Qualcomm Incorporated

Lorenzo Ferrari

Alexandros Manolakos

Srinivas Yerramalli

Xiaoxia Zhang

Taesang Yoo

Yih-Hao Lin

Rajat Prakash

Sony Akkarakaran

Jing X Sun

Marwen Zorgui

Stephen William Edge

Sven Fischer

Jingchao Bao

Akash Sandeep Doshi

Alberto Rico Alvarino

Aleksandar Damnjanovic

Joseph Binamira Soriaga

Le Liu

Yisheng Xue

Raghu Narayan Challa

Siddhartha Mallik

Danlu Zhang

Mihir Vijay Laghate

Max Welling

Arash Behboodi

Farhad Ghazvinian Zanjani

Ryan Michael Carey

Lindsey Makana Kostas

Yuan Gao

Rana Ali Amjad

In an embodiment, a serving BS of a UE may transmit a PDCCH communication to the UE. The PDCCH communication triggers a partial RACH procedure, whereby a RACH transmission is performed. In some designs, the RACH transmission is for positioning, and positioning measurements are performed at the serving BS and (optionally) at one or more non-serving BSs. In some designs, measurement data based on the positioning measurements are conveyed to a position estimation entity (e.g., LMF), which performs a positioning estimate of the UE.

Partial random access channel procedure

Disclosed are techniques for wireless communication. In an aspect, a user equipment (UE) receives one or more positioning reference signals from a first transmission-reception point (TRP) involved in a positioning session with the UE, detects whether or not there is a positioning bias event associated with the first TRP based on one or more parameters related to the one or more positioning reference signals, the positioning bias event affecting an accuracy of a location estimate of the UE, and transmits, in response to the detection that there is a positioning bias event, a report of the positioning bias event to a network node. Upon receiving the report, the network node performs one or more corrective actions to address the positioning bias event.

User equipment signaling to support bias detection

A method of training an artificial neural network (ANN), receives, from a base station, signal information for a radio frequency signal between the base station and a user equipment (UE). The artificial neural network is trained to determine a location of the UE and to map the environment based on the received signal information and in the absence of labeled data.

Unsupervised learning for simultaneous localization and mapping in deep neural networks using channel state information

Position determination of a user equipment (UE) is supported using channel measurements obtained for Wireless Access Points (WAPs), wherein the channel measurements are for Line of Sight (LOS) and Non-LOS (NLOS) signals. Based on WAP almanac information and the channel measurements, channel parameters indicative of positions of signal sources relative to a first position of a UE may be determined. Using the first position of the UE and an association of the signal sources with corresponding channel parameters, a second position of the UE may be determined. The position of the UE may be a probability density function. Additionally, position information for signal sources may be determined, such as a probability density function, as well as signal blockage probability and an antenna geometry and the WAP almanac information may be updated accordingly.

Systems and methods for positioning with channel measurements

Methods, systems, and devices for wireless communications are described. A user equipment (UE) may be configured with a set of parameters to determine a valid timing advance (TA) to transmit data using preconfigured uplink resources (PUR) during an idle or inactive mode. In some cases, the parameters are one or more TA commands and one or more conditions associated with each TA command. The UE may identify the current condition of the UE and determine whether the current condition of the UE matches one of indicated conditions. The UE may select a TA command based on finding a match and use the TA command to transmit an uplink PUR transmission. Additionally or alternatively, the parameters may be neural network parameters that indicate a neural network model that the UE may use to determine a TA command associated with a valid TA based on the current condition of the UE.

Timing advance command implementations for preconfigured uplink resource transmissions

A user equipment (UE) transmits reference signals for positioning while in Idle or Inactive state. While in a connected state, the UE is pre-configured with Sounding Reference Signal (SRS) resource configuration including at least one of timing adjustment (TA) and an uplink (UL) transmission spatial filter. The UE transmits positioning SRS while in Idle or Inactive mode based on the pre-configuration. The TA and UL transmission spatial filter may be updated by a serving base station using control signals or a paging message received by the UE while in in Idle or Inactive mode. The validity of the TA and UL transmission spatial filter may be monitored using expiration timers or a relative position change threshold. The reference signals transmitted may be based on a UE may Physical Random Access Channel (PRACH), which is insensitive to TA changes. A long sequence PRACH may be used for improved positioning accuracy.

Methods and apparatus for supporting positioning in idle or inactive mode

A method of wireless communication performed by a first transmission device incudes receiving a first set of observations from a first receiving device based on transmissions from the first transmission device to the first receiving device at a previous time slot of a fixed contention-based spectrum sharing system. The first transmission device shares a spectrum with a second transmission device. The method also includes measuring an energy level from an ongoing data transmission of the second transmission device at a current time slot. The method further includes generating, at an artificial neural network of the first transmission device, at least one of a transmission determination, a set of transmission parameters, or a combination thereof, based on a second set of observations, the energy level, and a counter. The method also includes transmitting, to the first receiving device, during the current time slot based on at least one of the transmission determination, the set of transmission parameters, or the combination thereof.

Multi-stage Markov decision process (MDP) model for a spectrum sharing system

A method of wireless communication performed by a first transmission device includes determining a set of spectrum sharing parameters based on sensing performed during a sensing period of a current time slot in a fixed contention based spectrum sharing system. The first transmission device shares a spectrum with a second transmission device. The method also includes determining, at a first artificial neural network of the first transmission device, a transmission device action, and/or a transmission parameter in response to receiving the set of spectrum sharing parameters. The method further includes transmitting, from the first transmission device, to a first receiving device during a data transmission phase of the current time slot based on the transmission device action and/or the transmission parameter.

Spectrum sharing with deep reinforcement learning (RL)

Disclosed are systems, methods, and non-transitory media for providing signaling consideration for wireless positioning with disjoint bandwidth segments. For instance, one or more indications of a preferred bandwidth configuration can be transmitted by a user equipment. Based on the one or more indications, the user equipment can receive a positioning configuration that indicates disjoint bandwidth segments containing a positioning reference signal based on the preferred bandwidth configuration. In response, the user equipment can then determine one or more positioning measurements based on the positioning reference signal in the disjoint bandwidth segments.

Signaling consideration for new radio positioning with disjoint bandwidth segments

Techniques are provide for calibrating device timelines for use in passive positioning of user equipment (UE). An example method for passive positioning of a user equipment includes receiving a first positioning reference signal from a first device at a first time, receiving a second positioning reference signal from a second device at a second time, receiving a timeline difference value associated with the first device and the second device, and determining a time difference of arrival between the first positioning reference signal and the second positioning reference signal based at least in part on the timeline difference value.

Signaling timing offset between stations for user equipment based positioning

Disclosed are techniques for wireless communication. In an aspect, a user equipment (UE) receives a sounding reference signal (SRS) resource configuration, the SRS resource configuration indicating at least a comb pattern for at least one SRS resource allocated to the UE and a puncturing unit for the comb pattern, wherein the comb pattern is divided into one or more puncturing units, wherein each puncturing unit comprises one or more time units of the comb pattern, and wherein each of the one or more time units comprises two or more symbols, and refrains from transmitting all SRS transmissions of the at least one SRS resource within a first puncturing unit of the one or more puncturing units based on a determination that one or more SRS transmissions of the at least one SRS resource within the first puncturing unit are to be dropped.

Puncturing unit for sounding reference signal (SRS) comb patterns with cyclic shifting

Techniques are provide for neural network based positioning of a mobile device. An example method for determining a line of sight delay, an angle of arrival, or an angle of departure value, according to the disclosure includes receiving reference signal information, determining a channel frequency response or a channel impulse response based on the reference signal information, processing the channel frequency response or the channel impulse response with a neural network, and determining the line of sight delay, the angle of arrival, or the angle of departure value based on an output of the neural network.

Neural network based line of sight detection for positioning

Techniques for position estimation using uplink (UL) and downlink (DL) signals via a fully or partially reciprocal wireless channel between a User Equipment (UE) and terrestrial transceiver can be enhanced by leveraging information obtained from UL or DL signals having the stronger Signal-to-Noise Ratio (SNR). This information can include the number of paths and/or complex sinusoids, and can be shared with the base station or location server to parameterize the model of the wireless channel. In some embodiments, the UE can further determine a quality metric for the model and send it to the location server or terrestrial transceiver.

Estimating and reporting of side-information for enhanced reciprocal signaling-based positioning

Aspects of the present disclosure relate to wireless communication systems, and in particular, to techniques for generation and processing of an embedding representing a beam for communication. Certain aspects provide a method for wireless communication by a wireless node. The method generally includes receiving an embedding representing a characterization associated with a beam; providing the embedding to a machine learning (ML) model; generating one or more communication parameters for communication using the beam via the ML model based on the embedding; and communicating using the one or more communication parameters.

Growing community of inventors

Oakland, CA, United States of America

Lorenzo Ferrari