmitting the UL-based positioning measurement for the set of SRSs to the network entity.
30. The method of claim 29 , wherein the configuration further configures the network node to perform a feature extraction for the UL-based positioning measurement, the method further comprising:
extracting at least one feature from the UL-based positioning measurement; and
transmitting the at least one feature to the network entity.