Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, an application server may receive information associated with reception quality at multiple locations of a physical environment. The application server may provide data for presenting a virtual environment by a UE in the physical environment, the data having one or more parameters based at least in part on a reception quality at a location associated with the UE in the physical environment. Numerous other aspects are described.

Abstract: Methods, systems, and devices for wireless communication are described. A wireless device may identify an aggregation capability to communicate in parallel over a plurality of wireless links. The wireless device may in some cases broadcast this aggregation capability (e.g., periodically). Additionally or alternatively, the wireless device may transmit the aggregation capability in response to a request received from another wireless device. In some cases, the first wireless device may transmit a request to a second wireless device inquiring about aggregation capabilities of the second wireless device. The second wireless device may respond with its aggregation capabilities (e.g., or may broadcast its aggregation capabilities independently of receiving the response). The wireless devices may establish a multi-link session based at least in part on the indicated aggregation capabilities.

Abstract: Methods, systems, and devices for wireless communications are described. A wireless communications entity, such as a user equipment (UE), a base station, a network core, or an application server, may identify a round-trip time (RTT) latency requirement that may pertain to a round-trip latency in wireless communications between the UE and the base station. The wireless communications entity may identify a one one-way directional delay budget that satisfies the RTT latency requirement for an application of an application server. The application server may be in communication with the UE via the base station. The wireless communications entity may modify a value of the one-way directional delay budget and transmit a message that is associated with the modified value of the one one-way directional delay budget.

Abstract: This disclosure provides methods, devices and systems for radio frequency (RF) sensing in wireless communication systems. In some implementations, a transmitting device may transmit a sounding dataset, over a wireless channel, to a receiving device. The sounding dataset may include information carried in one or more training fields configured for channel estimation and sounding control information based, at least in part, on a configuration of the transmitting device. The receiving device may acquire channel state information (CSI) for the wireless channel based on the received sounding dataset and selectively generate a channel report for the wireless channel based, at least in part, on the CSI and the sounding control information. The channel report may indicate changes to the wireless channel which, in turn, may be used to sense objects in the vicinity of the transmitting device or the receiving device.

Abstract: An access point (AP) may prioritize the allocation of uplink resources between multiple basic service sets (BSSs). In some aspects, the AP may select one of a plurality of BSSs, may allocate one or more random-access resource units (RUs) to only the selected BSS, and may transmit, for each of the selected BSSs, a respective frame indicating the random-access RUs allocated to that BSS. Wireless devices belonging to the selected BSS may contend for access to the random-access RUs allocated by the frame, and then transmit uplink data using the random-access RUs.

Abstract: Certain aspects of the present disclosure provide techniques for object positioning using mixture density networks, comprising: receiving radio frequency (RF) signal data collected in a physical space; generating a feature vector encoding the RF signal data by processing the RF signal data using a first neural network; processing the feature vector using a first mixture model to generate a first encoding tensor indicating a set of moving objects in the physical space, a first location tensor indicating a location of each of the moving objects in the physical space, and a first uncertainty tensor indicating uncertainty of the locations of each of the moving objects in the physical space; and outputting at least one location from the first location tensor.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a first device may receive, from a second device, perception information for an environment of the first device based at least in part on a perception capability of the second device. The first device may generate a perception associated with a communication by the first device based at least in part on the perception information from the second device, where the perception indicates characteristics of the environment. The first device may adjust a parameter associated with the communication based at least in part on the perception. Numerous other aspects are described.

Abstract: Disclosed are systems, methods, and non-transitory media for sensing radio frequency signals. For instance, radio frequency data can be received by an apparatus and from at least one wireless device in an environment. Based on the radio frequency data received from the at least one wireless device, the apparatus can determine sensing coverage of the at least one wireless device. The apparatus can further provide the determined sensing coverage and a position of at least one device to a user device.

Abstract: Methods, systems, and devices for wireless communications are described. A station (STA) may receive a null data packet (NDP) on a plurality of subcarriers, and the STA may generate a channel state information (CSI) matrix for each subcarrier of the plurality of subcarriers. After generating a CSI matrix for a subcarrier, such as at least one subcarrier, the STA may scale each value in the CSI matrix using a power-of-two value to minimize complexity. Specifically, instead of scaling each value in the CSI matrix to a value between zero and one using divisions (for example, which may be computationally expensive), the STA may use shifting to scale each value in the CSI matrix. The STA may then quantize the scaled values in the CSI matrix for reporting, and the STA may transmit the quantized, scaled values in the CSI matrix in a CSI report.

Abstract: In some implementations, an initiator device establishes a measurement session with each of a plurality of responder devices based at least in part on their capabilities. The initiator device negotiates, with each of the responder devices, a respective set of one or more sensing parameters based at least in part on the capabilities of the initiator device and the capabilities of the respective responder device, the respective sets of sensing parameters associated with the responder devices being identified by a unique Measurement Setup identifier (ID). The initiator device performs one or more measurement instances with the responder devices based on the respective sets of sensing parameters, each measurement instance identified by a unique Measurement Instance ID and the respective Measurement Setup ID. The initiator device obtains, from each responder device, one or more measurement reports indicating channel state information (CSI) based on the one or more respective measurement instances.

Abstract: In an aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus obtain a signal from a remote wireless node. The apparatus may switch between a first mode and a second mode in response to the signal. The apparatus may sense the shared transmission medium and sense if an absence of traffic is detected. The apparatus may delay data transmission for a fixed time interval from detecting the absence of traffic. The apparatus may initiate the data transmission at the end of the fixed time interval if operating in the first mode or initiate the data transmission at the end of a random time interval following the fixed time interval if operation in the second mode.

Abstract: Certain aspects of the present disclosure provide techniques for training and inferencing with machine learning localization models. In one aspect, a method, includes training a machine learning model based on input data for performing localization of an object in a target space, including: determining parameters of a neural network configured to map samples in an input space based on the input data to samples in an intrinsic space; and determining parameters of a coupling matrix configured to transport the samples in the intrinsic space to the target space.

Abstract: This disclosure provides methods, devices and systems for radio frequency (RF) sensing in wireless communication systems. In some implementations, a transmitter device transmits sounding sequences configured for channel estimation over a wireless channel to a receiver device. The transmitter device also transmits or receives non-sounding frames associated with a channel report of the receiver device. The transmitter device transmits a frame soliciting the channel report from the receiver device. The transmitter device receives the channel report, which may include channel state information (CSI) of the wireless channel responsive to at least the sounding sequences. Some types of channel reports may take longer to generate than other types of channel reports. Transmitting or receiving the non-sounding frames during the time period may prevent other devices from accessing the wireless channel when the receiver device needs additional time to generate a certain type of channel report.

Abstract: Disclosed are systems, methods, and non-transitory media for performing passive radio frequency (RF) location detection operations. In some aspects, RF data, such as RF signals including channel state information (CSI), can be received from a wireless device. The RF data can be provided to a self-supervised machine-learning architecture that is configured to perform three-dimensional (3D) object location estimation.

Abstract: Disclosed are systems, methods, and non-transitory media for sensing radio frequency signals. For instance, radio frequency data can be received by an apparatus and from at least one wireless device in an environment. Based on the radio frequency data received from the at least one wireless device, the apparatus can determine sensing coverage of the at least one wireless device. The apparatus can further provide the determined sensing coverage and a position of at least one device to a user device.

Abstract: Disclosed are systems, methods, and non-transitory media for performing passive radio frequency (RF) location detection operations. In some aspects, RF data, such as RF signals including channel state information (CSI), can be received from a wireless device. The RF data can be provided to a self-supervised machine-learning architecture that is configured to perform object location estimation.

Abstract: Disclosed are systems, methods, and non-transitory media for performing radio frequency sensing detection operations. For instance, radio frequency data can be received that is associated with at least one wireless device. The radio frequency data can be based on radio frequency signals reflected from a first object and received by the at least one wireless device. Training label data can also be obtained (e.g., from a labeling device, from the at least one wireless device, etc.). The training label data can be based at least in part on the first object and input data (e.g., received by the labeling device, the at least one wireless device, etc.). A sensing model can be generated based on the radio frequency data and the training label data.

Abstract: This disclosure describes systems, devices, apparatus, and methods, including computer programs encoded on storage media, for controlling a network with one or more access points (APs). A controller may be configured to schedule at least some resources of the one or more APs to improve network efficiency. The APs may measure and report a variety of information and statistics to the controller. The controller may determine one or more transmission parameters and one or more operations a given AP is permitted to perform during a respective time interval. The controller may communicate the one or more transmission parameters using an indication, such as a message. At least one AP associated with the controller may communicate with stations (STAs) using the one or more transmission parameters.

Abstract: In an aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus obtain a signal from a remote wireless node. The apparatus may switch between a first mode and a second mode in response to the signal. The apparatus may sense the shared transmission medium and sense if an absence of traffic is detected. The apparatus may delay data transmission for a fixed time interval from detecting the absence of traffic. The apparatus may initiate the data transmission at the end of the fixed time interval if operating in the first mode or initiate the data transmission at the end of a random time interval following the fixed time interval if operation in the second mode.

Abstract: Certain aspects of the present disclosure provide techniques for object positioning using mixture density networks, comprising: receiving radio frequency (RF) signal data collected in a physical space; generating a feature vector encoding the RF signal data by processing the RF signal data using a first neural network; processing the feature vector using a first mixture model to generate a first encoding tensor indicating a set of moving objects in the physical space, a first location tensor indicating a location of each of the moving objects in the physical space, and a first uncertainty tensor indicating uncertainty of the locations of each of the moving objects in the physical space; and outputting at least one location from the first location tensor.