Abstract: In an aspect, a network entity may receive, from a target device, one or more self-radio frequency fingerprint (self-RFFP) measurements obtained by the target device based on reflections of one or more reference signals transmitted by the target device. The wireless device may determine a location of the target device based on applying a machine learning model to the one or more self-RFFP measurements.

Abstract: Disclosed are techniques for UE-based wireless positioning. In an aspect, a user equipment (UE) may acquire, from a first set of transmission/reception entities (TREs), a first set of measurements of signals. The UE may select, from the first set of TREs, a second set of TREs, based on criteria for selecting and/or prioritizing TREs for radio frequency fingerprint (RFFP)-based positioning. The UE may acquire, from the second set of TREs, a second set of measurements, the second set of measurements comprising RFFP measurements. The UE may estimate a position of the UE based on the second set of measurements. In an aspect, the UE may input the second set of measurements into a trained machine learning (ML) model that outputs an estimated position of the UE. In an aspect, the UE receives the selection/prioritization criteria and/or the trained ML model from a network node.

Abstract: Disclosed are techniques for training a position estimation module. In an aspect, a first network entity obtains a plurality of positioning measurements, obtains a plurality of positions of one or more user equipments (UEs), the plurality of positions determined based on the plurality of positioning measurements, stores the plurality of positioning measurements as a plurality of features and the plurality of positions as a plurality of labels corresponding to the plurality of features, and trains the position estimation module with the plurality of features and the plurality of labels to determine a position of a UE from positioning measurements taken by the UE.

Abstract: Aspects described herein relate to adapting one of a parameter for transmitting a signal as a narrow beam in a wireless network or a corresponding threshold based on an operating bandwidth. A node can determine whether a condition is met for narrow beam channel access based on the bandwidth-adjusted (or bandwidth-specific) parameter or threshold.

Abstract: Techniques for line-of-sight (LOS) probability map signaling are disclosed. The techniques can include receiving a positioning signal via a wireless link between the UE and a transmission/reception point (TRP) of a radio access network (RAN), identifying an LOS probability function associated with the wireless link based on LOS probability map information provided by a location management function (LMF) of a core network for the RAN, and generating an LOS probability estimate for the wireless link using the LOS probability function.

Abstract: Disclosed are techniques for training a machine learning model. In an aspect, a user equipment (UE) receives, from a network entity, one or more selection criteria for determining whether the UE is to participate in training the machine learning model, determines whether the UE satisfies the one or more selection criteria during a first period of time, and transmits, to the network entity, after a second period of time, updated parameters for the machine learning model, wherein the machine learning model is updated during the second period of time based on a determination that the UE satisfies the one or more selection criteria.

Abstract: This disclosure provides systems, methods and apparatus, including computer programs encoded on computer storage media, for channel occupancy sharing conditions for beam-based channel access. In some aspects, one or more wireless devices may support a beam-based channel access procedure according to which a first wireless device may share a channel occupancy time (COT) of a second wireless device without performing a listen-before-talk (LBT) procedure if one or more conditions associated with a transmission from the first wireless device are satisfied. Such conditions may be associated with whether a directional beam used by the first wireless device satisfies a narrow beam condition, a time gap between a transmission from the second wireless device and a transmission from the first wireless device, or a duration of a continuous transmission from the first wireless device, or any combination thereof.

Abstract: Disclosed are techniques for wireless communication. In an aspect, a user equipment (UE) may obtain a first set of position estimates of the UE based on applying a first positioning model to one or more radio frequency fingerprint positioning (RFFP) measurements. The UE may obtain a second set of position estimates of the UE using a positioning technique that does not use the first positioning model. The UE may transmit a mismatch report, wherein the mismatch report is based on comparing the first set of position estimates with the second set of position estimates.

Abstract: Methods, systems, and devices for wireless communication are described. Aspects of the disclosure describe narrow beam-based channel access that enables a device to communicate in a shared radio frequency spectrum band without performing channel access procedures. Specifically, aspects of the disclosure describe techniques for defining one or more directional beams as a narrow beam, where the relative narrowness of the beam may be determined in the context of interference (e.g., as opposed to being defined from a geometric perspective). For example, a particular beam may be determined to be a narrow beam, and therefore associated with communications in shared radio frequency spectrum bands without channel access procedures, based on one or more metrics and a number of spatial streams associated with the beam. A device may use such narrow beams for communications without channel access procedures in shared radio frequency spectrum bands.

Abstract: In some implementations, a base device may determine a quali-colocation (QCL) relation between a first wireless reference signal transmitted by a first sidelink (SL) anchor and a second wireless reference signal transmitted by a second SL anchor, wherein: the first SL anchor and the second SL anchor comprise UEs separate from the receiving UE, and the first wireless reference signal and the second wireless reference signal are transmitted for positioning of the receiving UE, performing radio frequency (RF) sensing, or both. The base device may wirelessly send, from the base device to the receiving UE, the mSL-QCL information, wherein the mSL-QCL information is indicative of the QCL relation between the first wireless reference signal and the second wireless reference signal.

Abstract: Methods, systems, and devices for wireless communications are described. The method may include the user equipment (UE) receiving control signaling indicating a set of schemes for reporting an environmental state associated with the UE and measuring one or more channel characteristics according to a scheme of the set of schemes. Moreover, the UE may transmit a report indicating the environmental state associated with the UE based on measuring the one or more channel characteristics. A machine learning model implemented by the UE, a network entity, or both is based on the indicated environmental state associated with the UE.

Abstract: Aspects presented herein may enable an ML module to associate RF fingerprints with beam directions and/or beam features to improve the uniqueness of RF fingerprints. In one aspect, network entity may receive, from one or more wireless devices, a plurality of first RF fingerprints, each of the plurality of first RF fingerprints being associated with at least one directional feature and a location. The network entity may receive a request to determine a position of a UE based on at least one second RF fingerprint associated with the UE or captured by the UE. The network entity may estimate the position of the UE based at least in part on matching the at least one second RF fingerprint to at least one of the plurality of first RF fingerprints.

Abstract: Disclosed are techniques for training a position estimation module. In an aspect, a first network entity obtains a plurality of positioning measurements, obtains a plurality of positions of one or more user equipments (UEs), the plurality of positions determined based on the plurality of positioning measurements, stores the plurality of positioning measurements as a plurality of features and the plurality of positions as a plurality of labels corresponding to the plurality of features, and trains the position estimation module with the plurality of features and the plurality of labels to determine a position of a UE from positioning measurements taken by the UE.

Abstract: Disclosed are techniques for wireless communication. In an aspect, a user equipment (UE) receives one or more positioning assistance data messages for a downlink radio frequency fingerprint (DL-RFFP) positioning procedure from a first network entity, the one or more positioning assistance data messages including at least one parameter related to a machine learning model the UE is configured to use for the DL-RFFP positioning procedure, and transmits one or more location information messages to a second network entity, the one or more location information messages including one or more parameters related to the DL-RFFP positioning procedure.

Abstract: Disclosed are techniques for wireless communication. In an aspect, a user equipment (UE) transmits one or more provide capabilities messages to a location server, the one or more provide capabilities messages indicating at least a first set of capabilities of the UE to engage in a downlink radio frequency fingerprint (DL-RFFP) positioning procedure, and receives one or more positioning assistance data messages for the DL-RFFP positioning procedure from the location server, the one or more positioning assistance data messages based at least on the first set of capabilities.

Abstract: In an aspect, a user equipment (UE) transmits an uplink reference signal for positioning (RS-P) to one or more transmission reception points (TRPs). The TRP(s) or an location management function (LMF) extracts features from one or more uplink radio frequency fingerprint (RFFPs) of the uplink RS-P by one or more network components via one or more network-based machine learning (ML) feature extraction models, and sends the extracted features to the UE for position estimation. Other aspects are directed to UE-based round-trip RFFP position estimation session of a UE. Other aspects are directed to network-based round-trip RFFP position estimation of a UE. The UE-based round-trip RFFP position estimation and the network-based round-trip RFFP position estimation may be based on an uplink RFFP (e.g., SRS) of an uplink reference signal for positioning (RS-P) and a downlink RFFP of a downlink RS-P (e.g.

Abstract: Disclosed are techniques for wireless communication. In an aspect, a network entity receives a provide location information message from a user equipment (UE), the provide location information message including one or more positioning estimates derived by the UE during one or more positioning inference occasions of a machine learning model, wherein the machine learning model is applied to one or more measurements of a wireless channel between the UE and a network node during each of the one or more positioning inference occasions, and transmits a performance report indicating a performance of the machine learning model at least in deriving the one or more positioning estimates during the one or more positioning inference occasions.

Abstract: Disclosed are techniques for wireless positioning. In an aspect, a user equipment (UE) may send, to a network entity, information identifying a capability of the UE to process frequency modulated continuous wave (FMCW) signals. The UE may receive, from a network entity, information identifying a set of transmission / reception points (TRPs) for transmitting FMCW signals for a positioning measurement, the set comprising at least a first TRP and a second TRP. The UE may measure a first FMCW signal that was transmitted by the first TRP to produce a first frequency of arrival. The UE may measure a second FMCW signal that was transmitted by the second TRP to produce a second frequency of arrival. The UE may determine a location of the UE based on a frequency difference between the first frequency of arrival and the second frequency of arrival.

Abstract: In an aspect, a network component (e.g., BS, server, etc.) obtains measurement information associated with uplink signal(s) from UE(s), with the uplink signal(s) having reciprocity with one or more downlink beams of wireless node(s) (e.g., TRP, reference UE, etc.). The network component determines (e.g., generates or refines) a measurement (e.g., RFFP-P) model based on the measurement information. The network component provides the measurement (e.g., RFFP-P) model to a target UE. The target UE receives at least one signal (e.g., PRS) on the one or more downlink beams from the wireless node(s). The target UE processes the at least one signal (e.g., predicts target UE location) based at least in part on the measurement (e.g., RFFP-P) model.

Abstract: Methods and apparatus for predicting wireless measurements based on virtual access points is described. In some embodiments, a location of a user equipment (UE) may be obtained, and given the location of the UE, an output may be generated using a machine learning model, the output including one or more predicted wireless measurements. The output may be indicative of a wireless channel in a multipath environment. In some variants, the machine learning model may have been trained by obtaining a training dataset comprising multipath components data and ground truth locations of a wireless device, and performing an optimization with respect to the multipath components data and the ground truth locations. In some implementations, a training output comprising a predicted multipath component may be produced during the training, and the optimization may include an iterative minimization of an error between at least the predicted multipath component and a labeled multipath component.