Signaling and reporting for UE-side ML displacement positioning
Aspects presented herein may enable a UE or a location server to estimate the displacement of the UE based on measuring wireless signals, such that the UE may perform accurate displacement estimation accurately without using sensors (e.g., IMUs). In one aspect, a UE receives, from a network entity, a request to report information associated with ML-based displacement positioning. The UE transmits, for the network entity based on the request, the information associated with the ML-based displacement positioning. The UE receives, from the network entity based on the information, a configuration for the ML-based displacement positioning. The UE receives, from at least one network node based on the configuration, a set of RSs associated with the ML-based displacement positioning.
1 . An apparatus for wireless communication at a user equipment (UE), comprising:
at least one memory; and
at least one processor coupled to the at least one memory and, the at least one processor is configured to:
receive, from a network entity, a request to report information associated with machine learning (ML)-based displacement positioning, wherein the ML-based displacement positioning comprises estimating a displacement of the UE between at least two points in time using at least one ML model based on an aggregation or composition of radio frequency fingerprint (RFFP) measurements of reference signals (RSs) received at the UE at the at least two points in time;
transmit, for the network entity based on the request, the information associated with the ML-based displacement positioning;
receive, from the network entity based on the information, a configuration for the ML-based displacement positioning; and
receive, from at least one network node based on the configuration, a set of RSs associated with the ML-based displacement positioning.
2 . The apparatus of claim 1 , wherein the ML-based displacement positioning is UE-assisted displacement positioning initiated by the network entity, and wherein the at least one processor is further configured to:
derive a set of RFFP measurements based on the set of RSs; and
transmit, for the network entity, the set of displacement RFFP measurements.
3 . The apparatus of claim 2 , wherein the information includes a capability of the UE to assist the ML-based displacement positioning and a list of displacement RFFPs that is able to be used for the ML-based displacement positioning at the network entity.
4 . The apparatus of claim 2 , wherein a displacement RFFP measurement in the set of displacement RFFP measurements corresponds to the composition of a first measurement of a first RS transmitted from at least one transmission reception point (TRP) when the UE is at a first location, and a second RFFP measurement in the set of displacement RFFP measurements corresponds to a second measurement of a second RS transmitted from the at least one TRP when the UE is at a second location.
5 . The apparatus of claim 1 , wherein the ML-based displacement positioning is performed by the UE, and wherein the at least one processor is further configured to:
estimate the displacement of the UE based on the set of RSs using an ML model; and
transmit, for the network entity, the estimated displacement of the UE.
6 . The apparatus of claim 5 , wherein the information associated with the ML-based displacement positioning includes a capability of the UE to perform the ML-based displacement positioning.
7 . The apparatus of claim 5 , wherein the information associated with the ML-based displacement positioning includes:
a bandwidth capability of the UE,
a buffering capability of the UE to observe multiple RS resources,
one or more supported displacement RFFP types the UE is configured to construct and report to the network entity,
a measurement gap specification, or
a combination thereof.
8 . The apparatus of claim 5 , wherein the estimated displacement of the UE includes soft-information of the estimated displacement.
9 . The apparatus of claim 5 , wherein to estimate the displacement of the UE based on the set of RSs using the ML model, the at least one processor is configured to:
transmit, based on the set of RSs, a set of displacement RFFP measurements for the ML model, wherein a first displacement RFFP measurement in the set of displacement RFFP measurements corresponds to a first measurement of a first RS transmitted from at least one transmission reception point (TRP) when the UE is at a first location, and a second displacement RFFP measurement in the set of displacement RFFP measurements corresponds to a second measurement of a second RS transmitted from the at least one TRP when the UE is at a second location; and
receive, from the ML model, the displacement of the UE based on the set of displacement RFFP measurements.
10 . The apparatus of claim 1 , wherein the at least one processor is configured to receive the ML-based displacement positioning in assistance data, and wherein the assistance data includes:
a time granularity for the set of RSs,
a periodicity of reporting the displacement of the UE or a set of displacement RFFP measurements,
a capability of the UE to adapt the time granularity for the set of RSs based on a speed of the UE, or
a combination thereof.
11 . The apparatus of claim 1 , wherein the at least one processor is further configured to:
estimate the displacement of the UE using at least one sensor; and
transmit, for the network entity, the estimated displacement of the UE.
12 . The apparatus of claim 1 , wherein the ML-based displacement positioning is performed by the UE, and wherein the at least one processor is further configured to:
estimate a first displacement of the UE based on the set of RSs using an ML model;
estimate a second displacement of the UE using a sensor;
fuse the first displacement and the second displacement to obtain a fused displacement; and
transmit the fused displacement for the network entity.
13 . The apparatus of claim 1 , wherein the set of RSs includes:
one or more positioning reference signals (PRSs),
one or more channel state information reference signals (CSI-RSs),
one or more synchronization signal blocks (SSBs), or
a combination thereof.
14 . The apparatus of claim 1 , wherein to receive the set of RSs associated with the ML-based displacement positioning based on the configuration, the at least one processor is configured to:
receive a first subset of RSs in the set of RSs from a first set of transmission reception points (TRPs) when the UE is at a first location; and
receive a second subset of RSs in the set of RSs from a second set of TRPs when the UE is at a second location.
15 . The apparatus of claim 14 , where the first set of TRPs and the second set of TRPs include at least one same TRP.
16 . The apparatus of claim 1 , wherein the at least one processor is further configured to:
train an ML model to perform the ML-based displacement positioning based on displacement RFFP measurements.
17 . The apparatus of claim 16 , wherein the at least one processor is further configured to:
record second information from at least one sensor during reception of the set of RSs, wherein the ML model is further trained based on the second information.
18 . The apparatus of claim 1 , wherein the at least one processor is further configured to:
derive a set of displacement RFFP measurements based on the set of RSs, wherein the set of RFFP measurements corresponds to a composition of multiple measurements including:
a channel impulse response (CIR) measurement,
a channel frequency response (CFR) measurement,
a reference signal received quality (RSRQ) measurement,
a reference signal received power (RSRP) measurement,
a delay spread measurement,
an angle spread measurement,
an angle of arrival (AoA) measurement,
an angle of departure (AoD) measurement,
a Doppler spread measurement, or
a combination thereof.
19 . A method of wireless communication at a user equipment (UE), comprising:
receiving, from a network entity, a request to report information associated with machine learning (ML)-based displacement positioning, wherein the ML-based displacement positioning comprises estimating a displacement of the UE between at least two points in time using at least one ML model based on an aggregation or composition of radio frequency fingerprint (RFFP) measurements of reference signals (RSs) received at the UE at the at least two points in time;
transmitting, for the network entity based on the request, the information associated with the ML-based displacement positioning;
receiving, from the network entity based on the information, a configuration for the ML-based displacement positioning; and
receiving, from at least one network node based on the configuration, a set of RSs associated with the ML-based displacement positioning.