Sparsity-based severe weather detection

Abstract

Aspects presented herein may enable a UE to detect and identify a weather condition of an environment based on sparsity of FFT / DWT coefficients derived from a set of range images associated with the environment. In one aspect, the UE converts a set of point clouds associated with an environment into a set of range images based on a spherical projection. The UE applies at least one of FFT or DWT to the range image set to obtain a set of FFT coefficients or a set of DWT coefficients. The UE identifies a level of condition of the environment based on sparsity of the set of FFT coefficients or the set of DWT coefficients.

Description

[0001] Cross-references to related applications

[0002] This application claims the benefit of U.S. non-provisional patent application No. 18 / 357,014, filed July 21, 2023, entitled “SPARSITY-BASED ADVERSE WEATHER DETECTION,” the entire contents of which are expressly incorporated herein by reference. Technical Field

[0003] This disclosure relates generally to communication systems, and more specifically to wireless communication relating to camera-assisted positioning and ranging. Background Technology

[0004] Wireless communication systems are widely deployed to provide a variety of telecommunications services, such as telephone, video, data, messaging, and broadcasting. Typical wireless communication systems may employ multiple access technologies capable of supporting communication with multiple users by sharing available system resources. Examples of such multiple access technologies include Code Division Multiple Access (CDMA) systems, Time Division Multiple Access (TDMA) systems, Frequency Division Multiple Access (FDMA) systems, Orthogonal Frequency Division Multiple Access (OFDMA) systems, Single Carrier Frequency Division Multiple Access (SC-FDMA) systems, and Time Division Synchronous Code Division Multiple Access (TD-SCDMA) systems.

[0005] These multiple access technologies have been adopted in various telecommunications standards to provide a common protocol that enables different wireless devices to communicate at the city, national, regional, and even global levels. An example telecommunications standard is 5G New Radio (NR). 5G NR is part of the Continuous Evolution of Mobile Broadband (CEM) program issued by the 3rd Generation Partnership Project (3GPP) to meet new requirements associated with latency, reliability, security, scalability (e.g., with the Internet of Things (IoT),) and other requirements. 5G NR includes services associated with enhanced mobile broadband (eMBB), massive machine-type communications (mMTC), and ultra-reliable low-latency communications (URLLC). Some aspects of 5G NR can be based on the 4G Long Term Evolution (LTE) standard. Further improvements to 5G NR technology are needed. Furthermore, these improvements can also be applied to other multiple access technologies and telecommunications standards that adopt these technologies. Summary of the Invention

[0006] The following is a simplified summary of one or more aspects to provide a basic understanding of these aspects. This summary is not a comprehensive overview of all conceived aspects. It neither identifies key or essential elements of all aspects nor describes the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed descriptions that follow.

[0007] In an aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus converts a set of point clouds associated with an environment to a set of range images based on spherical projection. The apparatus applies at least one of a fast Fourier transform (FFT) or a discrete wavelet transform (DWT) to the set of range images to obtain a set of FFT coefficients or a set of DWT coefficients. The apparatus identifies a level of a condition of the environment based on sparsity of the set of FFT coefficients or the set of DWT coefficients.

[0008] To the accomplishment of the foregoing and related ends, one or more aspects comprise the features hereinafter fully described and particularly pointed out in the claims. The following description and the annexed drawings set forth in detail certain illustrative features of the one or more aspects. These features are indicative, however, of but a few of the various ways in which principles of various aspects can be employed. BRIEF DESCRIPTION OF DRAWINGS

[0009] Figure 1 is a diagram illustrating an example of a wireless communications system and an access network.

[0010] Figure 2A is a diagram illustrating an example of a first frame, in accordance with various aspects of the present disclosure.

[0011] Figure 2B is a diagram illustrating an example of a downlink (DL) channel within a subframe, in accordance with various aspects of the present disclosure.

[0012] Figure 2C is a diagram illustrating an example of a second frame, in accordance with various aspects of the present disclosure.

[0013] Figure 2D is a diagram illustrating an example of an uplink (UL) channel within a subframe, in accordance with various aspects of the present disclosure.

[0014] Figure 3 is a diagram illustrating an example of a base station and user equipment (UE) in an access network.

[0015] Figure 4 is a diagram illustrating an example of UE positioning based on reference signal measurements.

[0016] Figure 5 Examples of sidelink communications between devices, in accordance with various aspects of the present disclosure, are illustrated.

[0017] Figure 6 is a diagram illustrating an example of camera-assisted positioning, in accordance with various aspects of the present disclosure.

[0018] Figure 7AThe illustrations are examples of camera vision under good / normal (e.g., non-severe) weather conditions, illustrating various aspects of this disclosure.

[0019] Figure 7B This is an illustration illustrating examples of camera vision under adverse weather conditions according to various aspects of this disclosure.

[0020] Figure 8A This is an illustration of examples of point clouds generated by light detection and ranging (Lidar) sensors under good / normal (e.g., non-severe) weather conditions, according to various aspects of this disclosure.

[0021] Figure 8B This is an illustration of examples of point clouds generated by a Lidar sensor under adverse weather conditions, according to various aspects of this disclosure.

[0022] Figure 9 This is an illustration of an example of identifying / detecting weather conditions based on scene-based sparsity according to various aspects of this disclosure.

[0023] Figure 10 This is an illustration of an example of identifying / detecting weather conditions based on scene-based sparsity according to various aspects of this disclosure.

[0024] Figure 11 This is an illustration of an example of identifying / detecting weather conditions based on scene-based sparsity according to various aspects of this disclosure.

[0025] Figure 12 This is a diagram illustrating an example relationship between the L1 norm of the Fast Fourier Transform (FFT) or Discrete Wavelet Transform (DWT) (FFT / DWT) coefficients and weather conditions according to various aspects of this disclosure.

[0026] Figure 13 This is an illustration illustrating an example of using multiple distance images from multiple ranging components to detect severe weather conditions according to various aspects of this disclosure.

[0027] Figure 14 This is an illustration illustrating examples of merging camera images and distance images for contrastive representation learning according to various aspects of this disclosure.

[0028] Figure 15 This is a flowchart of a wireless communication method.

[0029] Figure 16 This is a flowchart of a wireless communication method.

[0030] Figure 17 These are illustrations of examples of hardware implementations of example devices and / or network entities. Detailed Implementation

[0031] Aspects presented herein can improve the accuracy and performance of ranging operations and / or localization operations by enabling devices, sensors, and / or components used for ranging / localization operations to detect / determine weather conditions, such as adverse weather conditions, in real-time. By enabling devices / sensors / components (e.g., smartphones, vehicles, autonomous vehicles, Lidar, ranging components, etc.) to detect adverse weather conditions in real-time, the devices / sensors / components can be able to make more suitable scene reasoning and perform more appropriate control strategies under the detected adverse weather conditions. For example, in one aspect of the disclosure, a set of point clouds can be projected into a range view and thus considered a two-dimensional (2D) tensor. Similarly, a sequence of range images can be considered a three-dimensional (3D) tensor. The sparsity of the tensor can be quantified as the LI norm of the Fast Fourier Transform (FFT) or Discrete Wavelet Transform (DWT) coefficients. By applying the FFT and / or DWT to the sequence of range images, the sparsity of the scene can be quantified, where a more sparse scene can indicate a lower likelihood of adverse weather. In other words, by quantifying the sparsity of the scene, the presence of adverse weather conditions can be identified. Moreover, in another aspect of the disclosure, camera images collected during adverse weather conditions, although possibly blurry, can still be incorporated into or used for a self-supervised approach (e.g., for machine learning / artificial intelligence).

[0032] Aspects presented herein can not specify a physical model of adverse weather conditions, meaning that given data (e.g., range images) is available, this can be generalized to different ranging component (e.g., Lidar sensor) configurations. Unlike data-driven approaches, aspects presented herein can be unsupervised (which can also be referred to as weakly supervised), meaning that it can not specify ground truth labels or human intervention. Aspects presented herein can quantify the amount of sensory degradation at a fine-grained level, rather than acting as a binary classifier (e.g., detecting the severity of weather conditions, rather than classifying weather as good or bad). Aspects presented herein can be formulated as a multi-frame approach, enhancing temporal consistency. Aspects presented herein can also be extended to incorporate camera images if such data is available.

[0033] Aspects presented herein can be applied to sensor suites equipped on vehicles, depending on the quality of the output predictions. The computational specification of aspects presented herein can be very low and can be deployed on low-cost digital signal processors (DSPs). Aspects presented herein can enable downstream planning algorithms to switch / adjust to weather-specific control strategies for safe navigation under adverse weather conditions. If camera images are available, image feature extractors can be trained for downstream vision-based tasks, including, but not limited to, initializing the encoder of 3D object detection networks.

[0034] The detailed descriptions following, illustrated with reference to the accompanying drawings, describe various configurations and do not represent the only configurations in which the concepts described herein can be practiced. To provide a thorough understanding of the various concepts, the detailed descriptions include specific details. However, these concepts can be practiced without these specific details. In some instances, well-known structures and components are shown in block diagram form to avoid obscuring these concepts.

[0035] Various apparatuses and methods are presented with reference to several aspects of a telecommunications system. These apparatuses and methods are described in detail below and illustrated in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively, “elements”). These elements may be implemented using electronic hardware, computer software, or any combination thereof. Whether these elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the system as a whole.

[0036] As an example, an element, any part of an element, or any combination of elements may be implemented as a "processing system" including one or more processors. When multiple processors are implemented, the multiple processors may perform functions individually or in combination. Examples of processors include microprocessors, microcontrollers, graphics processing units (GPUs), central processing units (CPUs), application processors, digital signal processors (DSPs), reduced instruction set computing (RISC) processors, system-on-a-chip (SoCs), baseband processors, field-programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gate logic, discrete hardware circuits, and other suitable hardware configured to perform the various functionalities described throughout this disclosure. One or more processors in the processing system can execute software. Whether referred to as software, firmware, middleware, microcode, hardware description language, or other terms, software should be broadly interpreted as instructions, instruction sets, code, code segments, program code, programs, subroutines, software components, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, or any combination thereof.

[0037] Accordingly, in one or more example aspects, implementations, and / or use cases, the described features can be implemented in hardware, software, or any combination thereof. If implemented in software, the functions can be stored on or encoded as one or more instructions or code on a computer-readable medium. Computer-readable media includes computer storage media. Storage media can be any available media that can be accessed by a computer. By way of example, and not limitation, such computer-readable media can comprise a random-access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), optical disk storage, magnetic disk storage, other magnetic storage devices, combinations of the aforementioned types of computer-readable media, or any other medium that can be used to store computer executable code in the form of instructions or data structures that can be accessed by a computer.

[0038] While aspects, implementations, and / or use cases are described in this application by illustration to some examples, those examples are not intended to limit the scope of aspects, implementations, and / or use cases. Numerous additional aspects, implementations, and / or use cases can be derived from examples that are disclosed in this application, with equivalence to each disclosed feature. It will be understood by those within the art that various aspects, implementations, and / or use cases disclosed herein can be implemented in any of a variety of different ways. Also, it will be understood that various implementations of each of the aspects, implementations, and / or use cases disclosed herein can be used alone or in any combination. Although each aspect, implementation, and / or use case is described in the application by illustration to some examples, those examples are not intended to limit the scope of aspects, implementations, and / or use cases. Numerous additional aspects, implementations, and / or use cases can be derived from examples that are disclosed in this application, with equivalence to each disclosed feature. It will be understood by those within the art that various aspects, implementations, and / or use cases disclosed herein can be implemented in any of a variety of different ways. Also, it will be understood that various implementations of each of the aspects, implementations, and / or use cases disclosed herein can be used alone or in any combination. Accordingly, in one or more example aspects, implementations, and / or use cases, the described features can be implemented in hardware, software, or any combination thereof. If implemented in software, the functions can be stored on or encoded as one or more instructions or code on a computer-readable medium. Computer-readable media includes computer storage media. Storage media can be any available media that can be accessed by a computer. By way of example, and not limitation, such computer-readable media can include a random-access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), optical disk storage, magnetic disk storage, other magnetic storage devices, combinations of the aforementioned types of computer-readable media, or any other medium that can be used to store computer executable code in the form of instructions or data structures that can be accessed by a computer.

[0039] Deployment of communication systems, such as 5G NR systems, can be arranged in a variety of ways with various components or constituent parts. In a 5G NR system or network, a network node, network entity, mobility element of a network, radio access network (RAN) node, core network node, network element, or network equipment, such as a base station (BS), or one or more units (or one or more components) that perform base station functionality, can be implemented in an aggregated or disaggregated architecture. For example, a BS, such as a Node B (NB), an evolved NB (eNB), an NR BS, a 5G NB, an access point (AP), a transmission reception point (TRP), or a cell, etc., can be implemented as an aggregated base station (also referred to as a standalone BS or a monolithic BS) or a disaggregated base station.

[0040] An aggregated base station can be configured to utilize a radio protocol stack that is physically or logically integrated within a single RAN node. A disaggregated base station can be configured to utilize a protocol stack that is physically or logically distributed across two or more units, such as one or more central or centralized units (CUs), one or more distributed units (DUs), or one or more radio units (RUs). In some aspects, a CU can be implemented within a RAN node, and one or more DUs can be co-located with the CU or, alternatively, can be geographically or virtually distributed in one or more other RAN nodes. A DU can be implemented to communicate with one or more RUs. Each of the CU, DU, and RU can be implemented as a virtual unit, i.e., a virtual central unit (VCU), a virtual distributed unit (VDU), or a virtual radio unit (VRU).

[0041] Base station operations or network designs can take into account the aggregated nature of base station functionality. For example, a disaggregated base station can be utilized in an integrated access backhaul (IAB) network, an open radio access network (O-RAN (such as a network configuration initiated by the O-RAN Alliance)), or a virtualized radio access network (vRAN, also referred to as a cloud radio access network (C-RAN)). Disaggregation can include distributing functionality across two or more units at various physical locations, as well as virtually distributing functionality of at least one unit, which can enable flexibility in network design. The various units of a disaggregated base station or disaggregated RAN architecture can be configured for wired or wireless communication with at least one other unit.

[0042] Figure 1is a diagram 100 illustrating examples of a wireless communication system and access network. The illustrated wireless communication system includes a disaggregated base station architecture. The disaggregated base station architecture can include one or more CUs 110 that can communicate directly with a core network 120 via a backhaul link, or indirectly with the core network 120 through one or more disaggregated base station units, such as a near real-time (near-RT) RAN intelligent controller (RIC) 125 via an E2 link, or a non-real-time (non-RT) RIC 115 associated with a service management and orchestration (SMO) framework 105, or both. The CUs 110 can communicate with one or more DUs 130 via respective midhaul links, such as an Fl interface. The DUs 130 can communicate with one or more RUs 140 via respective front-haul links. The RUs 140 can communicate with respective UEs 104 via one or more radio frequency (RF) access links. In some implementations, a UE 104 can be simultaneously served by multiple RUs 140.

[0043] Each of the units (i.e., the CUs 110, the DUs 130, the RUs 140, and the near-RT RIC 125, the non-RT RIC 115, and the SMO framework 105) can include or be coupled to one or more interfaces configured to receive or transmit signals, data, or information (collectively, signals) via a wired or wireless transmission medium. Each of the units or an associated processor or controller providing instructions to the communication interfaces of the units can be configured to communicate with one or more of the other units via the transmission medium. For example, the units can include wired interfaces configured to receive or transmit signals to one or more of the other units over a wired transmission medium. Additionally, the units can include wireless interfaces that can include receivers, transmitters, or transceivers (such as RF transceivers) configured to receive signals and / or transmit signals to one or more of the other units over a wireless transmission medium.

[0044] In some aspects, the CU 110 can host one or more higher layer control functions. Such control functions can include radio resource control (RRC), packet data convergence protocol (PDCP), service data adaptation protocol (SDAP), and / or the like. Each control function can be implemented with an interface configured to communicate signals with other control functions hosted by the CU 110. The CU 110 can be configured to handle user plane functionality (i.e., central unit-user plane (CU-UP)), control plane functionality (i.e., central unit-control plane (CU-CP)), or a combination thereof. In some implementations, the CU 110 can be logically split into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP units can communicate bi-directionally with the CU-CP units via an interface, such as an El interface. The CU 110 can be implemented to communicate with the DUs 130 as needed for network control and signal transfer.

[0045] The DU 130 can correspond to a logical unit that includes one or more base station functions for controlling the operation of one or more RUs 140. In some aspects, the DU 130 can host one or more of a radio link control (RLC) layer, a medium access control (MAC) layer, and one or more high physical (PHY) layers (such as modules for forward error correction (FEC) encoding and decoding, scrambling, modulation, demodulation, and / or the like) in accordance with, at least in part, a functional split, such as those defined by 3GPP. In some aspects, the DU 130 can also host one or more low PHY layers. Each layer (or module) can be implemented with an interface configured to communicate signals with other layers (and modules) hosted by the DU 130 or with control functions hosted by the CU 110.

[0046] The lower layer functionality can be implemented by one or more RUs 140. In some deployments, the RUs 140 controlled by the DU 130 can correspond to logical nodes that host RF processing functions or low PHY layer functions (such as performing fast Fourier transform (FFT), inverse FFT (iFFT), digital beamforming, physical random access channel (PRACH) extraction and filtering, and / or the like) or both based, at least in part, on a functional split, such as a lower layer functional split. In such an architecture, the RUs 140 can be implemented to handle over-the-air (OTA) communications with one or more UEs 104. In some implementations, real-time and non-real-time aspects of control plane and user plane communications with the RUs 140 can be controlled by the corresponding DU 130. In some scenarios, this configuration can enable the DUs 130 and the CUs 110 to be implemented in a cloud-based RAN architecture, such as a vRAN architecture.

[0047] The SMO framework 105 can be configured to support RAN deployment and orchestration of non-virtualized network elements and virtualized network elements. For non- virtualized network elements, the SMO framework 105 can be configured to support deployment of dedicated physical resources for RAN coverage requirements, which can be managed via an operations and maintenance interface, such as an Ol interface. For virtualized network elements, the SMO framework 105 can be configured to interact with a cloud computing platform, such as Open Cloud (O-Cloud) 190, to perform network element lifecycle management, such as to instantiate virtualized network elements, via a cloud computing platform interface, such as an 02 interface. Such virtualized network elements can include, but are not limited to, CUs 110, DUs 130, RUs 140, and near-RT RICs 125. In some implementations, the SMO framework 105 can communicate with hardware aspects of a 4G RAN, such as Open eNB (O-eNB) 111, via an Ol interface. Additionally, in some implementations, the SMO framework 105 can communicate directly with one or more RUs 140 via an Ol interface. The SMO framework 105 can also include a non-RT RIC 115 configured to support functionality of the SMO framework 105.

[0048] The non-RT RIC 115 can be configured to include logical functions that enable non-real-time control and optimization of RAN elements and resources, artificial intelligence (AI) / machine learning (ML) (AI / ML) workflows including model training and updates, or policy-based direction of applications / features in the near-RT RIC 125. The non-RT RIC 115 can be coupled to or in communication with the near-RT RIC 125, such as via an Al interface. The near-RT RIC 125 can be configured to include logical functions that enable near-real-time control and optimization of RAN elements and resources via data collection and actions through an interface, such as via an E2 interface, that connects one or more CUs 110, one or more DUs 130, or both, and the O-eNB with the near-RT RIC 125.

[0049] In some implementations, to generate AI / ML models to be deployed in the near-RT RIC 125, the non-RT RIC 115 can receive parameters or external enrichment information from an external server. Such information can be utilized by the near-RT RIC 125 and can be received at the SMO framework 105 or the non-RT RIC 115 from non-network data sources or from network functions. In some examples, the non-RT RIC 115 or the near-RT RIC 125 can be configured to tune RAN behavior or performance. For example, the non-RT RIC 115 can monitor long-term trends and patterns of performance and employ AI / ML models to perform corrective actions through the SMO framework 105, such as via reconfiguration of Ol, or via creation of RAN management policies, such as Al policies.

[0050] At least one of the CU 110, the DU 130, and the RU 140 can be referred to as a base station 102. Thus, a base station 102 can include one or more of the CU 110, the DU 130, and the RU 140 (each component is indicated with a dashed line to represent that each component can or can not be included in the base station 102). The base station 102 provides wireless access to the core network 120 for the UEs 104. The base station 102 can include a macro cell (high power cellular base station) and / or a small cell (low power cellular base station). The small cell includes a femto cell, a pico cell, and a micro cell. A network that includes both small cells and macro cells can be known as a heterogeneous network. A heterogeneous network also can include home evolved node Bs (eNBs) (HeNBs), which can provide service to a restricted group known as a closed subscriber group (CSG). The communication links between the RUs 140 and the UEs 104 can include uplink (UL) (also referred to as reverse link) transmissions from a UE 104 to a RU 140 and / or downlink (DL) (also referred to as forward link) transmissions from a RU 140 to a UE 104. The communication links can use multiple-input and multiple-output (MIMO) antenna technology, including spatial multiplexing, beamforming, and / or transmit diversity. The communication links can be through one or more carriers, where each carrier can be a band of frequency waves having a predetermined width and can be used to transmit data between base stations 102 and UEs 104. The base station 102 / UE 104 can use spectrum up to Y MHz (e.g., 5 MHz, 10 MHz, 15 MHz, 20 MHz, 100 MHz, 400 MHz, etc.) of bandwidth per carrier allocated in a carrier aggregation. The carriers can or can not be adjacent to each other. The allocation of carriers can be asymmetric, with more carriers

[0051] Certain UEs 104 can communicate with each other using device-to-device (D2D) communication links 158. The D2D communication links 158 can use the DL / UL WWAN spectrum. The D2D communication links 158 can use one or more sidelink channels, such as a physical sidelink broadcast channel (PSBCH), a physical sidelink discovery channel (PSDCH), a physical sidelink shared channel (PSSCH), and a physical sidelink control channel (PSCCH). D2D communication can be through a variety of wireless D2D communications systems, such as for example, Bluetooth ™ (Bluetooth is a trademark of the Bluetooth Special Interest Group (SIG)), Wi-Fi ™ based on the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard, LTE, or NR.

[0052] The wireless communications system can also include a Wi-Fi AP 150 in communication with UEs 104 (also known as Wi-Fi stations (STAs)) via communication links 154, e.g., in a 5 GHz unlicensed frequency spectrum or the like. When communicating in an unlicensed frequency spectrum, the UEs 104 / AP 150 can perform a clear channel assessment (CCA) prior to communicating in order to determine whether the channel is available.

[0053] The electromagnetic spectrum is often subdivided based on frequency / wavelength into various classes, bands, channels, and so on. In 5G NR, two initial operating bands have been identified as frequency range designations FR1 (410 MHz to 7. 125 GHz) and FR2 (24.25 GHz to 52.6 GHz). Despite a portion of FR1 being greater than 6 GHz, FR1 is often referred to (interchangeably) as a “sub-6 GHz” band in various documents and articles. A similar nomenclature issue sometimes occurs with respect to FR2, which is often (interchangeably) referred to as a “millimeter wave” band in documents and articles, despite the frequencies being lower than the extremely high frequency (EHF) band (30 GHz to 300 GHz) which is designated by the International Telecommunications Union (ITU) as a “millimeter wave” band.

[0054] The frequencies between FR1 and FR2 are often referred to as mid-band frequencies. Recent 5G NR studies have identified operating bands for these mid-band frequencies as Frequency Range designation FR3 (7.125 GHz to 24.25 GHz). Bands that fall within FR3 can inherit FR1 and / or FR2 characteristics, and thus can effectively extend the features of FR1 and / or FR2 to mid-band frequencies. Moreover, higher bands are currently being explored to extend 5G NR operations beyond 52.6 GHz. For example, three higher operating bands have been identified as Frequency Range designations FR2-2 (52.6 GHz to 71 GHz), FR4 (71 GHz to 114.25 GHz), and FR5 (114.25 GHz to 300 GHz). Each of these higher bands falls within the EHF band.

[0055] In light of the above, unless specifically stated otherwise, if a term "sub-6 GHz" or the like is used herein, it can broadly represent frequencies that can be less than 6 GHz, can be within FR1, or can include mid-band frequencies. Further, unless specifically stated otherwise, if a term "millimeter wave" or the like is used herein, it can broadly represent frequencies that can include mid-band frequencies, can be within FR2, FR4, FR2-2, and / or FR5, or can be within the EHF band.

[0056] The base stations 102 and the UEs 104 can each include multiple antennas (such as antenna elements, antenna panels, and / or antenna arrays) to facilitate beamforming. The base stations 102 can transmit to UEs 104 in one or more transmit directions 186 on the downlink 104. The UEs 104 can transmit to the base stations 102 in one or more transmit directions 188 on the uplink 106. The base stations 102 / UEs 104 can perform beam training to determine the best receive and transmit directions for each of the base stations 102 / UEs 104. The transmit and receive directions for the base stations 102 can or can not be the same. The transmit and receive directions for the UEs 104 can or can not be the same.

[0057] The base stations 102 can include and / or be referred to as gNBs, NodeBs, eNBs, access points, transceiver base stations, radio base stations, radio transceivers, transceiver functions, basic service sets (BSSs), extended service sets (ESSs), TRPs, network nodes, network entities, network equipment, or some other suitable terminology. The base stations 102 can be implemented as integrated access and backhaul (IAB) nodes, relay nodes, sidelink nodes, aggregated (monolithic) base stations with baseband units (BBUs) including CUs and DUs and RUs, or as disaggregated base stations including one or more of CUs, DUs, and / or RUs. A collection of base stations that can include disaggregated base stations and / or aggregated base stations can be referred to as a next generation (NG) RAN (NG-RAN).

[0058] The core network 120 can include an access and mobility management function (AMF) 161, a session management function (SMF) 162, a user plane function (UPF) 163, a unified data management (UDM) 164, one or more location servers 168, and other functional entities. The AMF 161 is a control node that handles signaling between the UEs 104 and the core network 120. The AMF 161 supports registration management, connection management, mobility management, and other functions. The SMF 162 supports session management and other functions. The UPF 163 supports packet routing, packet forwarding, and other functions. The UDM 164 supports generation of authentication and key agreement (AKA) credentials, user identification handling, access authorization, and subscription management. The one or more location servers 168 are illustrated as including a gateway mobile location center (GMLC) 165 and a location management function (LMF) 166. However, in general, the one or more location servers 168 can include one or more location / determination servers, which can include one or more of a GMLC 165, an LMF 166, a positioning determination entity (PDE), a serving mobile location center (SMLC), a mobile positioning center (MPC), and the like. The GMLC 165 and the LMF 166 support UE location services. The GMLC 165 provides an interface for clients / applications (e.g., emergency services) to access UE positioning information. The LMF 166 receives measurements and assistance information from the NG-RAN and the UE 104 via the AMF 161 to compute a position of the UE 104. The NG-RAN can utilize one or more positioning methods to determine a position of the UE 104. Positioning the UE 104 can involve signal measurements, position estimation, and optional velocity calculations based on these measurements. The signal measurements can be made by the UE 104 and / or the base stations 102 serving the UE 104. The measured signals can be based on one or more of a satellite positioning system (SPS) 170 (e.g., Global Navigation Satellite System (GNSS), Global Positioning System (GPS), Non-Terrestrial Network (NTN), or other satellite positioning / location system), LTE signals, Wireless Local Area Network (WLAN) signals, Bluetooth signals, Terrestrial Beacon System (TBS), sensor-based information (e.g., barometric pressure sensors, motion sensors), NR Enhanced Cell ID (NR E-CID) methods, NR signals (e.g., multi-round trip time (multi-RTT), DL angle of departure (DL-AoD), DL time difference of arrival (DL-TDOA), UL time difference of arrival (UL-TDOA), and UL angle of arrival (UL-AoA) positioning), and / or other systems / signals / sensors.

[0059] Examples of a UE 104 include a cellular phone, a smart phone, a session initiation protocol (SIP) phone, a laptop, a personal digital assistant (PDA), a satellite radio, a global positioning system, a multimedia device, a video device, a digital audio player (e.g., MP3 player), a camera, a game console, a tablet, a smart device, a wearable device, a vehicle, an electric meter, a gas pump, a large or small kitchen appliance, a healthcare device, an implant, a sensor / actuator, a display, or any other similar functional device. Some of the UEs 104 can be referred to as IoT devices (e.g., parking meter, gas pump, toaster, vehicle, heart monitor, etc.). The UE 104 can also be referred to as a station, a mobile station, a subscriber station, a mobile unit, a subscriber unit, a wireless unit, a remote unit, a mobile device, a wireless device, a wireless communications device, a remote device, a mobile subscriber station, an access terminal, a mobile terminal, a wireless terminal, a remote terminal, a handset, a user agent, a mobile client, a client, or some other suitable terminology. In some scenarios, the term UE can also apply to one or more accessory devices, such as in a device constellation arrangement. One or more of these devices can collectively or individually access a network.

[0060] Referring again to Figure 1 In certain aspects, the UE 104 can include a weather detection component 198 that can be configured to convert a set of point clouds associated with an environment to a set of range images based on a spherical projection, apply at least one of an FFT or a DWT to the set of range images to obtain a set of FFT coefficients or a set of DWT coefficients, and identify a level of a condition of the environment based on sparsity of the set of FFT coefficients or the set of DWT coefficients. In certain aspects, the base station 102 can include a weather information collection component 199 that can be configured to collect the identified level of the condition of the environment from the UE 104 (e.g., based on crowd-sourcing).

[0061] Figure 2A FIG. 200 is a diagram 200 illustrating an example of a first subframe within a 5G NR frame structure. Figure 2B FIG. 230 is a diagram 230 illustrating an example of DL channels within a 5G NR subframe. Figure 2C FIG. 250 is a diagram 250 illustrating an example of a second subframe within a 5G NR frame structure. Figure 2D FIG. 280 is a diagram 280 illustrating an example of UL channels within a 5G NR subframe. The 5G NR frame structure can be frequency-division duplexed (FDD) in which Figure 2A、 Figure 2C In the examples provided, a 5G NR frame structure is assumed to be TDD with subframe 4 configured with slot format 28 (with mostly DL), where D is DL, U is UL, and F is flexible to use between DL / UL, and subframe 3 configured with slot format 1 (with all UL). While subframes 3, 4 are shown with slot formats 1, 28, respectively, any particular subframe can be configured with any of the various available slot formats 0-61. Slot formats 0, 1 are all DL, UL, respectively. Other slot formats 2-61 include a mix of DL, UL, and flexible symbols. UEs are configured with a slot format (dynamically through DL control information (DCI) or semi-statically / statically through radio resource control (RRC) signaling) through a received slot format indicator (SFI). Note that the following description also applies for a 5G NR frame structure that is FDD.

[0062] Figures 2A-2D A frame structure is illustrated, and aspects of the disclosure can be applicable to other wireless communication technologies that can have different frame structures and / or different channels. One frame (10 ms) can be divided into 10 equal sized subframes (1 ms). Each subframe can include one or more slots. A subframe can also include mini-slots, which can contain 7, 4, or 2 symbols. Each slot can contain 14 or 12 symbols depending on whether a cyclic prefix (CP) is normal or extended. For a normal CP, each slot can contain 14 symbols, and for an extended CP, each slot can contain 12 symbols. Symbols on the DL can be CP orthogonal frequency division multiplexing (OFDM) (CP-OFDM) symbols. Symbols on the UL can be CP-OFDM symbols (for high throughput scenarios) or discrete Fourier transform (DFT) spread OFDM (DFT-s-OFDM) symbols (for power limited scenarios; limited to single stream transmission). The number of slots within a subframe is based on the CP and the numerology. The numerology defines the subcarrier spacing (SCS) (see Table 1). The symbol length / duration can scale with 1 / SCS.

[0063]

[0064] Table 1: Numerology, SCS, and CP

[0065] For a normal CP (14 symbols / slot), different numerologies m 0 to 4 allow for 1, 2, 4, 8, and 16 slots per subframe, respectively. For an extended CP, numerology 2 allows for 4 slots per subframe. Thus, for a normal CP and numerology m, there are 14 symbols / slot and 2 µ slots / subframe. The subcarrier spacing can be equal to where The numerologies are parameter sets 0 through 4. Thus, the subcarrier spacing for parameter set µ = 0 is 15 kHz, and the subcarrier spacing for parameter set µ = 4 is 240 kHz. The symbol length / duration is inversely related to the subcarrier spacing. Figures 2A-2D An example of normal CP with 14 symbols per slot and parameter set µ = 2 with 4 slots per subframe is provided. The slot duration is 0.25 ms, the subcarrier spacing is 60 kHz, and the symbol duration is approximately 16.67 μβ. Within a frame set, there can be one or more different bandwidth parts (BWPs) that are frequency division multiplexed (see Figure 2B ). Each BWP can have a particular numerology and CP (normal or extended).

[0066] A resource grid can be used to represent the frame structure. Each time slot includes a resource block (RB) (also referred to as a physical RB (PRB)) that extends 12 consecutive subcarriers. The resource grid is divided into multiple resource elements (REs). The number of bits carried by each RE depends on the modulation scheme.

[0067] As illustrated in Figure 2A Some of the REs carry reference (pilot) signals (RS) for the UE. The RS can include demodulation RS (DM-RS) (indicated as R for one particular configuration, but other DM-RS configurations are possible) and channel state information reference signals (CSI-RS) for channel estimation at the UE. The RS can also include beam measurement RS (BRS), beam refinement RS (BRRS), and phase tracking RS (PT-RS).

[0068] Figure 2BExamples of various DL channels are illustrated. The physical downlink control channel (PDCCH) carries DCI within one or more control channel elements (CCEs) (e.g., 1, 2, 4, 8, or 16 CCEs), each CCE including six RE groups (REGs), each REG including 12 consecutive REs in an OFDM symbol of an RB. A PDCCH within one BWP can be referred to as a control resource set (CORESET). A UE is configured to monitor PDCCH search space (e.g., common search space, UE-specific search space) for PDCCH candidates during PDCCH monitoring occasions on the CORESET, where the PDCCH candidates have different DCI formats and different aggregation levels. Additional BWPs can be located at higher and / or lower frequencies of the channel bandwidth. A primary synchronization signal (PSS) can be within symbol 2 of particular subframes of a frame. The PSS is used by a UE 104 to determine subframe / symbol timing and a physical layer identity. A secondary synchronization signal (SSS) can be within symbol 4 of particular subframes of a frame. The SSS is used by a UE to determine a physical layer cell identity group number and radio frame timing. Based on the physical layer identity and the physical layer cell identity group number, the UE can determine a physical cell identifier (PCI). Based on the PCI, the UE can determine the locations of DM-RS. The physical broadcast channel (PBCH), which carries a master information block (MIB), can be logically grouped with the PSS and SSS to form a synchronization signal (SS) / PBCH block (also referred to as SS block (SSB)). The MIB provides system bandwidth configuration information and a scheduling

[0069] As Figure 2C illustrated, some of the REs carry DM-RS (indicated as R for one particular configuration, but other DM-RS configurations are possible) for channel estimation at the base station. The UE can transmit DM-RS for the physical uplink control channel (PUCCH) and DM-RS for the physical uplink shared channel (PUSCH). The PUSCH DM-RS can be transmitted in the first one or two symbols of a slot. The PUCCH DM-RS can be transmitted in different configurations depending on whether short or long PUCCHs are transmitted and depending on the particular PUCCH format used. The UE can transmit sounding reference signals (SRS). The SRS can be transmitted in the last symbol of a slot. The SRS can have a comb-2 structure, and a UE can transmit SRS on one of the combs. The SRS can be used by a base station for channel quality estimation to enable frequency-dependent scheduling for the UL.

[0070] Figure 2DExamples of various UL channels within a subframe are illustrated. The PUCCH can be located as indicated in one configuration. The PUCCH carries uplink control information (UCI), such as scheduling requests, channel quality indicator (CQI), precoding matrix indicators (PMI), rank indicators (RI), and hybrid automatic repeat request (HARQ) acknowledgment (ACK) (HARQ-ACK) feedback (i.e., one or more HARQ ACK bits indicating one or more ACKs and / or negative ACKs (NACKs)). The PUSCH carries data, and can additionally be used to carry buffer status reports (BSR), power headroom reports (PHR), and / or UCI.

[0071] Figure 3 is a block diagram of the components of base station 310 and UE 350, which can be used in implementing the techniques described in this disclosure. At the base station 310, a transmit processor 320 can receive data from a data source 312 and control information from a controller / processor 340. The transmit processor 320 can process (e.g., encode and modulate) the data and control information to generate data symbols and control symbols, which can be precoded by a TX MIMO processor 322 if applicable, further processed by a modulator 324, and transmitted to the UE 350 via the antennas 326. At the UE 350, the antennas 354 can receive the transmitted signals, and the signals can be processed by a demodulator 356 to generate processed signals. A receive processor 358 can then process the processed signals to obtain data and control information, which can be provided to a data sink 360 and the controller / processor 359, respectively. The controller / processor 359 can include a processor 359 and memory 359, and can be used to implement the techniques described in this disclosure.

[0072] The transmit (TX) processor 316 and the receive (RX) processor 370 implement layer 1 functionality associated with various signal processing functions. Layer 1, which includes a physical (PHY) layer, can include error detection on the transport channels, forward error correction (FEC) coding / decoding of the transport channels, interleaving, rate matching, mapping to physical channels, modulation / demodulation of physical channels, and MIMO antenna processing. The TX processor 316 handles mapping to signal constellations based on various modulation schemes (e.g., binary phase-shift keying (BPSK), quadrature phase-shift keying (QPSK), M-phase-shift keying (M-PSK), M-quadrature amplitude modulation (M-QAM)). The coded and modulated symbols can then be split into parallel streams. Each stream can then be mapped to an OFDM subcarrier, multiplexed with a reference signal (e.g., pilot) in the time and / or frequency domain, and then combined together using an inverse fast Fourier transform (IFFT) to produce a physical channel carrying a time domain OFDM symbol stream. The OFDM stream is spatially precoded to produce multiple spatial streams if multiple spatial streams are used. Channel estimates from a channel estimator 374 can be used to determine the beamforming

[0073] At the UE 350, each receiver 354Rx receives a signal through its respective antenna 352. Each receiver 354Rx recovers information modulated onto an RF carrier and provides the information to the receive (RX) processor 356. The TX processor 368 and the RX processor 356 implement layer 1 functionality associated with various signal processing functions. The RX processor 356 can perform spatial processing on the information to recover any spatial streams destined for the UE 350. If multiple spatial streams are destined for the UE 350, they can be combined by the RX processor 356 into a single OFDM symbol stream. The RX processor 356 then converts the OFDM symbol stream from the time domain to the frequency domain using a fast Fourier transform (FFT). The frequency domain signal comprises a separate OFDM symbol stream for each subcarrier of the OFDM signal. The symbols on each subcarrier, and the reference signal, are recovered and demodulated by determining the most likely signal constellation points transmitted by the base station 310. These soft decisions can be based on channel estimates computed by the channel estimator 358. The soft decisions are then decoded and deinterleaved to recover the data and control signals that were originally transmitted by the base station 310 on the physical channel. The data and control signals are then provided to the controller / processor 359, which implements layer 3 and layer 2 functionality.

[0074] The controller / processor 359 can be associated with a memory 360 that stores program codes and data. The memory 360 can be referred to as a computer-readable medium. In the UL, the controller / processor 359 provides demultiplexing between transport and logical channels, packet reassembly, deciphering, header decompression, and control signal processing to recover IP packets from the core network. The controller / processor 359 is also responsible for error detection using an ACK and / or NACK protocol to support HARQ operations.

[0075] Similar to the functionality described in connection with the DL transmission by the base station 310, the controller / processor 359 provides RRC layer functionality associated with system information (e.g., MIB, SIBs) acquisition, RRC connections, and measurement reporting; PDCP layer functionality associated with header compression / decompression, and security (ciphering, deciphering, integrity protection, integrity verification); RLC layer functionality associated with the transfer of upper layer PDUs, error correction using ARQ, concatenation, segmentation, and reassembly of RLC SDUs, re-segmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto TBs, demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction using HARQ, priority handling, and logical channel prioritization.

[0076] The TX processor 368 can use channel estimates derived by the channel estimator 358 from a reference signal or feedback transmitted by the base station 310 to select the appropriate coding and modulation schemes and to facilitate spatial processing. The spatial streams generated by the TX processor 368 can be provided to different antenna 352 via separate transmitters 354. Each transmitter 354 can modulate an RF carrier with a respective spatial stream for transmission.

[0077] The UL transmission is processed at the base station 310 in a manner similar to that described in connection with the receiver function at the UE 350. Each receiver 318 receives a signal through its respective antenna 320. Each receiver 318 recovers information modulated onto an RF carrier and provides the information to a RX processor 370.

[0078] The controller / processor 375 can be associated with a memory 376 that stores program codes and data. The memory 376 can be referred to as a computer-readable medium. In the UL, the controller / processor 375 provides demultiplexing between transport and logical channels, packet reassembly, deciphering, header decompression, control signal processing to recover IP packets from the core network. The controller / processor 375 is also responsible for error detection using an ACK and / or NACK protocol to support HARQ operations.

[0079] At least one of the TX processor 368, RX processor 356, and controller / processor 359 can be configured to perform and Figure 1 The weather detection component 198 integrates various aspects.

[0080] At least one of the TX processor 316, RX processor 370, and controller / processor 375 can be configured to perform and Figure 1 The weather information collection component 199 integrates various aspects.

[0081] Figure 4 Figure 400 illustrates an example of UE positioning (which may also be referred to as "network-based positioning") based on reference signal measurements according to various aspects of this disclosure. UE 404 can [operate at time T]. SRS_TX Send UL-SRS 412 and at time T PRS_RX Receives the DL positioning reference signal (PRS) (DL-PRS) 410. TRP 406 can be used at time T. SRS_RX Receive UL-SRS 412 and at time T PRS_TX Send DL-PRS 410. UE 404 may receive DL-PRS 410 before sending UL-SRS 412, or may send UL-SRS 412 before receiving DL-PRS 410. In both cases, the location server (e.g., location server 168) or UE 404 may base its response on ||T SRS_RX – T PRS_TX | – |T SRS_TX – T PRS_RX || to determine RTT 414. Therefore, multi-RTT positioning can utilize the UE Rx-Tx time difference measurement (i.e., |T) of downlink signals received from multiple TRPs 402, 406 and measured by UE 404. SRS_TX – T PRS_RX |) and DL PRS reference signal received power (RSRP) (DL PRS-RSRP), and the measured TRP Rx-Tx time difference measurement (i.e., |T) of the uplink signal transmitted from UE404 at multiple TRPs 402, 406. SRS_RX – T PRS_TX|) and UL SRS-RSRP. The UE 404 measures the UE Rx-Tx time difference measurements (and / or the DL-PRS-RSRP of the received signal) using assistance data received from the location server, and the TRPs 402, 406 measure the gNB Rx-Tx time difference measurements (and / or the UL-SRS-RSRP of the received signal) using assistance data received from the location server. These measurements can be used at the location server or the UE 404 to determine the RTT, which is used to estimate the location of the UE 404. Other methods for determining the RTT are possible, such as for example using DL-TDOA and / or UL-TDOA measurements.

[0082] PRS can be defined for network-based positioning (e.g., NR positioning) to enable a UE to detect and measure more neighbor transmission and reception points (TRPs) with support for multiple configurations to enable various deployments (e.g., indoor, outdoor, sub-6, mmW, etc.). To support PRS beam operation, beam sweeping can also be configured for PRS. UL positioning reference signals can be based on sounding reference signals (SRS) with enhancements / adjustments for positioning purposes. In some examples, UL-PRS can be referred to as “SRS for positioning,” and new information elements (IEs) can be configured for SRS for positioning in RRC signaling.

[0083] DL PRS-RSRP can be defined as the linear average of the power contributions (in [W]) of resource elements carrying the antenna ports of DL PRS reference signals configured for RSRP measurement over the considered measurement frequency bandwidth. In some examples, for FR1, the reference point for DL PRS-RSRP can be the UE’s antenna connectors. For FR2, DL PRS-RSRP can be measured based on the combined signal from the antenna elements corresponding to a given receiver branch. For FR1 and FR2, if the UE uses receiver diversity, the reported DL PRS-RSRP value can not be lower than the corresponding DL PRS-RSRP of any of the individual receiver branches. Similarly, UL SRS-RSRP can be defined as the linear average of the power contributions (in [W]) of resource elements carrying sounding reference signals (SRS). UL SRS-RSRP can be measured over the considered measurement frequency bandwidth, in the configured measurement occasions, by the configured resource elements. In some examples, for FR1, the reference point for UL SRS-RSRP can be the base station’s (e.g., gNB’s) antenna connectors. For FR2, UL SRS-RSRP can be measured based on the combined signal from the antenna elements corresponding to a given receiver branch. For FR1 and FR2, if the base station uses receiver diversity, the reported UL SRS-RSRP value can not be lower than the corresponding UL SRS-RSRP of any of the individual receiver branches.

[0084] PRS-path RSRP (PRS-RSRPP) can be defined as the linear average of the power of the channel response at the i-th path delay of resource elements carrying the DL PRS signals configured for measurement, where the DL PRS-RSRPP of the 1st path delay is the power contribution corresponding to the first detected path in time. In some examples, a PRS path phase measurement can refer to a phase associated with the i-th path of the channel derived using PRS resources.

[0085] DL-AoD positioning can utilize measured DL-PRS-RSRP of downlink signals received at the UE 404 from multiple TRPs 402, 406. The UE 404 measures the DL-PRS-RSRP of the received signals using assistance data received from a positioning server, and the resulting measurements are used along with the azimuth angle of departure (A-AoD), zenith angle of departure (Z-AoD), and other configuration information to position the UE 404 relative to the neighboring TRPs 402, 406.

[0086] DL-TDOA positioning can utilize the DL Reference Signal Time Difference (RSTD) (and / or DL-PRS-RSRP) of downlink signals received at the UE 404 from multiple TRPs 402, 406. The UE 404 measures the DL RSTD (and / or DL-PRS-RSRP) of the received signals using assistance data received from a positioning server, and the resulting measurements are used along with other configuration information to position the UE 404 relative to the neighboring TRPs 402, 406.

[0087] UL-TDOA positioning can utilize the UL Relative Time of Arrival (RTOA) (and / or UL-SRS-RSRP) of uplink signals sent from the UE 404 at multiple TRPs 402, 406. The TRPs 402, 406 measure the UL-RTOA (and / or UL-SRS-RSRP) of the received signals using assistance data received from a positioning server, and the resulting measurements are used along with other configuration information to estimate the location of the UE 404.

[0088] UL-AoA positioning can utilize the measured Azimuth of Arrival (A-AoA) and Zenith of Arrival (Z-AoA) of uplink signals sent from the UE 404 at multiple TRPs 402, 406. The TRPs 402, 406 measure the A-AoA and Z-AoA of the received signals using assistance data received from a positioning server, and the resulting measurements are used along with other configuration information to estimate the location of the UE 404. For purposes of this disclosure, positioning operations in which the UE provides measurements to a base station / positioning entity / server for use in computing the UE’s position can be described as “UE-assisted,” “UE-assisted positioning,” and / or “UE-assisted position computation,” while positioning operations in which the UE measures and computes its own position can be described as “UE-based,” “UE-based positioning,” and / or “UE-based position computation.”

[0089] Additional positioning methods can be used to estimate the location of the UE 404, such as, for example, UE-side UL-AoD and / or DL-AoA. Note that data / measurement from various techniques can be combined in various ways to increase accuracy, determine and / or enhance determinism, supplement / complement measurements, and / or replace / provide missing information.

[0090] Note that the terms “positioning reference signal” and “PRS” generally refer to specific reference signals used for positioning in NR and LTE systems. However, as used herein, the terms “positioning reference signal” and “PRS” can also refer to any type of reference signal that can be used for positioning, such as but not limited to: PRS as defined in LTE and NR, TRS, PTRS, CRS, CSI-RS, DMRS, PSS, SSS, SSB, SRS, UL-PRS, etc. Furthermore, the terms “positioning reference signal” and “PRS” can refer to downlink or uplink positioning reference signals, unless otherwise indicated by the context. To further distinguish between types of PRS, downlink positioning reference signals can be referred to as “DL PRS,” and uplink positioning reference signals (e.g., SRS, PTRS for positioning) can be referred to as “UL-PRS.” Furthermore, for signals that can be transmitted in both uplink and downlink (e.g., DMRS, PTRS), these signals can be prepended with “UL” or “DL” to distinguish the direction. For example, “UL-DMRS” can be distinguished from “DL-DMRS.” Furthermore, the terms “location” and “positioning” can be used interchangeably throughout the specification, which terms can refer to a specific geographic location or a relative location.

[0091] Figure 5An example 500 of sidelink communication between devices is illustrated. In one example, UE 502 can transmit a sidelink transmission 514 (e.g., including a control channel (e.g., PSCCH) and / or a corresponding data channel (e.g., PSSCH)) that can be received by UEs 504, 506, 508. The control channel can include information (e.g., sidelink control information (SCI)) for decoding the data channel, including reservation information such as information about time and / or frequency resources reserved for the data channel transmission. For example, the SCI can indicate a TTI that can be occupied by the data transmission as well as a number of RBs. The SCI can be used by receiving devices to avoid interference by refraining from transmitting on the reserved resources. In addition to sidelink reception, UEs 502, 504, 506, 508 can each be capable of sidelink transmission. Thus, UEs 504, 506, 508 are illustrated as transmitting sidelink transmissions 513, 515, 516, 520. Sidelink transmissions 513, 514, 515, 516, 520 can be unicast, broadcast, or multicast to nearby devices. For example, UE 504 can transmit sidelink transmissions 513, 515 intended to be received by other UEs within a range 501 of UE 504, and UE 506 can transmit sidelink transmission 516. Additionally or alternatively, RSU 507 can receive communications from and / or transmit communications to UEs 502, 504, 506, 508. One or more of UEs 502, 504, 506, 508 or RSU 507 can include a weather detection component 198 as described in connection with Figure 1

[0092] ​Sidelink communications can be based on one or more transmission modes. In one transmission mode for a first radio access technology (RAT, which can be referred to herein as“mode 4” for the first RAT), a wireless device can autonomously select resources for transmissions. A network entity can allocate one or more sub-channels to a wireless device to use one or more channels to transmit one or more transport blocks (TBs). The wireless device can randomly reserve the allocated resources for one-shot transmissions. The wireless device can use a sensing-based semi-persistent transmission scheme or a semi-persistent scheduling (SPS) mode to select resources for transmissions. For example, before selecting resources for data transmissions, the wireless device can first determine whether the resources have been reserved by another wireless device. Semi-persistent transmissions allow the wireless device to exploit semi-periodic traffic arrival by using historical interference patterns to predict future interference patterns. The wireless device can sense at least one of priority information, energy sensing information, or PSCCH decoding information to optimize resource selection. In one aspect, the wireless device can avoid selecting resources that are scheduled for higher priority packet transmissions for transmissions. In another aspect, the wireless device can rank resources according to how much energy is received and can pick the lowest energy resource. In another aspect, the wireless device can avoid resources for which control is decoded or for which received energy can be above a threshold.

[0093] A network entity can configure a periodicity of a reserved subchannel using DCI transmitted over a PDCCH. The periodicity of the semi-persistent transmission resource can be, for example, 20, 50, 100, 200, 300, 400, 500, 600, 700, 800, 900, or 1000 milliseconds (ms). Such periodicity can be referred to as a resource reservation period (RSVP). In alternative embodiments, the periodicity can be referred to as a resource reservation interval (RRI). A network entity can limit the possible values of the periodicity of the transmission resource. A wireless device, such as a UE, can select a transmission resource based on the periodicity of an arriving packet. A counter can be used to trigger a periodic reselection. For example, a wireless device can randomly select a counter between 5 and 15, and can reserve a resource based on the counter (e.g., 10*counter resource reservation period, number of MAC protocol data unit (PDU) transmissions equal to the counter). After each transmission, or after a reservation period elapses, the counter can be decremented until it reaches zero. For example, in the case of a reservation period of 100 ms and a counter of 10, then the counter can be decremented once every 100 ms until a second elapses, at which point the wireless device can reselect a sidelink resource. In one aspect, the wireless device can reselect a sidelink resource based on a reselection probability value. For example, in response to the counter decrementing to zero, the wireless device can reselect a sidelink resource in x% of the time, and can not reselect a sidelink resource in (1 - x)% of the time, where x < 1. The wireless device can then reset the counter, and repeat the process when the counter again decrements to zero. The wireless device can measure a received signal strength indicator (RSSI) measurement of each 100 ms time slot, and can then calculate an RSSI of a frequency band resource as an average of each of the 10 RSSI measurements taken over a period of a second. The wireless device can select a preferred frequency band resource as the one in the last 20% of the wireless device’s ranked RSSI calculated resources. In some aspects, the counter can be decremented after each MAC PDU transmission. The wireless device can be configured to reselect a sidelink resource after the counter expires (i.e., reaches zero) and a MAC PDU is received.

[0094] Sidelink communications of other RATs can be based on different types or modes of resource allocation mechanisms. In another resource allocation mode of the second RAT, which can be referred to herein as “mode 1” of the second RAT, centralized resource allocation can be provided. For example, a network entity can determine resources for sidelink communications and can allocate the resources to different wireless devices for sidelink transmissions. In this first mode, a wireless device can receive an allocation of sidelink resources from a base station. In a second resource allocation mode, which can be referred to herein as “mode 2,” distributed resource allocation can be provided. In mode 2, each wireless device can autonomously determine resources to use for sidelink transmissions. To coordinate selection of sidelink resources by various wireless devices, each wireless device can use sensing techniques to monitor resource reservations of other sidelink wireless devices and can select resources for sidelink transmissions from resources that are not reserved. Devices communicating based on sidelink can determine one or more radio resources used by other devices in time and frequency domain in order to select transmission resources that avoid collision with other devices.

[0095] Sidelink transmissions and / or resource reservations can be periodic or aperiodic, where a wireless device can reserve resources for transmissions in a current slot and up to two future slots (discussed below).

[0096] Thus, in this second mode (e.g., mode 2), various wireless devices can autonomously select resources for sidelink transmissions, e.g., without a central entity (such as a base station) indicating resources for the devices. A first wireless device can reserve selected resources in order to inform other wireless devices about resources that the first wireless device intends to use for sidelink transmissions.

[0097] In some examples, resource selection for sidelink communications can be based on a mechanism of sensing. For example, a wireless device can determine whether a resource has been reserved by other wireless devices prior to selecting the resource for a data transmission.

[0098] For example, as part of the sensing mechanism for resource allocation mode 2 for the second RAT, a wireless device can determine (e.g., sense) whether a selected sidelink resource has been reserved by other wireless devices before selecting the sidelink resource for data transmission. If the wireless device determines that the sidelink resource has not been reserved by other wireless devices, the wireless device can transmit data using the selected sidelink resource, e.g., in a PSSCH transmission. The wireless device can estimate or determine which radio resources (e.g., sidelink resources) can be in use and / or reserved by other wireless devices by detecting and decoding sidelink control information (SCI) transmitted by other wireless devices. The wireless device can estimate or determine which radio resources are in use and / or reserved by other wireless devices using a sensing-based resource selection algorithm. The wireless device can receive SCI from another wireless device, which can include reservation information based on a resource reservation field in the SCI. The wireless device can continuously monitor (e.g., sense) and decode SCI from peer wireless devices. The SCI can include reservation information, e.g., indicating that a particular wireless device has selected a time slot and RBs for future transmission. The wireless device can exclude resources used and / or reserved by other wireless devices from a candidate resource set used by the wireless device for sidelink transmission, and the wireless device can select / reserve resources for sidelink transmission from resources that are not used and thus form the candidate resource set. The wireless device can continuously perform sensing on SCI with resource reservations in order to maintain a candidate resource set from which the wireless device can select one or more resources for sidelink transmission. Once the wireless device selects a candidate resource, the wireless device can transmit SCI indicating the wireless device’s own reservation of the resource for sidelink transmission. The number of resources (e.g., sub-channels per subframe) reserved by the wireless device can depend on the size of data to be transmitted by the wireless device. Although this example is described with respect to the wireless device receiving reservation information from another wireless device, the reservation information can be received from a RSU or other device communicating based on sidelink.

[0099] Positioning and / or distance of a UE relative to another UE can be determined / estimated based on sidelink (SL) communications. For example, two UEs can determine their locations (e.g., absolute locations) based on a global navigation satellite system (GNSS), and these UEs can exchange their locations (e.g., their geographic longitude and latitude) with each other, such as via vehicle-to-everything (V2X) safety messages. Thus, a UE can obtain or otherwise determine its location based on the GNSS, and can broadcast or otherwise send information about its location in a sidelink message. As such, each of the surrounding UEs can be able to determine the location of the UE that sent its location, and / or can determine the distance between itself and the UE that sent its location. If each of the UEs in an area sends its respective location information, the UEs can determine distances to the surrounding UEs relative to their locations. In another example, UEs can determine their relative distances to another UE and / or their absolute locations (e.g., geographic locations) based on reference signals transmitted and received between the UEs over the sidelink, where such ranging or positioning techniques can be referred to as SL-based ranging or positioning. Distances between UEs can be monitored for various reasons. In some applications, such as V2X, distances between UEs can be monitored as part of collision avoidance, improved road user safety, etc. SL-based ranging or positioning can provide an alternative or additional ranging / positioning mechanism to UEs when GNSS-based positioning is degraded or unavailable (e.g., when a UE is in a tunnel, urban area, canyon, or under a canopy, etc.). For example, SL-based ranging or positioning can be used by UEs for public safety use cases when network services and / or other positioning services are unavailable. In other examples, if GNSS is available, SL-based ranging or positioning can be used by a positioning device in addition to GNSS-based positioning to enhance the accuracy of GNSS-based positioning.

[0100] In addition to GNSS-based positioning and network-based positioning (e.g., as Figure 4Various camera-based positioning have also been developed to provide alternative / additional positioning mechanisms / modes beyond those described. Camera-based positioning (which can also be referred to as “camera-based visual positioning,” “visual positioning,” and / or “vision-based positioning”) is a positioning mechanism / mode that uses images captured by at least one camera to determine the location of a target (e.g., a UE or a vehicle equipped with at least one camera, an object in the field of view of at least one camera, etc.). For example, images captured by a dashboard camera of a vehicle can be used to compute a three-dimensional (3D) position and / or 3D orientation of the vehicle as it moves. For the purposes of this disclosure, a vehicle can refer to something used to transport people or cargo. Examples of vehicles can include cars, trucks, airplanes, trains, carts, etc. Similarly, images captured by a camera of a mobile device can be used to estimate the location of a user of that mobile device or the location of one or more objects in those images. In some implementations, camera-based positioning can provide centimeter-level and 6 degrees of freedom (6DOF) positioning. 6DOF can refer to a representation of how an object moves through 3D space by linear translation or axial rotation (e.g., 6DOF = 3D position + 3D attitude). For example, a single degree of freedom on an object can be controlled by up / down, forward / backward, left / right, pitch, roll, or yaw. Camera-based positioning has great potential for a variety of applications, especially in environments where satellite signals (e.g., GNSS / GPS signals) are degraded / unavailable.

[0101] In some scenarios, images captured by a camera can also be used to improve the accuracy / reliability of other positioning mechanisms / modes (e.g., GNSS-based positioning, network-based positioning, etc.) and / or positioning-related sensors (e.g., IMU, Lidar, radar, etc.), which can be referred to as “vision-aided positioning,” “camera-aided positioning,” “camera-aided location,” and / or “camera-aided perception,” etc. For example, while GNSS and / or an inertial measurement unit (IMU) can provide good positioning performance, overall positioning performance can degrade due to IMU bias drift when GNSS measurement outages occur. Thus, images captured by a camera can provide valuable information to reduce errors. For the purposes of this disclosure, a positioning session (e.g., a period of time in which one or more entities are configured to determine a location of a UE) associated with camera-based positioning or camera-aided positioning can be referred to as a camera-based positioning session or a camera-aided positioning session. In some examples, camera-based positioning and / or camera-aided positioning can be associated with an absolute position of a UE, a relative position of a UE, an orientation of a UE, or a combination thereof.

[0102] Figure 6is a diagram 600 illustrating examples of camera-assisted positioning in accordance with various aspects of the present disclosure. A vehicle 602 can be equipped with a GNSS system and a set of cameras, which can include a front-facing camera 604 (to capture a front view of the vehicle 602), a side-facing camera 606 (to capture a side view of the vehicle 602), and / or a rear-facing camera 608 (to capture a front view of the vehicle 602), among others. The vehicle 602 can also include one or more ranging components. For the purposes of the present disclosure, a ranging component can refer to any device capable of detecting / estimating a distance between a device and one or more objects. For example, a ranging component can be a radar, a camera (if the camera has the ability to determine distances / dept Figure 6 The vehicle 602 is used as an example, but is for illustrative purposes only. The aspects presented herein can also apply to other types of transportation vehicles (e.g., motorcycles, bicycles, buses, trains, etc.), devices (e.g., UEs on a pedestrian, such as a smartphone and a smartwatch), and / or positioning mechanisms / modes (e.g., in combination with GNSS-based positioning, network-based positioning, etc.). Moreover, for the purposes of the present disclosure, a positioning mechanism / mode that uses at least one sensor (e.g., an IMU, a camera) to assist in positioning (e.g., GNSS-based positioning, network-based positioning, etc.) can be referred to as a sensor-fused positioning. Figure 4

[0103] ​A GNSS system can estimate the position of vehicle 602 based on receiving GNSS signals transmitted from multiple satellites (e.g., based on performing GNSS-based positioning). However, when GNSS signals are not available or weak, such as when vehicle 602 is in an urban area or a tunnel, the estimated position of vehicle 602 can become inaccurate. Accordingly, in some implementations, a set of cameras and / or other sensors / ranging components on vehicle 602 can be used to assist with positioning, such as to verify whether a position estimated by a GNSS system based on GNSS signals is accurate. For example, as shown at 610, an image captured by a front-facing camera 604 of vehicle 602 can include / identify a particular building 612 (which can also be referred to as a feature) having a known position, and vehicle 602 (or a GNSS system or a positioning engine associated with vehicle 602) can determine / verify whether a position (e.g., longitude and latitude coordinates) estimated by the GNSS system is close to the known position of that particular building 612. Accordingly, with the assistance of cameras, the accuracy and reliability of GNSS-based positioning can be further improved. For purposes of this disclosure, a GNSS system associated with a camera (e.g., capable of performing camera-assisted / camera-based positioning) can be referred to as a “GNSS+camera system,” or (if the GNSS system is also associated with / includes at least one IMU) a “GNSS+IMU+camera system.”

[0104] In some examples, software or an application that accepts positioning-related measurements from a GNSS chipset and / or sensors to estimate a position, velocity, and / or altitude of a device can be referred to as a “positioning engine.” Moreover, a positioning engine that is capable of achieving a certain level of high accuracy (e.g., centimeter / dime ter-level accuracy) and / or latency can be referred to as a precise positioning engine (PPE). For example, a positioning engine that is capable of performing real-time kinematic (RTK) (e.g., receiving or processing correction data associated with RTK) can be considered a PPE. Another example of a PPE is a positioning engine that is capable of performing precise point positioning (PPP). PPP is a positioning technique that removes or models GNSS system errors to provide a high level of positioning accuracy from a single receiver.

[0105] While ranging components (such as Lidar and / or cameras) on a device (e.g., a UE, a vehicle, etc.) can be used to detect / estimate a distance between the device and one or more objects (or features of an object), the accuracy of the ranging component can be impacted by weather conditions. For example, adverse weather conditions such as rain, fog, and / or snow can degrade the performance of the ranging component. In some examples, performance can also be referred to as “perception performance” (e.g., the ability of a device to perceive information related to its surrounding environment). Examples of perception performance can include the object detection rate of an autonomous vehicle, the ability to quantify / detect changes in control characteristics (e.g., tire friction) from visual features, etc. For purposes of the present disclosure, adverse weather or adverse weather conditions can refer to disruptive or potentially disruptive weather events or environmental conditions, which can include, but are not limited to, rain, snow, fog, smog, air pollution, volcanic eruptions, hurricanes, floods, blizzards, disease, wildfires, extreme heat, and extreme cold, etc. Thus, adverse weather or adverse weather conditions can not be limited to natural causes, but can also include man-made causes (e.g., pollution). In some scenarios, detecting the presence of adverse weather conditions based on the use of cameras can be challenging due to motion blur and buildup on the lens, which can be caused by objects / attributes associated with adverse weather conditions (e.g., raindrops, snowflakes, ash, pollutants, etc.). On the other hand, non-adverse weather conditions (which can also be referred to as “good weather conditions,” “normal weather conditions,” and / or “clear weather conditions,” etc.) can refer to weather conditions that do not result in potential damage caused by adverse weather conditions.

[0106] Figure 7A FIG. 700A is a diagram 700A illustrating an example of camera vision under good / normal (e.g., non-adverse) weather conditions, in accordance with various aspects of the present disclosure. Under good / normal weather conditions, images captured by a camera can depict objects (e.g., cars, trees, pedestrians, etc.) in the image with a certain level of clarity (e.g., with clear / complete outlines of the objects). Figure 7B FIG. 700B is a diagram 700B illustrating an example of camera vision under adverse weather conditions, in accordance with various aspects of the present disclosure. On the other hand, under adverse weather conditions, images captured by a camera can be completely or at least partially obscured by objects / particles associated with the adverse weather conditions (e.g., snowflakes, raindrops, fog / smog particles, volcanic ash, etc.).

[0107] Figure 8Ais a diagram 800A illustrating examples of point clouds generated by Lidar sensors under good / normal (e.g., non-inclement) weather conditions, in accordance with various aspects of the present disclosure. Lidar (an acronym for light detection and ranging) is a ranging component / device that is capable of emitting / illuminating a laser light from a source (e.g., emitter), where the emitted / illuminated laser light can reflect off one or more objects in a scene / environment. The reflected light can then be detected by a receiver of the Lidar, and a time of flight (TOF) of the laser light can be used to render a distance map of the one or more objects in the scene. In some examples, as shown at 802, the distance map of the one or more objects (or surfaces of the one or more objects) can be represented by a set of points (e.g., a set of three-dimensional (3D) coordinates (X, Y, Z)), which can be referred to as a “point cloud.” Thus, a point cloud can be 3D machine / computer vision that captures the position and shape of an object in a format suitable for processing by a computer or programmable logic controller (PLC) / programmable automation controller (PAC). As shown at 802, under good / normal weather conditions, the point clouds generated by the Lidar sensors for a set of objects (e.g., a cone, a cylinder, and a cuboid) can depict the shapes (e.g., surfaces) of the set of objects with a certain degree of clarity.

[0108] Figure 8B is a diagram 800B illustrating examples of point clouds generated by Lidar sensors under inclement weather conditions, in accordance with various aspects of the present disclosure. On the other hand, as shown at 804, under inclement weather conditions (such as a rainy day), the point clouds generated by the Lidar sensors for the set of objects can be affected by raindrops. Thus, the point clouds can fail to depict the shapes (e.g., surfaces) of the set of objects with a good degree of clarity.

[0109] In some examples, while certain devices can be configured to detect inclement weather conditions based on their associated physical properties (e.g., detect a snowy day based on physical properties of snow), such devices typically do not utilize large public datasets. Moreover, certain devices that are Lidar sensors can be configured to process a single point cloud for various purposes (such as for ranging detection), they typically do not utilize / analyze a sequence of consecutive point clouds.

[0110] The aspects presented herein can improve the accuracy and performance of ranging operations and / or positioning operations by enabling devices, sensors, and / or components used for ranging / positioning operations to detect / determine weather conditions, such as adverse weather conditions, in real-time. By enabling devices / sensors / components to detect adverse weather conditions in real-time, UEs (e.g., smartphones, vehicles, autonomous vehicles, etc.) can be able to make more suitable scene reasoning and perform more appropriate control strategies in the presence of detected adverse weather conditions. For example, in one aspect of the disclosure, a set of point clouds can be projected into a range view and thus considered a two-dimensional (2D) tensor. Similarly, a sequence of range images can be considered a 3D tensor. The sparsity of the tensor can be quantified as the LI norm of the Fast Fourier Transform (FFT) or Discrete Wavelet Transform (DWT) coefficients. By applying the FFT and / or DWT to the sequence of range images, the sparsity of the scene can be quantified, where a more sparse scene can indicate a lower likelihood of adverse weather. In other words, by quantifying the sparsity of the scene, the presence of adverse weather conditions can be identified. Moreover, in another aspect of the disclosure, camera images collected during adverse weather conditions, although possibly blurry, can still be incorporated into a self-supervised manner (e.g., for machine learning / artificial intelligence). For the purposes of the present disclosure, FFT can refer to an algorithm that computes the Discrete Fourier Transform (DFT) or the inverse Discrete Fourier Transform (IDFT) of a sequence. For example, Fourier analysis can convert a signal from its original domain (usually time or space) to a representation in the frequency domain and vice versa. The DFT can obtain by decomposing a sequence of values into components of different frequencies. The DWT can refer to any wavelet transform that discretely samples the wavelet. Like other wavelet transforms, one of its distinctions from the Fourier transform is the time resolution, e.g., it is able to capture both frequency and location information (time position). The FFT coefficients can refer to the values obtained from the FFT (e.g., coefficients). For example, when the FFT is applied to a signal, the FFT computation can be referred to as a complex number set of coefficients. These coefficients (e.g., FFT coefficients) can represent the amplitude and phase information of different frequency components present in the signal. The FFT coefficients can not have any time aspect as they can take the entire signal as input. Thus, applying the FFT to a signal, one can only know the contribution (e.g., amplitude) from each frequency, but can not pinpoint the location in time where a particular frequency occurs. On the other hand, the DWT coefficients can refer to the values obtained from the DWT (e.g., coefficients). When the DWT is applied to a signal, the DWT decomposes that signal into a series of coefficients at different levels or scales. Each level can represent different levels of detail or frequency bands. The DWT can produce a set of approximation coefficients (e.g., representing low frequency components) and detail coefficients (e.g., representing high frequency components) for each level of decomposition. Thus, the DWT coefficients can contain time information of the analyzed signal.

[0111] Depending on the context, sparsity can refer to a fact or condition that is sparsely distributed rather than densely or profusely dispersed or densely distributed. In some examples, sparsity can also refer to the density of a condition and is used interchangeably with the term "density." For example, in some contexts, the sparsity of FFT / DWT coefficients can also refer to the density of FFT / DWT coefficients. A distance image can refer to an image that provides distance information between an object / feature and a reference point. For example, a distance image can be a type of digital image where each pixel of the distance image represents the distance between a known reference frame and a visible point in the scene. Thus, a distance image can reproduce the 3D structure of a scene. In other words, a distance image is a representation of a scene or object that provides information about the distance from a sensor to various points in the scene. Distance images are commonly used in fields such as computer vision, robotics, and 3D imaging. Distance images can be obtained using distance sensing techniques such as LiDAR or depth cameras. These sensors can be configured to emit signals (e.g., laser beams, infrared light, etc.) and measure the time required for these signals to bounce off an object in the scene. Based on the time-of-flight or phase shift of the returned signal, a sensor can calculate the distance to different points in a scene. Furthermore, a tensor can refer to a container of data, where the data can be numbers or characters. Tensors can be represented as array data structures. Tensors can be used to represent data in a variety of ways, including as sequences, as graphs, or as sets of points in space. In data science and machine learning (ML) or artificial intelligence (AI), tensors can be used to represent high-dimensional data. Tensors can also be used to represent complex relationships between variables. For example, in machine learning, tensors can be used to represent the weights of a neural network. In some examples, a two-dimensional (2D) array (which can also be called a matrix) can be called a 2D tensor. Similarly, a three-dimensional (3D) array can be called a 3D tensor. The L1 norm (or L1 normalization) can refer to the sum of the set of absolute values ​​(or absolute vector values), where the absolute value of a scalar can be represented by the symbol |a1|.

[0112] Figure 9 , Figure 10 and Figure 11 Figures 900, 1000, and 1100 respectively illustrate examples of identifying / detecting weather conditions based on scene-based sparsity according to various aspects of this disclosure. A UE 902 (e.g., a smartphone, vehicle, vehicle UE, autonomous vehicle, etc.) may be associated with / equipped with one or more ranging components 904 (such as a set of Lidar sensors). As shown at 906 (and also in conjunction with...) Figure 8AAs described, one or more ranging components 904 can detect the distance to one or more objects 908 (or features of one or more objects 908) in their vicinity and can generate a point cloud representing those objects / features. For the purposes of this disclosure, the vicinity of UE 902 (e.g., including one or more objects 908) can be collectively referred to as the scene or environment around UE 902.

[0113] In one aspect, such as Figure 9 As shown at 930, in order for UE 902 to be able to identify / detect weather conditions based on the sparsity of the scene / environment, UE 902 may, for example, first convert a point cloud (e.g., 3D points) generated from one or more ranging components 904 into a set of distance images using spherical projection. Spherical projection (also referred to as front view projection in some examples) can refer to a way of representing 3D point cloud data as 2D image data, and therefore spherical projection can also act as a dimensionality reduction method. In other words, UE 902 can convert a 3D point cloud into a 2D image by using spherical projection. In one example, as shown at 910, the 2D image (or 2D distance image) may include a distance channel that shows the distance of one or more objects 908 to UE 902 (or to one or more ranging components 904). For example, the distance of one or more objects 908 to UE 902 can be represented by different colors, where a darker color indicates that the object (or the point representing the object) is closer to UE 902, and a lighter color indicates that the object (or the point representing the object) is farther away from UE 902 compared to the darker color. In another example, as shown at 912, the 2D image (or 2D distance image) may include an intensity channel that shows the intensity of one or more objects 908 relative to UE 902 (or from one or more ranging components 904). Intensity can refer to the brightness of the reflected laser signal. For example, objects that tend to reflect light / laser beams (e.g., road / parking signs, peepholes, road / lane markings, etc.) can be represented by a brighter color, while objects that tend to absorb light or not reflect light (e.g., black paint, coal, etc.) can be represented by a darker / less brighter color compared to objects that tend to reflect light.

[0114] like Figure 10 As shown at 940, after UE 902 converts the point cloud into a distance image set, UE 902 can apply Fast Fourier Transform (FFT) and / or Discrete Wavelet Transform (DWT) to the distance image set and convert the distance image set into an FFT / DWT coefficient set (which can also be in the form of an image), as shown at 914.

[0115] Then, as Figure 11As shown at 950, after converting the set of range images to a set of FFT / DWT coefficients, the UE 902 can quantify the level of the adverse weather condition based on the set of FFT / DWT coefficients. In one example, as shown at 916, each range image in the set of range images or its corresponding overall FFT / DWT coefficients can include two parts: scene and noise. As shown at 918, the FFT / DWT coefficients of the scene, which can include one or more objects 908 (e.g., buildings, road surface, vehicles, pedestrians, etc.), can be sparse coefficients. On the other hand, as shown at 920, the FFT / DWT coefficients of the noise (e.g., referring to things / particles associated with the adverse weather condition, such as droplets, fog, snowflakes, etc.) can be dense / denser coefficients compared to the scene. Thus, the UE 902 can be able to identify whether the range image is associated with only the scene (e.g., can be under good / normal weather condition) or both the scene and the noise (e.g., can be under adverse weather condition) based on the sparsity of the FFT / DWT coefficients.

[0116] In other words, since FFT and DWT can generate sparse representation for undamaged images (e.g., scene without noise) and dense representation for noise, they can be used to identify the weather condition. For example, the sparsity of the FFT / DWT coefficients can be measured by L1 norm, and the total coefficients can be used as an indicator of the presence of noise. Then, given a similar scene, when the noise level increases, the total coefficients can become denser. On the other hand, having sparser total coefficients can indicate lower level of noise from adverse weather condition.

[0117] Figure 12is a plot 1200 illustrating an example relationship between the LI norm of the FFT / DWT coefficients and the weather condition according to various aspects of the present disclosure. Generally, noisy range images (e.g., referring to images that are corrupted by bad weather conditions) tend to be denser. Thus, their FFT / DWT coefficients can have a larger LI norm. Conversely, point clouds / range images with lower LI norm of the FFT / DWT coefficients can not be corrupted (e.g., not by bad weather conditions). For example, as shown at 1202, a point cloud without noise can have a low LI norm of the FFT / DWT coefficients, which can indicate a good / normal weather condition. As shown at 1204, the LI norm of the FFT / DWT coefficients of a point cloud with some noise can be higher compared to a point cloud without noise, which can indicate the presence of a moderate bad weather condition (e.g., moderate snow, moderate rain, etc.). As shown at 1206 and 1208, the LI norm of the FFT / DWT coefficients of a point cloud with a high level of noise can be much higher compared to a point cloud without noise or with some noise, which can indicate the presence of a severe bad weather condition (e.g., a blizzard, a hurricane, etc.). Thus, in some scenarios, the granularity of the weather condition can be proportional to the LI norm of the FFT / DWT coefficients (e.g., the higher the LI norm, the more severe the bad weather condition).

[0118] In some implementations, after the UE 902 detects and identifies the weather condition in a scene / region (e.g., based on the sparsity of the LI norm of the FFT / DWT coefficients derived from the range images of the scene / region), the UE 902 can send the detected / identified weather condition of the scene / region to a server (e.g., a location server, a crowdsourcing server, etc.). This information can be shared with other UEs in (or close to / heading towards) the scene / region, so that these UEs can be aware of the weather condition, which can be helpful for UEs that are unable to identify the weather condition. For example, after an autonomous vehicle (e.g., through a server) learns of a bad weather condition in a region, the autonomous vehicle can apply suitable driving settings / parameters when entering the region. In some examples, after the UE 902 detects and identifies the weather condition, the UE 902 can also modify certain parameters based on the identified weather condition. For example, if the UE 902 is a vehicle, such as an autonomous vehicle, the UE 902 can modify its driving / control parameters and / or safety features based on the identified weather condition.

[0119] Figure 13is a diagram 1300 illustrating an example of detecting adverse weather conditions using multiple range images from multiple ranging components, in accordance with various aspects of the present disclosure. In another aspect of the present disclosure, when one or more ranging components (e.g., Lidar sensors) are configured to capture / obtain a series of consecutive range images (e.g., via multiple timestamps) and / or capture / obtain a set of range images via multiple ranging components, the UE 902 can use multiple frames from the series of consecutive range images (e.g., taken by one ranging component) to enhance temporal consistency (and accuracy of adverse weather detection) in addition to the single frame representation of range images (e.g., weather condition identification using a range image from one timestamp or one time point) as shown. For example, multiple range images generated from different timestamps of one or more Lidar sensors can be more accurate (for detecting adverse weather) than a range image generated from one time point. In some examples, the multi-frame representation (e.g., using multiple range images from multiple timestamps) can specify that the UE 902 uses a 3D FFT and / or a 3D DWT to convert the range images into FFT / DWT coefficients. Similarly, high / denser FFT / DWT coefficients can indicate that an adverse weather condition is present, and low / sparser FFT / DWT coefficients can indicate that a normal / non-adverse weather condition is present. Figure 11

[0120] In some configurations, when a vehicle is equipped with multiple ranging components (e.g., multiple Lidar sensors), each ranging component can be configured to be associated with a confidence level or weight, and different ranging components can have different confidences. For example, if a vehicle includes a first Lidar sensor and a second Lidar sensor, where the first Lidar sensor is less costly (and thus can have lower accuracy) than the second Lidar sensor, the second Lidar sensor can be assigned a higher confidence level or weight, and the first Lidar sensor can be assigned a lower confidence level or weight (than the second Lidar sensor). Then, if both Lidar sensors are used to compute sparsity (of a scene), a final sparsity can be computed based on the confidence levels / weights, e.g., final sparsity = weight of first Lidar sensor * (sparsity estimate from first Lidar sensor) + weight of second Lidar sensor * (sparsity estimate from second Lidar sensor), where the “weight of second Lidar sensor” and the “weight of second Lidar sensor” are weights (i.e., confidence levels) that add up to one or a specified number. Thus, aspects presented herein can be applied to multiple ranging components with different costs and accuracies, which can reduce implementation costs of the present disclosure. ​

[0121] In some implementations, if a vehicle is equipped with multiple ranging components associated with different confidence levels (e.g., with different accuracies and costs), the vehicle can also be configured to use ranging components with a confidence level above a confidence level threshold. Thus, the vehicle can avoid using ranging components with a low confidence level that can impact the accuracy of weather condition detection.

[0122] In another aspect of the disclosure, based on enabling a device (e.g., UE 902) to detect and identify weather conditions in a scene based on sparsity associated with the scene (or associated with FFT / DWT coefficients derived from the scene), a range image from a ranging component (e.g., one or more ranging components 904) can be merged with a camera image for contrastive representation learning. Contrastive representation learning (or simply contrastive learning) can refer to a technique that enhances the performance of visual tasks by learning attributes that are common among data classes and attributes that separate data classes from each other using the principle of contrasting samples with each other.

[0123] For example, camera images (e.g., captured by one or more cameras associated with a device) in adverse weather conditions can be blurry due to lens accretions (e.g., liquid droplets, snowflakes, and / or fog particles obstructing the lens), but they can still provide useful information (e.g., for identifying traffic lights, moving objects, etc.). Thus, range images (such as the Lidar range images described in connection with Figure 9 and Figure 10 The LI norm of the described Lidar range images) can be used to construct positive and negative pairs of triplets loss with a learnable feature extractor. Triplets loss can refer to a way of teaching a machine learning (ML) / artificial intelligence (AI) model how to identify similarities or differences between items. Triplets loss can use groups of three items called triplets, which consist of an anchor item (denoted by (A)), a similar item (positive, denoted by (P)), and a dissimilar item (negative, denoted by (N)).

[0124] Figure 14 is a diagram 1400 illustrating an example of merging camera images with range images for contrastive representation learning in accordance with various aspects of the disclosure. In one example, a triplets loss function (with a learnable feature extractor) can be described by a Euclidean distance function (f): As shown at 1402, a positive and negative pair of triplets loss can be constructed using a group of three range images, where a first range image (range image 1) can be associated with adverse weather (e.g., snowfall), a second range image (range image 2) can be associated with adverse weather (e.g., snowfall), and a third range image (range image 3) can be associated with normal / non-adverse weather (e.g., sunny day). Based on the range images being associated with different weather conditions, the triplets loss function can be used to learn a feature extractor that can be used to identify adverse weather conditions in a scene. Figure 11The described L1-norm of the FFT / DWT coefficients of the obtained range images, the first range image and the second range image (also anchor points) can form a positive pair because their L1-norms can be similar / close to each other, and the second image and the third image can form a negative pair because they can have different levels of L1-norms. Based on the pairing, corresponding camera images (e.g., taken by a camera at the same time and same / similar geographic location as the range images from the Lidar sensor) can be used to provide useful information and / or extract features (e.g., on the same vehicle with a camera and a Lidar sensor, or on different vehicles driving in the same city, etc.), as shown at 1404. For example, by knowing that a camera image is associated with certain weather conditions, an AI / ML module can be configured to learn the inherent properties (e.g., blur, color / intensity distribution, etc.) of different weather conditions to help downstream tasks, such as developing a robust object detector that performs equally well under different weather conditions. The feature extractor can thus be used for downstream tasks, such as initializing an encoder of a 3D object detection network.

[0125] Aspects presented herein can improve the performance of ranging components / devices. For example, the perception performance of an autonomous vehicle is degraded under adverse weather. It can be challenging to use a camera to detect the presence of adverse weather due to motion blur and accretions (due to liquid droplets and snowflakes). Conventional methods model the physical properties of snowfall but fail to leverage public datasets. Further, conventional methods focus on processing a single point cloud, rather than a sequence of consecutive point clouds. Aspects described herein can propose projecting a point cloud into a field of view and thus be considered a 2D tensor. The sparsity of a scene can be determined by applying FFT and DWT techniques to a range image or a set of range images, and by quantifying the sparsity, the presence of an adverse weather condition can be identified.

[0126] Aspects presented herein can not specify any physical model of adverse weather conditions, meaning that it can be easily generalized to different ranging component (e.g., Lidar sensor) configurations as long as data (e.g., range images) is available. Unlike other data-driven methods, aspects presented herein can be unsupervised, meaning that it can not specify ground truth labels. Aspects presented herein can quantify the amount of sensory degradation at a fine-grained level, rather than acting as a binary classifier (e.g., detecting the severity of a weather condition, rather than classifying the weather as good or bad). Aspects presented herein can be formulated as a multi-frame method, enhancing temporal consistency. Aspects presented herein can also be extended to incorporate camera images if such data is available.

[0127] Based on the quality of the output predictions, the aspects presented in this paper can be applied to sensor suites equipped on vehicles. The computational specifications of the aspects presented in this paper are likely minimal and can be deployed on low-cost digital signal processors (DSPs). The aspects presented in this paper enable downstream planning algorithms to switch / adjust to weather-specific control strategies for safe navigation in adverse weather conditions. If camera images are available, image feature extractors can be trained for downstream vision-based tasks, including (but not limited to) initializing encoders for 3D object detection networks.

[0128] Figure 15 This is a flowchart 1500 of a wireless communication method. This method can be performed by a UE (e.g., UE 104, 404, 502, 506, 508, 902; vehicle 602; device 1704). This method enables the UE to detect and identify weather conditions based on the sparsity of FFT / DWT coefficients derived from a distance image set.

[0129] At position 1504, the UE can convert a set of point clouds associated with the environment into a set of distance images based on spherical projection, such as combining... Figures 9-13 As described. For example, such as Figure 9 As shown at 930, UE 902 can convert a point cloud into a set of distance images based on spherical projection. This conversion of the point cloud set can be performed by, for example... Figure 17 The device 1704 is executed by a weather detection component 198, one or more sensor modules 1718 (e.g., one or more Lidar sensors), a camera 1732, a transceiver 1722, a cellular baseband processor 1724, and / or an application processor 1706.

[0130] At 1506, the UE can apply at least one of FFT or DWT to the distance image set to obtain an FFT coefficient set or a DWT coefficient set, such as combining... Figures 9-13 As described. For example, such as Figure 10 As shown at 940, UE 902 can apply FFT and / or DWT to the distance image set to obtain an FFT / DWT coefficient set. This application of the FFT or the DWT can be performed by, for example... Figure 17 The device 1704 is executed by a weather detection component 198, one or more sensor modules 1718 (e.g., one or more Lidar sensors), a camera 1732, a transceiver 1722, a cellular baseband processor 1724, and / or an application processor 1706.

[0131] At 1510, the UE can identify the level of the environmental condition based on the sparsity of the FFT coefficient set or the DWT coefficient set, such as by combining... Figures 9-13 As described. For example, such asFigure 11 and Figure 12 As shown at 950, the UE 902 can determine a weather condition based on a sparsity of the FFT / DWT coefficients. The identification of the level of the condition of the environment can be performed by, for example, the weather detection component 198 of the apparatus 1704, one or more sensor modules 1718 (e.g., one or more Lidar sensors), the camera 1732, the transceiver 1722, the cellular baseband processor 1724, and / or the application processor 1706 in Figure 17

[0132] In one example, the condition can be a severe weather condition or a clear weather condition, and to identify the level of the condition of the environment, the UE can identify the level of the severe weather condition or the clear weather condition.

[0133] In another example, the sparsity of the set of FFT coefficients or the set of DWT coefficients can be based on an LI norm.

[0134] In another example, the condition can be a severe weather condition, and the severe weather condition is more severe in a case where the set of FFT coefficients or the set of DWT coefficients is more dense compared to a case where the set of FFT coefficients or the set of DWT coefficients is less dense.

[0135] In another example, the set of point clouds corresponds to a 3D visualization of the environment that includes a plurality of georeferenced points.

[0136] In another example, the UE can modify at least one control parameter of a vehicle based on the identification of the level of the condition of the environment.

[0137] In another example, the UE can obtain, prior to the transformation of the set of point clouds, the set of point clouds associated with the environment from at least one sensor, where the transformation of the set of point clouds can be based on the obtained set of point clouds, such as described in connection with Figures 9-13 Figure 9 As shown, the UE 902 can obtain a point cloud of one or more objects 908 using one or more ranging components 904. The obtaining of the set of point clouds can be performed by, for example, the weather detection component 198 of the apparatus 1704, one or more sensor modules 1718 (e.g., one or more Lidar sensors), the camera 1732, the transceiver 1722, the cellular baseband processor 1724, and / or the application processor 1706 in Figure 17 ​​the weather detection component 198 of the apparatus 1704 in FIG. 17, one or more sensor modules 1718 (e.g., one or more Lidar sensors), the camera 1732, the transceiver 1722, the cellular baseband processor 1724, and / or the application processor 1706. In some implementations, the at least one sensor includes at least one light detection and ranging (Lidar) sensor. In some implementations, the UE can obtain the set of range images via a plurality of timestamps of the one or more Lidar sensors, and to apply at least one of the FFT or the DWT to the set of range images, the UE can apply at least one of a three-dimensional (3D) FFT or a 3D DWT to the set of range images.

[0138] In another example, the UE can detect the sparsity of the set of FFT coefficients or the set of DWT coefficients prior to the identification of the level of the condition of the environment, where the identification of the level of the condition of the environment is based on the detected sparsity of the set of FFT coefficients or the set of DWT coefficients, such as described in connection with Figures 9-13 Figure 12 For example, as shown in FIG. 9, the UE 902 can detect sparsity of FFT / DWT coefficients of a scene / environment, where the weather condition (or the level of the inclement weather condition) can be based on the sparsity of the FFT / DWT coefficients or the set of DWT coefficients. The detection of the sparsity of the set of FFT / DWT coefficients can be performed by, for example, Figure 17 the weather detection component 198 of the apparatus 1704 in FIG. 17, one or more sensor modules 1718 (e.g., one or more Lidar sensors), the camera 1732, the transceiver 1722, the cellular baseband processor 1724, and / or the application processor 1706.

[0139] In another example, the UE can output an indication of an identified level of the condition of the environment, the identified level based on the sparsity of the set of FFT coefficients or the set of DWT coefficients, such as described in connection with Figures 9-13 For example, the UE 902 can use the identified weather condition to set or modify a driving-related parameter, or provide the identified weather condition to a server. The output of the indication can be performed by, for example, Figure 17 ​the weather detection component 198 of the apparatus 1704 in FIG. 17, one or more sensor modules 1718 (e.g., one or more Lidar sensors), the camera 1732, the transceiver 1722, the cellular baseband processor 1724, and / or the application processor 1706. In some implementations, to output the indication of the identified level of the condition of the environment, the UE can transmit the indication of the identified level of the condition of the environment, or the UE can store the indication of the identified level of the condition of the environment in a memory or cache.

[0140] In another example, the UE can use at least one camera to capture an image of the environment, and pair the captured image with at least one other image based on the sparsity of the set of FFT coefficients or the set of DWT coefficients, such as described in connection with Figure 14 For example, as shown at 1402, a set of three range images can be used to construct positive and negative pairs of the triplet loss. Based on the pairing, at 1404, corresponding camera images (e.g., taken by a camera at approximately the same time as the range images from a Lidar sensor) can be used to provide useful information and / or extract features. The capture of the images and / or the pairing of the captured images can be performed by, for example, Figure 17 the weather detection component 198 of the apparatus 1704 in FIG. 17, one or more sensor modules 1718 (e.g., one or more Lidar sensors), the camera 1732, the transceiver 1722, the cellular baseband processor 1724, and / or the application processor 1706. In some implementations, the UE can train an artificial intelligence (AI) / machine learning (ML) (AI / ML) model to identify a set of features of the environment based on the pairing of the captured image with the at least one other image.

[0141] Figure 17 is a flow diagram of a method of wireless communication 1600. The method can be performed by a UE (e.g., the UE 104, 404, 502, 506, 508, 902; the vehicle 602; the apparatus 1704). The method can enable the UE to detect and identify a weather condition based on sparsity of FFT / DWT coefficients derived from a set of range images.

[0142] At 1604, the UE can convert a set of point clouds associated with an environment into a set of range images based on a spherical projection, such as described in connection with Figure 3 For example, as shown at 930 of FIG. 9, the UE 902 can convert a set of point clouds into a set of range images based on a spherical projection. The conversion of the set of point clouds can be performed by, for example, ​ ​ ​The device 1704 is executed by a weather detection component 198, one or more sensor modules 1718 (e.g., one or more Lidar sensors), a camera 1732, a transceiver 1722, a cellular baseband processor 1724, and / or an application processor 1706.

[0143] At 1606, the UE can apply at least one of FFT or DWT to the distance image set to obtain an FFT coefficient set or a DWT coefficient set, such as combining... ​ As described. For example, such as ​ As shown at 940, UE 902 can apply FFT and / or DWT to the distance image set to obtain an FFT / DWT coefficient set. This application of the FFT or the DWT can be performed by, for example... ​ The device 1704 is executed by a weather detection component 198, one or more sensor modules 1718 (e.g., one or more Lidar sensors), a camera 1732, a transceiver 1722, a cellular baseband processor 1724, and / or an application processor 1706.

[0144] At 1610, the UE can identify the level of the environmental condition based on the sparsity of the FFT coefficient set or the DWT coefficient set, such as by combining... ​ As described. For example, such as ​ and ​ As shown at 950, UE 902 can determine weather conditions based on the sparsity of FFT / DWT coefficients. The identifier for this level of this environmental condition can be, for example... ​ The device 1704 is executed by a weather detection component 198, one or more sensor modules 1718 (e.g., one or more Lidar sensors), a camera 1732, a transceiver 1722, a cellular baseband processor 1724, and / or an application processor 1706.

[0145] In one example, the condition could be severe weather or clear weather, and in order to identify the level of the condition of the environment, the UE could identify the level of the severe weather or the clear weather.

[0146] In another example, the sparsity of the FFT coefficient set or the DWT coefficient set may be based on the L1 norm.

[0147] In another example, the condition could be severe weather, and the severe weather would be more severe in the case of a denser FFT coefficient set or DWT coefficient set compared to a case where the FFT coefficient set or DWT coefficient set is less dense.

[0148] In another example, the set of point clouds corresponds to a three-dimensional (3D) visualization of the environment that includes a plurality of geo-referenced points.

[0149] In another example, the UE can modify at least one control parameter of a vehicle based on the identification of the level of the condition of the environment.

[0150] In another example, as shown at 1602, the UE can obtain, prior to the transformation of the set of point clouds, the set of point clouds associated with the environment from at least one sensor, where the transformation of the set of point clouds can be based on the obtained set of point clouds, such as described in connection with ​ FIG. 16, for example, as shown, UE 902 can obtain a set of point clouds of one or more objects 908 using one or more ranging components 904. The obtaining of the set of point clouds can be performed by, for example, weather detection component 198 of apparatus 1704 in ​ FIG. 17, for example, as shown, UE 902 can obtain a set of point clouds of one or more objects 908 using one or more ranging components 904. The obtaining of the set of point clouds can be performed by, for example, weather detection component 198 of apparatus 1704 in ​ In some implementations, the at least one sensor includes at least one light detection and ranging (Lidar) sensor. In some implementations, the UE can obtain the set of range images via a plurality of timestamps of the one or more Lidar sensors, and to apply at least one of the FFT or the DWT to the set of range images, the UE can apply at least one of a three-dimensional (3D) FFT or a 3D DWT to the set of range images.

[0151] In another example, as shown at 1608, the UE can detect, prior to the identification of the level of the condition of the environment, the sparsity of the set of FFT coefficients or the set of DWT coefficients, where the identification of the level of the condition of the environment is based on the detected sparsity of the set of FFT coefficients or the set of DWT coefficients, such as described in connection with ​ FIG. 16, for example, as shown, UE 902 can obtain a set of point clouds of one or more objects 908 using one or more ranging components 904. The obtaining of the set of point clouds can be performed by, for example, weather detection component 198 of apparatus 1704 in ​ FIG. 17, for example, as shown, UE 902 can obtain a set of point clouds of one or more objects 908 using one or more ranging components 904. The obtaining of the set of point clouds can be performed by, for example, weather detection component 198 of apparatus 1704 in ​ In some implementations, the at least one sensor includes at least one light detection and ranging (Lidar) sensor. In some implementations, the UE can obtain the set of range images via a plurality of timestamps of the one or more Lidar sensors, and to apply at least one of the FFT or the DWT to the set of range images, the UE can apply at least one of a three-dimensional (3D) FFT or a 3D DWT to the set of range images.

[0152] In another example, as shown at 1612, the UE can output an indication of the identified level of the condition of the environment, the identified level based on the sparsity of the set of FFT coefficients or the set of DWT coefficients, such as described in connection with ​ The output of the indication can be performed by, for example, the weather detection component 198 of the apparatus 1704 in FIG. 13B, the one or more sensor modules 1718 (e.g., one or more Lidar sensors), the camera 1732, the transceiver 1722, the cellular baseband processor 1724, and / or the application processor 1706. In some implementations, to output the indication of the identified level of the condition of the environment, the UE can transmit the indication of the identified level of the condition of the environment, or the UE can store the indication of the identified level of the condition of the environment in a memory or cache. ​ The output of the indication can be performed by, for example, the weather detection component 198 of the apparatus 1704 in FIG. 13B, the one or more sensor modules 1718 (e.g., one or more Lidar sensors), the camera 1732, the transceiver 1722, the cellular baseband processor 1724, and / or the application processor 1706. In some implementations, to output the indication of the identified level of the condition of the environment, the UE can transmit the indication of the identified level of the condition of the environment, or the UE can store the indication of the identified level of the condition of the environment in a memory or cache.

[0153] In another example, as shown at 1614, the UE can capture an image of the environment using at least one camera, and pair the captured image with at least one other image based on the sparsity of the set of FFT coefficients or the set of DWT coefficients, such as described in connection with ​ The output of the indication can be performed by, for example, the weather detection component 198 of the apparatus 1704 in FIG. 13B, the one or more sensor modules 1718 (e.g., one or more Lidar sensors), the camera 1732, the transceiver 1722, the cellular baseband processor 1724, and / or the application processor 1706. In some implementations, to output the indication of the identified level of the condition of the environment, the UE can transmit the indication of the identified level of the condition of the environment, or the UE can store the indication of the identified level of the condition of the environment in a memory or cache. ​ The output of the indication can be performed by, for example, the weather detection component 198 of the apparatus 1704 in FIG. 13B, the one or more sensor modules 1718 (e.g., one or more Lidar sensors), the camera 1732, the transceiver 1722, the cellular baseband processor 1724, and / or the application processor 1706. In some implementations, to output the indication of the identified level of the condition of the environment, the UE can transmit the indication of the identified level of the condition of the environment, or the UE can store the indication of the identified level of the condition of the environment in a memory or cache.

[0154] ​is a diagram 1700 that illustrates an example of a hardware implementation for an apparatus 1704. The apparatus 1704 can be a UE, a component of a UE, or can implement UE functionality. In some aspects, the apparatus 1704 can include at least one cellular baseband processor 1724 (also referred to as a modem) coupled with one or more transceivers 1722 (e.g., cellular RF transceivers). The cellular baseband processor 1724 can include at least one on-chip memory 1724'. In some aspects, the apparatus 1704 can further include one or more Subscriber Identity Modules (SIM) cards 1720, and at least one application processor 1706 coupled with a secure digital (SD) card 1708 and a screen 1710. The application processor 1706 can include on-chip memory 1706'. In some aspects, the apparatus 1704 can further include a Bluetooth module 1712, a WLAN module 1714, an Ultra-Wide Band (UWB) module 1738, a SPS module 1716 (e.g., a GNSS module), one or more sensor modules 1718 (e.g., barometric pressure sensors / altimeters; Ultra-Wide Band (UWB) sensors, motion sensors such as Inertial Measurement Units (IMUs), gyroscopes, and / or accelerometers; Light Detection and Ranging (LIDAR), Radio Detection and Ranging (RADAR), Sound Navigation and Ranging (SONAR), magnetometers, audio, and / or other technologies for positioning), an additional memory module 1726, a power supply 1730, and / or a camera 1732. The Bluetooth module 1712, the WLAN module 1714, the UWB module 1738, and the SPS module 1716 can include on-chip transceivers (TRXs) (or in some cases, just receivers (RXs)). The Bluetooth module 1712, the WLAN module 1714, the UWB module 1738, and the SPS module 1716 can include their own dedicated antennas and / or utilize the antenna 1780 for communications. The cellular baseband processor 1724 communicates with the UE 104 and / or with a RU associated with the network entity 1702 by the transceiver 1722 via one or more antennas 1780. The cellular baseband processor 1724 and the application processor 1706 can each include computer- readable medium / memory 1724', 1706', respectively. The additional memory module 1726 can also be considered a computer-readable medium / memory. Each computer-readable medium / memory 1724', 1706', 1726 can be non-transitory. The cellular baseband processor 1724 and the application processor 1706 each are responsible for general processing, including the execution of software stored on the computer-readable medium / memory. The software, when executed by the cellular baseband processor 1724 / application processor 1706, causes the cellular baseband processor 1724 / application processor 1706 to perform the various functions described supra. The computer-readable medium / memory can also be used for storing data that is manipulated by the cellular baseband processor 1724 / application processor 1706 when executing software.The cellular baseband processor 1724 / application processor 1706 can be a component of the UE 350 and can include at least one memory 360 and / or at least one of the TX processor 368, the RX processor 356, and the controller / processor 359. In one configuration, the apparatus 1704 can be at least one processor chip (modem and / or application) and include only the cellular baseband processor 1724 and / or the application processor 1706, while in another configuration, the apparatus 1704 can be the entire UE (e.g., see FIG. 3. ​ of the UE 350) and include additional modules of the apparatus 1704.

[0155] As discussed above, the weather detection component 198 can be configured to convert a set of point clouds associated with an environment into a set of range images based on a spherical projection. The weather detection component 198 can be further configured to apply at least one of a FFT or a DWT to the set of range images to obtain a set of FFT coefficients or a set of DWT coefficients. The weather detection component 198 can be further configured to identify a level of a condition of the environment based on a sparsity of the set of FFT coefficients or the set of DWT coefficients. The weather detection component 198 can be located within the cellular baseband processor 1724, the application processor 1706, or both the cellular baseband processor 1724 and the application processor 1706. The weather detection component 198 can be one or more hardware components specifically configured to carry out the described processes / algorithms, implemented by one or more processors configured to perform the described processes / algorithms, stored within a computer-readable medium for implementation by one or more processors, or some combination thereof. When multiple processors are present, the multiple processors can carry out the stated processes / algorithms individually or in combination. As illustrated, the apparatus 1704 can include a variety of components configured for various functions. In one configuration, the apparatus 1704 (and in particular the cellular baseband processor 1724 and / or the application processor 1706) can include means for converting a set of point clouds associated with an environment into a set of range images based on a spherical projection. The apparatus 1704 can further include means for applying at least one of a FFT or a DWT to the set of range images to obtain a set of FFT coefficients or a set of DWT coefficients. The apparatus 1704 can further include means for identifying a level of a condition of the environment based on a sparsity of the set of FFT coefficients or the set of DWT coefficients.

[0156] In one configuration, the condition can be a severe weather condition or a clear weather condition, and to identify the level of the condition of the environment, the UE can identify the level of the severe weather condition or the clear weather condition.

[0157] In another configuration, the sparsity of the set of FFT coefficients or the set of DWT coefficients can be based on an LI norm.

[0158] In another configuration, the condition can be a severe weather condition, and the severe weather condition is more severe in the condition in which the set of FFT coefficients or the set of DWT coefficients is more dense compared to the condition in which the set of FFT coefficients or the set of DWT coefficients is less dense.

[0159] In another configuration, the set of point clouds corresponds to a three-dimensional (3D) visualization of the environment that includes a plurality of georeferenced points.

[0160] In another configuration, the apparatus 1704 can also include means for modifying at least one control parameter of a vehicle based on the identification of the level of the condition of the environment.

[0161] In another configuration, the apparatus 1704 can also include means for obtaining, prior to the transformation of the set of point clouds, the set of point clouds associated with the environment from at least one sensor, where the transformation of the set of point clouds can be based on the obtained set of point clouds. In some implementations, the apparatus 1704 can also include means for obtaining the set of range images via a plurality of timestamps of one or more Lidar sensors, and the means for applying at least one of the FFT or the DWT to the set of range images can include configuring the apparatus 1704 to apply at least one of a 3D FFT or a 3D DWT to the set of range images.

[0162] In another configuration, the apparatus 1704 can also include means for detecting the sparsity of the set of FFT coefficients or the set of DWT coefficients prior to the identification of the level of the condition of the environment, where the identification of the level of the condition of the environment is based on the detected sparsity of the set of FFT coefficients or the set of DWT coefficients.

[0163] In another configuration, the apparatus 1704 can also include means for outputting an indication of the identified level of the condition of the environment, the identified level being based on the sparsity of the set of FFT coefficients or the set of DWT coefficients. In some implementations, the means for outputting the indication of the identified level of the condition of the environment can include configuring the apparatus 1704 to transmit the indication of the identified level of the condition of the environment, or store the indication of the identified level of the condition of the environment in a memory or cache.

[0164] In another configuration, the apparatus 1704 can also include means for capturing an image of the environment using the at least one camera and means for pairing the captured image with at least one other image based on the sparsity of the set of FFT coefficients or the set of DWT coefficients. In some implementations, the apparatus 1704 can also include means for training an Al / ML model to identify a set of features of the environment based on the pairing of the captured image with the at least one other image.

[0165] The components can be the weather detection component 198 of the apparatus 1704 configured to perform the functions recited by the components. As described above, the apparatus 1704 can include the TX processor 368, the RX processor 356, and the controller / processor 359. Thus, in one configuration, the components can be the TX processor 368, the RX processor 356, and / or the controller / processor 359 configured to perform the functions recited by the components.

[0166] It should be understood that the particular order or hierarchy of steps in the processes / flow diagrams disclosed is merely an example. It should be appreciated that a particular order or hierarchy of steps can be rearranged, so long as the steps involve the disclosed functions. Also, a person having ordinary skill in the art will readily recognize that the steps in the processes / flow diagrams can be combined, or performed in parallel, or a combination thereof.

[0167] The preceding description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other aspects. Thus, the claims are not to be limited to the aspects described herein, but are to be given the full scope defined by the language of the claims. Unless otherwise defined, a reference to a singular element includes “one or more” thereof. Terms such as “if,” “when,” and “while” do not imply direct temporal relationships or reactions. That is, the phrases “when,” “while,” and “if” are simply used to indicate conditional relationships, unless specifically stated otherwise. The term “exemplary” is used herein to mean “serving as an example, instance, or illustration.” Any aspect described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other aspects. Unless specifically stated otherwise, the term “some” refers to one or more. Combinations such as “at least one of A, B, or C,” “one or more of A, B, or C,” “at least one of the group consisting of A, B, and C,” “one or more of the group consisting of A, B, and C,” and “A, B, and / or C or any combination thereof’ include number one, number two, number three, or number one, number two, and number three. Specifically, combinations such as “at least one of A, B, or C,” “one or more of A, B, or C,” “at least one of the group consisting of A, B, and C,” “one or more of the group consisting of A, B, and C,” and “A, B, and / or C or any combination thereof’ can be one A, one B, one C, one A and one B, one A and one C, one B and one C, or one A, one B, and one C, where any of A, B, or C can be one or more members of the set. A set is a collection of elements, where the number of elements in the set is either zero or one or more. Thus, a set can include one or more elements. When a set of elements includes one or more members, the set can include one or more instances of each member. When a set of functions is configured to perform a set of tasks, each function in the set of functions can be configured to perform a particular subset of the set of tasks, either alone or in any combination with other functions in the set. Thus, each function in the set of functions can be configured to perform a particular subset of the set of tasks, where the subset is the full set, a proper subset of the set, or an empty subset of the set. If a first device receives data from a second device or sends data to the second device, the data can be received or sent directly from or to the first and second devices, or indirectly via a set of devices between the first and second devices. A device configured to “output” data, such as a signal or message, may, for example, send the data with a transceiver, or can transfer the data to a device that sends the data. A device configured to “obtain” data, such as a signal or message, may, for example, receive the data with a transceiver, or can obtain the data from a device that receives the data.Information stored in the memory includes instructions and / or data. All structural and functional equivalents to the elements of the various aspects described throughout this disclosure that are known or later come to be known to those of ordinary skill in the art are expressly incorporated herein by reference and are intended to be encompassed by the claims. Moreover, nothing disclosed herein is intended to be dedicated to the public regardless of whether such disclosure is explicitly recited in the claims. The words “module,” “mechanism,” “element,” “device,” and the like do not require that all of these components be implemented in software. Rather, some of the components can be implemented one or more other hardware components. Additionally, it should be understood that any logical or combining of elements that can not explicitly be described or claimed to be a single device, may, nonetheless, be implemented as one or more of the described devices and / or components.

[0168] As used herein, the phrase “based on” shall not be construed as a signification of an exclusive set of items, conditions, factors, etc. on which information is to be based unless there is explicit claim to such an exclusive set. In other words, the phrase “based on A” (where A can be information, conditions, factors, etc.) should be interpreted as “based at least in part on A” unless otherwise specifically claimed.

[0169] The following aspects are merely exemplary and can be combined with other aspects or teachings described herein without limitation.

[0170] Aspect 1 is a method of wireless communication at a user equipment (UE), the method comprising: converting a set of point clouds associated with an environment based on a spherical projection to a set of range images; applying at least one of a fast Fourier transform (FFT) or a discrete wavelet transform (DWT) to the set of range images to obtain a set of FFT coefficients or a set of DWT coefficients; and identifying a level of a condition of the environment based on a sparsity of the set of FFT coefficients or the set of DWT coefficients.

[0171] Aspect 2 is the method of Aspect 1, further comprising: outputting an indication of the identified level of the condition of the environment, the identified level based on the sparsity of the set of FFT coefficients or the set of DWT coefficients.

[0172] Aspect 3 is the method of Aspect 1 or Aspect 2, wherein outputting the indication of the identified level of the condition of the environment comprises: transmitting the indication of the identified level of the condition of the environment; or storing the indication of the identified level of the condition of the environment in a memory or cache.

[0173] Aspect 4 is the method of any one of aspects 1 through 3, further comprising: prior to the identifying of the level of the condition of the environment, detecting the sparsity of the set of FFT coefficients or the set of DWT coefficients, wherein the identifying of the level of the condition of the environment is based on the detected sparsity of the set of FFT coefficients or the set of DWT coefficients.

[0174] Aspect 5 is the method of any one of aspects 1 through 4, wherein the condition is a severe weather condition or a clear weather condition, and wherein the identifying of the level of the condition of the environment comprises identifying the level of the severe weather condition or the clear weather condition.

[0175] Aspect 6 is the method of any one of aspects 1 through 5, wherein the sparsity of the set of FFT coefficients or the set of DWT coefficients is based on an LI norm.

[0176] Aspect 7 is the method of any one of aspects 1 through 6, further comprising: prior to the transforming of the set of point clouds, obtaining the set of point clouds associated with the environment from at least one sensor, wherein the transforming of the set of point clouds is based on the obtained set of point clouds.

[0177] Aspect 8 is the method of any one of aspects 1 through 7, wherein the at least one sensor comprises at least one light detection and ranging (Lidar) sensor.

[0178] Aspect 9 is the method of any one of aspects 1 through 8, further comprising: obtaining the set of range images via a plurality of timestamps of one or more Lidar sensors, and wherein the applying of at least one of the FFT or the DWT to the set of range images comprises: applying at least one of a three-dimensional (3D) FFT or a 3D DWT to the set of range images.

[0179] Aspect 10 is the method of any one of aspects 1 through 9, wherein the condition is a severe weather condition, and wherein the severe weather condition is more severe in instances where the set of FFT coefficients or the set of DWT coefficients is more dense than in instances where the set of FFT coefficients or the set of DWT coefficients is less dense.

[0180] Aspect 11 is the method of any one of aspects 1 through 10, further comprising: capturing an image of the environment using at least one camera; and pairing the captured image with at least one other image based on the sparsity of the set of FFT coefficients or the set of DWT coefficients.

[0181] Aspect 12 is the method of any of aspects 1-11, further comprising training an artificial intelligence (AI) / machine learning (ML) (AI / ML) model to identify a set of features of the environment based on the pairing of the captured image with the at least one other image.

[0182] Aspect 13 is the method of any of aspects 1-12, wherein the set of point clouds correspond to a three-dimensional (3D) visualization of the environment that includes a plurality of georeferenced points.

[0183] Aspect 14 is the method of any of aspects 1-13, further comprising modifying at least one control parameter of a vehicle based on the identification of the level of the condition of the environment.

[0184] Aspect 15 is 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 configured as, alone or in any combination, to implement any of aspects 1-14 based at least in part on information stored in the at least one memory.

[0185] Aspect 16 is the apparatus of aspect 15, further comprising at least one of a transceiver or an antenna coupled to the at least one processor.

[0186] Aspect 17 is an apparatus for wireless communication, comprising means for implementing any of aspects 1-14.

[0187] Aspect 18 is a computer-readable medium (for example, a non-transitory computer- readable medium) storing computer executable code, where the code when executed by a processor causes the processor to implement any of aspects 1-14.

Claims

1. An apparatus for wireless communication at a user equipment (UE), the apparatus comprising: transceiver; At least one memory; and At least one processor, coupled to the at least one memory, and configured individually or in any combination, based at least in part on information stored in the at least one memory, to: Based on spherical projection, a set of point clouds associated with the environment is converted into a set of distance images; At least one of Fast Fourier Transform (FFT) or Discrete Wavelet Transform (DWT) is applied to the distance image set to obtain an FFT coefficient set or a DWT coefficient set; and The level of the environmental condition is identified based on the sparsity of the FFT coefficient set or the DWT coefficient set.

2. The apparatus of claim 1, wherein the at least one processor is further configured, alone or in any combination, to: Output an indication of the identified level of the state of the environment, the identified level being based on the sparsity of the FFT coefficient set or the DWT coefficient set.

3. The apparatus of claim 2, wherein, in order to output the indication of the identified level of the condition of the environment, the at least one processor is configured individually or in any combination to: Send the indication of the identified level of the condition of the environment; or The indication of the identified level of the condition of the environment is stored in memory or cache.

4. The apparatus of claim 1, wherein the at least one processor is further configured, alone or in any combination, to: Before identifying the level of the condition of the environment, the sparsity of the FFT coefficient set or the DWT coefficient set is detected, wherein the identification of the level of the condition of the environment is based on the detected sparsity of the FFT coefficient set or the DWT coefficient set.

5. The apparatus of claim 1, wherein the condition is an adverse weather condition or a sunny weather condition, and wherein, in order to identify the level of the condition of the environment, the at least one processor is configured individually or in any combination to identify the level of the adverse weather condition or the sunny weather condition.

6. The apparatus of claim 1, wherein the sparsity of the FFT coefficient set or the DWT coefficient set is based on the L1 norm.

7. The apparatus of claim 1, wherein the at least one processor is further configured, alone or in any combination, to: Prior to the transformation of the point cloud set, the point cloud set associated with the environment is obtained from at least one sensor, wherein the transformation of the point cloud set is based on the obtained point cloud set.

8. The apparatus of claim 7, wherein the at least one sensor comprises at least one light detection and ranging (Lidar) sensor.

9. The apparatus of claim 8, wherein the at least one processor is further configured, alone or in any combination, to: The distance image set is obtained via multiple timestamps from one or more LiDAR sensors, and wherein, in order to apply at least one of the FFT or the DWT to the distance image set, the at least one processor is configured individually or in any combination to: At least one of three-dimensional (3D) FFT or 3D DWT is applied to the distance image set.

10. The apparatus of claim 1, wherein the condition is a severe weather condition, and wherein the severe weather condition is more severe when the FFT coefficient set or the DWT coefficient set is denser than when the FFT coefficient set or the DWT coefficient set is less dense.

11. The apparatus of claim 1, wherein the at least one processor is further configured, alone or in any combination, to: Use at least one camera to capture images of the environment; and The captured image is paired with at least one other image based on the sparsity of the FFT coefficient set or the DWT coefficient set.

12. The apparatus of claim 11, wherein the at least one processor is further configured, alone or in any combination, to: Train an artificial intelligence (AI) / machine learning (ML) (AI / ML) model to identify a set of features of the environment based on the pairing of the captured image with the at least one other image.

13. The apparatus of claim 1, wherein the point cloud set corresponds to a three-dimensional (3D) visualization of the environment including a plurality of geographic reference points.

14. The apparatus of claim 1, wherein the at least one processor is further configured, alone or in any combination, to: At least one control parameter of the vehicle is modified based on the identifier of the level of the condition of the environment.

15. A method for conducting wireless communication at a user equipment (UE), the method comprising: Based on spherical projection, a set of point clouds associated with the environment is converted into a set of distance images; At least one of Fast Fourier Transform (FFT) or Discrete Wavelet Transform (DWT) is applied to the distance image set to obtain an FFT coefficient set or a DWT coefficient set; and The level of the environmental condition is identified based on the sparsity of the FFT coefficient set or the DWT coefficient set.

16. The method according to claim 15, further comprising: Output an indication of the identified level of the state of the environment, the identified level being based on the sparsity of the FFT coefficient set or the DWT coefficient set.

17. The method of claim 16, wherein outputting the indication of the identified level of the condition of the environment comprises: Send the indication of the identified level of the condition of the environment; or The indication of the identified level of the condition of the environment is stored in memory or cache.

18. The method according to claim 15, further comprising: Before identifying the level of the condition of the environment, the sparsity of the FFT coefficient set or the DWT coefficient set is detected, wherein the identification of the level of the condition of the environment is based on the detected sparsity of the FFT coefficient set or the DWT coefficient set.

19. The method of claim 15, wherein the condition is an adverse weather condition or a clear weather condition, and wherein the level identifying the condition of the environment includes the level identifying the adverse weather condition or the clear weather condition.

20. The method of claim 15, wherein the sparsity of the FFT coefficient set or the DWT coefficient set is based on the L1 norm.

21. The method according to claim 15, further comprising: Prior to the transformation of the point cloud set, the point cloud set associated with the environment is obtained from at least one sensor, wherein the transformation of the point cloud set is based on the obtained point cloud set.

22. The method of claim 21, wherein the at least one sensor comprises at least one light detection and ranging (Lidar) sensor.

23. The method according to claim 22, further comprising: The distance image set is obtained via multiple timestamps from one or more LiDAR sensors, and the application of at least one of the FFT or the DWT to the distance image set includes: At least one of three-dimensional (3D) FFT or 3D DWT is applied to the distance image set.

24. The method of claim 15, wherein the condition is a severe weather condition, and wherein the severe weather condition is more severe when the FFT coefficient set or DWT coefficient set is denser than when the FFT coefficient set or DWT coefficient set is less dense.

25. The method according to claim 15, further comprising: Use at least one camera to capture images of the environment; as well as The captured image is paired with at least one other image based on the sparsity of the FFT coefficient set or the DWT coefficient set.

26. The method according to claim 25, further comprising: Train an artificial intelligence (AI) / machine learning (ML) (AI / ML) model to identify a set of features of the environment based on the pairing of the captured image with the at least one other image.

27. The method of claim 15, wherein the point cloud set corresponds to a three-dimensional (3D) visualization of the environment including a plurality of geographic reference points.

28. The method according to claim 15, further comprising: At least one control parameter of the vehicle is modified based on the identifier of the level of the condition of the environment.

29. An apparatus for wireless communication at a user equipment (UE), the apparatus comprising: A component used to convert a set of point clouds associated with the environment into a set of distance images based on spherical projection; A component for applying at least one of Fast Fourier Transform (FFT) or Discrete Wavelet Transform (DWT) to the distance image set to obtain an FFT coefficient set or a DWT coefficient set; and A component for identifying the level of the state of the environment based on the sparsity of the FFT coefficient set or the DWT coefficient set.

30. A computer-readable medium storing computer-executable code at a user equipment (UE), said code causing said at least one processor, when executed, to: Based on spherical projection, a set of point clouds associated with the environment is converted into a set of distance images; At least one of Fast Fourier Transform (FFT) or Discrete Wavelet Transform (DWT) is applied to the distance image set to obtain an FFT coefficient set or a DWT coefficient set; and The level of the environmental condition is identified based on the sparsity of the FFT coefficient set or the DWT coefficient set.

Images