Method and apparatus for transmitting and receiving signals in wireless communication system

Abstract

An embodiment of the present specification relates to an integrated sensing and communication (ISAC) system which converts and analyzes point cloud data into a graph using an alpha complex and a Wasserstein distance, and precisely identifies and shares an object through a CNN. Thereby, object recognition performance is maximized in a dynamic three-dimensional environment, and stable cooperative driving is supported.

Description

Method and device for transmitting and receiving signals in a wireless communication system

[0001] This specification relates to methods and devices used in wireless communication systems.

[0002] Wireless communication systems are being widely deployed to provide various types of communication services, such as voice and data. Generally, a wireless communication system is a multiple access system capable of supporting communication with multiple users by sharing available system resources (bandwidth, transmission power, etc.). Examples of multiple access systems include CDMA (Code Division Multiple Access), FDMA (Frequency Division Multiple Access), TDMA (Time Division Multiple Access), OFDMA (Orthogonal Frequency Division Multiple Access), and SC-FDMA (Single Carrier Frequency Division Multiple Access).

[0003] The technical problem to be solved by the present specification is to provide a method for efficiently transmitting and receiving wireless communication signals and an apparatus for doing so.

[0004] The technical challenges are not limited to those described above, and other technical challenges can be inferred from the embodiments.

[0005] The present specification provides a method and apparatus for transmitting and receiving signals in a wireless communication system.

[0006] As one aspect of the present specification, a method is provided comprising: acquiring point cloud data based on sensing data collected through multiple sensors; generating information about an object based on the point cloud data; and transmitting information about the object.

[0007] In another aspect of the present specification, a device for performing the method comprises a terminal, a base station, a processor, and a storage medium.

[0008] The above devices may include at least a terminal, a network, and an autonomous vehicle capable of communicating with other autonomous vehicles other than the device.

[0009] The embodiments of this specification described above are merely some of the preferred embodiments of this specification, and various embodiments reflecting the technical features can be derived and understood by those skilled in the art based on the detailed description.

[0010] According to one embodiment of the present specification, when a signal is transmitted and received between communication devices, there is an advantage that more efficient signal transmission and reception can be performed through an operation differentiated from the prior art.

[0011] The technical effects are not limited to those described above, and other technical effects may be inferred from the examples.

[0012] Figure 1 illustrates the structure of a radio frame.

[0013] Figure 2 illustrates a resource grid of slots.

[0014] FIG. 3 illustrates a communication procedure between a terminal and a base station applicable to the present disclosure.

[0015] Figures 4 and 5 show an example of how ISAC is applied to a 3GPP wireless communication system.

[0016] FIGS. 6 to 8 are drawings for explaining a signal transmission and reception method according to an embodiment of the present disclosure.

[0017] FIGS. 9 to 11 illustrate devices according to embodiments of the present disclosure.

[0018] The following technologies can be used in various wireless access systems such as CDMA, FDMA, TDMA, OFDMA, and SC-FDMA. CDMA can be implemented using wireless technologies such as UTRA (Universal Terrestrial Radio Access) or CDMA2000. TDMA can be implemented using wireless technologies such as GSM (Global System for Mobile Communications), GPRS (General Packet Radio Service), and EDGE (Enhanced Data Rates for GSM Evolution). OFDMA can be implemented using wireless technologies such as IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802-20, and E-UTRA (Evolved UTRA). UTRA is part of the UMTS (Universal Mobile Telecommunications System). 3GPP (3rd Generation Partnership Project) LTE (Long Term Evolution) is part of E-UMTS (Evolved UMTS) using E-UTRA, and LTE-A (Advanced) / LTE-A pro is an evolved version of 3GPP LTE. 3GPP NR (New Radio or New Radio Access Technology) is an evolved version of 3GPP LTE / LTE-A / LTE-A pro.

[0019] For the sake of clarity, the description is based on 3GPP communication systems (e.g., LTE, NR), but the technical scope of this specification is not limited thereto. LTE refers to technology from 3GPP TS 36.xxx Release 8 onwards. Specifically, LTE technology from 3GPP TS 36.xxx Release 10 onwards is referred to as LTE-A, and LTE technology from 3GPP TS 36.xxx Release 13 onwards is referred to as LTE-A pro. 3GPP NR refers to technology from TS 38.xxx Release 15 onwards. LTE / NR may be referred to as a 3GPP system. "xxx" indicates a specific standard document number. LTE / NR may be collectively referred to as a 3GPP system. Regarding background technology, terms, abbreviations, etc. used in the description of this specification, reference may be made to matters described in previously published standard documents. For example, the following documents may be referenced.

[0020] 3GPP NR

[0021] - 38.211: Physical channels and modulation

[0022] - 38.212: Multiplexing and channel coding

[0023] - 38.213: Physical layer procedures for control

[0024] - 38.214: Physical layer procedures for data

[0025] - 38.300: NR and NG-RAN Overall Description

[0026] - 38.331: Radio Resource Control (RRC) protocol specification

[0027] Figure 1 illustrates the structure of a wireless frame used in NR.

[0028] In NR, uplink (UL) and downlink (DL) transmissions consist of frames. A radio frame has a length of 10 ms and is defined as two 5 ms half-frames (HF). A half-frame is defined as five 1 ms subframes (SF). A subframe is divided into one or more slots, and the number of slots within a subframe depends on the subcarrier spacing (SCS). Each slot contains 12 or 14 OFDM(A) symbols depending on the cyclic prefix (CP). When normal CP is used, each slot contains 14 symbols. When extended CP is used, each slot contains 12 symbols. Here, the symbols may include OFDM symbols (or CP-OFDM symbols) or SC-FDMA symbols (or DFT-s-OFDM symbols).

[0029] Table 1 illustrates how the number of symbols per slot, the number of slots per frame, and the number of slots per subframe vary depending on the SCS when a standard CP is used.

[0030] [Table 1]

[0031]

[0032] Table 2 illustrates how the number of symbols per slot, the number of slots per frame, and the number of slots per subframe vary depending on the SCS when an extended CP is used.

[0033] [Table 2]

[0034]

[0035] In an NR system, OFDM(A) numerology (e.g., SCS, CP length, etc.) can be configured differently among multiple cells merged into a single terminal (User Equipment; UE). Accordingly, the (absolute time) interval of a time resource (e.g., SF, slot, or TTI) (collectively referred to as TU (Time Unit) for convenience) composed of the same number of symbols can be configured differently among the merged cells.

[0036] NR supports multiple OFDM (Orthogonal Frequency Division Multiplexing) numerologies (e.g., subcarrier spacing, SCS) to support various 5G services. For example, if the SCS is 15 kHz, it supports a wide area in traditional cellular bands, and if the SCS is 30 kHz / 60 kHz, it can support dense-urban, lower latency, and wider carrier bandwidth.

[0037] The NR frequency band is defined by two types of frequency ranges (FR) (FR1 / FR2). FR1 / FR2 can be configured as shown in Table 3 below. Additionally, FR2 can refer to millimeter wave (mmW).

[0038] [Table 3]

[0039]

[0040] Figure 2 illustrates the slot structure of an NR frame.

[0041] A slot contains multiple symbols in the time domain. For example, in the case of a standard CP, one slot contains 14 symbols, and in the case of an extended CP, one slot contains 12 symbols. A carrier contains multiple subcarriers in the frequency domain. A Resource Block (RB) is defined as multiple (e.g., 12) consecutive subcarriers in the frequency domain. Multiple RB interlacs (simply interlacs) can be defined in the frequency domain. An interlac m∈{0, 1, ..., M-1} can be composed of (common) RBs {m, M+m, 2M+m, 3M+m, ...}. M represents the number of interlacs. A Bandwidth Part (BWP) is defined as multiple consecutive RBs (e.g., physical RB, PRB) in the frequency domain and can correspond to a single OFDM numerology (e.g., SCS(u), CP length, etc.). A carrier wave may contain up to N (e.g., 5) BWPs. Data communication is performed through the active BWPs, and only one BWP can be active for a single terminal within a single cell / carrier wave. In the resource grid, each element is referred to as a Resource Element (RE), and one modulation symbol can be mapped to it.

[0042] In a wireless communication system, a terminal receives information from a base station via the downlink (DL) and transmits information to the base station via the uplink (UL). The information transmitted and received by the base station and the terminal includes data and various control information, and various physical channels and signals exist depending on the type and purpose of the information being transmitted and received. A physical channel corresponds to a set of resource elements (REs) that carry information originating from the upper layer. A physical signal corresponds to a set of resource elements (REs) used by the physical layer (PHY), but it does not carry information originating from the upper layer. The upper layer includes the MAC (Medium Access Control) layer, RLC (Radio Link Control) layer, PDCP (Packet Data Convergence Protocol) layer, RRC (Radio Resource Control) layer, etc.

[0043] DL physical channels include PBCH (Physical Broadcast Channel), PDSCH (Physical Downlink Shared Channel), and PDCCH (Physical Downlink Control Channel). DL physical signals include DL RS (Reference Signal), PSS (Primary Synchronization Signal), and SSS (Secondary Synchronization Signal). DL RS includes DM-RS (Demodulation RS), PT-RS (Phase-tracking RS), and CSI-RS (Channel-state Information RS). UL physical channels include PRACH (Physical Random Access Channel), PUSCH (Physical Uplink Shared Channel), and PUCCH (Physical Uplink Control Channel). UL physical signals include UL RS. UL RS includes DM-RS, PT-RS, and SRS (Sounding RS).

[0044] The base station can be, for example, gNodeB.

[0045] 6G network architecture

[0046] FIG. 3 illustrates a communication procedure between a terminal and a base station applicable to the present disclosure. FIG. 3 illustrates the operation of a terminal (100) and a base station (200) transmitting and / or receiving data, and the operation performed prior to this.

[0047] Referring to FIG. 3, in step 101, the terminal (100) and the base station (200) perform synchronization. For example, the terminal (100) performs an initial cell search operation. Specifically, the terminal (100) can detect at least one synchronization signal transmitted from the base station (200) according to a predefined rule. Here, the synchronization signal may include a plurality of synchronization signals (e.g., primary synchronization signal, secondary synchronization signal) classified according to structure or use. Through this, the terminal (100) can identify the boundaries of the frame, subframe, slot, and / or symbol of the base station (200) and obtain information about the base station (200) (e.g., cell identifier).

[0048] In step 103, the terminal (100) obtains system information transmitted from the base station (200). The system information is information related to the attributes, characteristics, and / or capabilities of the base station (200) required to connect to the base station (200) and use the service, and can be classified according to content (e.g., whether it is essential for connection), transmission structure (e.g., channel used, whether it is provided on-demand), etc., and can be classified, for example, into a master information block (MIB) and a system information block (SIB). If necessary, the terminal (100) may transmit a signal requesting the system information prior to receiving the system information. However, the request and provision of the system information may be performed after the random access procedure described later.

[0049] In step 105, the terminal (100) and the base station (200) perform a random access procedure. The terminal (100) may transmit and / or receive at least one message for the random access procedure (e.g., random access preamble, RAR (random access response) message, etc.) based on information related to the random access channel of the base station (200) obtained through system information (e.g., channel location, channel structure, structure of supported preamble, etc.). For example, the terminal (100) may transmit a preamble (e.g., MSG1) through the random access channel, receive a RAR message (e.g., MSG2), transmit a message (e.g., MSG3) containing information related to the terminal (100) (e.g., identification information) to the base station (200) using scheduling information included in the RAR message, and receive a message (e.g., MSG4) for contention resolution and / or connection establishment. As another example, MSG1 and MSG3 can be transmitted and received as a single message, or MSG2 and MSG4 can be transmitted and received as a single message.

[0050] In step 107, the terminal (100) and the base station (200) perform signaling of control information. Here, the control information may be defined in various layers, such as a layer that controls the connection (e.g., a radio resource control (RRC) layer), a layer that handles mapping between logical channels and transmission channels (e.g., a media access control (MAC) layer), and a layer that handles physical channels (e.g., a physical (PHY) layer). For example, the terminal (100) and the base station (200) may perform at least one of signaling to establish a connection, signaling to determine settings related to communication, and signaling to indicate allocated resources.

[0051] In step 109, the terminal (100) and the base station (200) transmit and / or receive data. That is, the terminal (100) and the base station (200) can process, transmit and / or receive data based on the signaling of control information. For example, when transmitting data, the terminal (100) or the base station (200) may perform at least one of channel encoding, rate matching, scrambling, constellation mapping, layer mapping, waveform modulation, antenna mapping, and resource mapping on the information bits. Conversely, when receiving data, the terminal (100) or the base station (200) may perform at least one of signal extraction from resources, antenna-specific waveform demodulation, signal placement considering layer mapping, constellation demapping, descrambling, and channel decoding.

[0052] 6G System Core Technology

[0053] As core implementation technologies for 6G systems, technologies such as artificial intelligence (AI), THz (Terahertz) communication, optical wireless technology, FSO backhaul network, massive MIMO technology, blockchain, 3D networking, quantum communication, unmanned aerial vehicles, cell-free communication, wireless information and energy transfer (WIET), integration of sensing and communication, integration of access backhaul networks, holographic beamforming, big data analysis, and large intelligent surface (LIS) can be adopted.

[0054] ISAC (Integrated Sensing and Communication)

[0055] FIGS. 4 and 5 illustrate an example of an application of ISAC to a 3GPP wireless communication system. The embodiment of FIGS. 4 and 5 can be combined with various embodiments of the present disclosure. Specifically, FIG. 4 illustrates an example of sensing using a sensing receiver and a sensing transmitter located at the same location (e.g., monostatic sensing), and FIG. 5 illustrates an example of sensing using a separated sensing receiver and a sensing transmitter (e.g., bistatic sensing).

[0056] For example, in the sensing process of ISAC, information about the surrounding environment can be collected by analyzing how the transmitted signal is reflected, scattered, or diffracted. In the case of signal transmission, a transmitter may transmit or radiate a signal for ISAC. As described above, the signal for ISAC may include data and RS. The signal for ISAC may be received by a receiver of a receiving device (e.g., a terminal or a base station). At this time, the receiver may receive the signal for ISAC and the reflected wave of the signal. In this case, the receiving device may simultaneously analyze the received signal and the reflected signal.

[0057] For example, the receiving device can decode the data through a direct path signal (LoS, Line of Sight) and extract the distance, speed, and direction of the object through the reflected signal or the reflected path signal (NLoS, Non-Line of Sight). For example, the receiving device can estimate the distance to the (surrounding) object and the speed of the object by applying the FMCW (Frequency-Modulated Continuous Wave) technique to the reflected signal, or detect the relative speed to the (surrounding) object by applying the Doppler Shift Analysis technique.

[0058] Below, we will explain in detail how to perform ISAC more effectively and accurately using the neural network model described above.

[0059] Point cloud-based ISAC system

[0060] The contents examined above can be applied in combination with the proposed methods described below, or can be supplemented to clarify the technical characteristics of the proposed methods.

[0061] In addition, the methods described below can be applied in the same way to the NR system (licensed band) or shared spectrum described above, and it goes without saying that the technical concept proposed in this specification can be modified or replaced to fit the terms, expressions, structures, etc. defined in each system so that it can be implemented in the system as well.

[0062] The following embodiments relate to the field of Integrated Sensing and Communication (ISAC). The following embodiments may be associated with autonomous vehicles, robotics, and urban surveillance systems. Specifically, the following embodiments enable real-time high-precision sensing and object recognition through point cloud data processing utilizing deep learning and topological graph kernels for optimized driving and collision avoidance.

[0063] ISAC systems require efficient and accurate methods for analyzing three-dimensional environments. Point clouds, a rich 3D data representation, are essential for providing real-time depth information and spatial context that are critical for autonomous driving and object detection. However, existing ISAC systems struggle to process noisy point clouds, large datasets, and various sensor sources (e.g., LiDAR, stereo cameras), which limits precision and speed in dynamic environments.

[0064] The embodiments of this specification provide a new ISAC system that integrates point cloud data processing based on a graph kernel with a discrete geodesic distribution and an Alpha complex-derived skeleton. This improves the ability to accurately classify, detect, and predict objects in a three-dimensional space in real time. When an adaptive Alpha complex graph structure is used, various point cloud data, including data containing noise or originating from multiple sources, can be processed efficiently, similarity measurement and classification are possible, and computation speed can be optimized without a decrease in accuracy.

[0065] Conventional 3D spatial data processing technology (hereinafter referred to as 'legacy technology') primarily represented 3D objects using 2D images, CAD models, or structured geometric shapes such as polygons and meshes. However, this method had the disadvantage of requiring additional data conversion and computational processing to accurately represent complex shapes and spatial relationships within 3D space.

[0066] In terms of data acquisition, conventional technology relied on single-frame images, manually generated modeling, or simple sensor measurements. In particular, understanding a 3D scene through traditional sensors such as cameras requires significant post-processing, such as depth estimation, which increased the computational load on the system.

[0067] In addition, during the processing and analysis process, algorithms based on 2D image processing must undergo complex and computationally intensive processes for object feature extraction or distance measurement, which limits the ability to achieve real-time performance in dynamic scenarios where immediate spatial awareness is essential, such as autonomous driving. Furthermore, there are limitations in precisely capturing fine details of complex or irregular environments without manual intervention, resulting in the problem of having to rely on approximations that are less accurate.

[0068] The embodiments of the present specification have the following technical differentiations compared to the aforementioned prior art through point cloud processing technology.

[0069] First, for data representation, a point cloud method is used to directly capture the 3D environment into millions of individual points. Since each point includes unique 3D coordinates (X, Y, Z) and color and intensity values, it is possible to achieve a much more detailed and accurate 3D representation than conventional 2D images or mesh-based representations.

[0070] Second, in terms of data acquisition, data from multiple angles is acquired by utilizing 3D sensors such as LiDAR, laser scanners, and stereo cameras. Unlike conventional technology that relied on a single viewpoint, this enables immediate and three-dimensional 3D representation of objects and environments.

[0071] Third, in the processing and analysis process, raw spatial data is processed directly. In particular, segmentation, object recognition, and path prediction are performed using AI technologies such as graph-based neural networks or deep learning, thereby reducing the computational complexity of depth perception and spatial analysis that conventional technologies have experienced.

[0072] Fourth, regarding real-time application, immediate interpretation is possible simultaneously with data acquisition, so the following embodiments can be applied to fields requiring rapid decision-making, such as autonomous driving, robotics, and augmented reality.

[0073] Finally, in terms of level of detail and flexibility, information loss is minimized, and fine details of large-scale irregular environments, such as landscapes or complex industrial structures, can be captured. Therefore, compared to conventional technology where manual intervention was essential, the following embodiments can be flexibly applied to various applications.

[0074] FIG. 6 is a flowchart schematically illustrating the operation of a system according to one embodiment.

[0075] Referring to FIG. 6, a system according to an embodiment of the present invention can first perform intelligent sensing and classification (S601). The sensor module of the system collects point cloud data from multiple sources (LiDAR, camera, etc.). In addition, the system performs classification on detected objects using an alpha complex graph kernel and Wasserstein similarity measures. This graph structure captures both geometric and topological attributes of the objects, enabling the ISAC system to distinguish complex 3D shapes (e.g., pedestrians, vehicles, obstacles) while minimizing noise interference.

[0076] Next, the system performs Adaptive Object Recognition and Prediction (S603). The system generates similarity matrices based on collected point cloud data. The system includes a neural network to predict the movement paths of objects and potential collisions using the generated similarity matrices. This neural network uses Convolutional Neural Network (CNN) layers on an alpha complex induction graph to generate highly accurate segmentation and classification results even in high-speed environments.

[0077] The system performs real-time communication for a specific system as autonomous navigation (S605). The system optimizes the communication protocol based on classified point cloud data. Additionally, the system transmits relevant object data and environment data based on object recognition and prediction results. When the system detects a potential risk, it transmits a warning to an autonomous driving system (or other systems mentioned in this specification, such as a robot system) within a certain range to enhance collaborative navigation and obstacle avoidance performance.

[0078] The system performs multi-source integration and data processing (S607). The system can operate in conjunction with multiple ISAC platforms (e.g., autonomous vehicles, drones, etc.) and can accommodate various point cloud densities and sensor data quality. The alpha complex graph kernel processes data efficiently, balancing high-precision detail and real-time requirements even in sparse point clouds.

[0079] Figure 7 is a block diagram schematically showing an example of the structure of the system.

[0080] Referring to FIG. 7, the system may be configured to include a sensor module (701), a data processing unit (702), a communication module (703), and a central controller (704). Although not illustrated, the system may further include a preprocessing module located between the sensor module and the data processing module, and / or an intelligent object recognition and prediction module located between the data processing unit and the communication module.

[0081] The sensor module collects point cloud data in real time from multiple sources, including LiDAR, stereo cameras, and other depth sensors. The sensor module supports data collection for stationary (static) and mobile (dynamic) sensors deployed on mobile devices, such as autonomous vehicles and drones, and / or on stationary devices. Additionally, the sensor module can perform preliminary filtering (data preprocessing) to remove noise and ensure data consistency.

[0082] The sensor module may include a sensor, an interface, and a sensor fusion engine.

[0083] Specifically, the sensor may include a LiDAR sensor and a stereo camera. The LiDAR sensor may be, for example, a 64-channel LiDAR sensor for capturing 3D point data. The LiDAR sensor captures point cloud data containing depth and intensity information for 3D spatial recognition. The stereo camera may be a dual camera for depth recognition in the color and infrared spectra. The stereo camera provides additional depth information in the RGB and / or infrared spectra to complement the data from the LiDAR sensor.

[0084] The data interface of the sensor module may include a CAN (Controller Area Network) bus and Ethernet for high-speed data transmission.

[0085] The Sensor Fusion Engine combines data collected from LiDAR sensors and stereo cameras using Kalman filters for data alignment and spatial noise reduction. Data fusion is configured to manage overlapping field views and variable resolution.

[0086] As the output format of the sensor module, a point cloud format in which position and intensity data are normalized and standardized for subsequent processing may be used. For example, PLY (Polygon File Format) or LAS (LiDAR Data Exchange Format) may be used.

[0087] If the system includes a sensor module and a separate preprocessing module, the preprocessing module performs noise filtering to refine raw point cloud data to remove unnecessary noise. Additionally, the preprocessing module integrates data from the LiDAR sensor and stereo camera using a Kalman filter to provide consistent and aligned 3D data. The operation of the preprocessing module may also be performed by the sensor module to which the functions of the preprocessing module are integrated.

[0088] The data processing unit includes an Alpha Complex Graph Kernel Processor. The Alpha Complex Graph Kernel Processor utilizes Alpha Complex and other simplicial complex methods to transform raw point cloud data into a structured graph representation and capture geometric and topological features. The data processing unit further includes a Wasserstein Distance Calculator. The Wasserstein Distance Calculator supports the classification and recognition process by measuring the similarity between point clouds and comparing the shapes, surfaces, and contours of objects. The data processing unit performs classification and segmentation on the collected data. Specifically, the data processing unit uses a CNN-based model that utilizes the Alpha Complex structure to identify and segment objects within the point cloud.

[0089] The Alpha Complex graph kernel processor (which may also be briefly referred to as a graph kernel processor) transforms point cloud data into a graph using the Alpha Complex algorithm with a focus on topology preservation. This can be understood as the graph kernel processor converting point cloud data into a graph structure while preserving its geometric and topological features for further data-related processing. In a graph structure, a node refers to an individual point that constitutes the point cloud in three-dimensional space. An edge refers to a connecting line between nodes. According to the Alpha Complex algorithm, two connected nodes are selected as topologically significant nodes, thereby causing the set of points to form a structure akin to the skeleton of an object.

[0090] Furthermore, when calculating distance information between nodes, the data processing unit utilizes geodesic paths—actual paths that travel along the surface of an object—rather than simple straight-line distances (Euclidean distance). For example, when connecting two points on undulating terrain, the distance is calculated based on the assumption of travel along the terrain surface, rather than a straight-line distance. This enables more precise shape recognition, even for objects with complex geometric features.

[0091] In addition, the connectivity status between nodes and distance information based on geodetic paths are structured and stored in the form of an adjacency matrix capable of computer computation. Rather than simply using the 3D coordinate (X, Y, Z) information of the points, the connection structure based on alpha complexes and geodetic path information along the surface are converted into matrix data. The generated adjacency matrix is ​​provided as input data to artificial intelligence models such as CNNs, and by analyzing it and learning the topological connection patterns of the points, the AI ​​model becomes able to precisely identify and classify whether the target object is a vehicle or a pedestrian.

[0092] The Wasserstein distance calculator can also be expressed as a geodesic similarity calculator. The geodesic similarity calculator uses the Wasserstein distance, specifically the Wasserstein-1 distance, to calculate pairwise similarity between graphs transformed by the alpha complex algorithm. This Wasserstein distance is a method for measuring the minimum movement cost between two probability distributions and is utilized to compare structural patterns and distribution differences of objects within a point cloud.

[0093] The geodetic similarity calculator implements the 'Fast Marching Method (FMM)' algorithm to calculate the shortest paths (i.e., geodetic paths) between nodes in a high-dimensional point cloud environment. To process vast amounts of point cloud data in real time and optimize computational efficiency, a 'pruning' technique may be applied, in which edges exceeding a preset distance threshold are excluded or removed from the computation. This ensures fast processing speeds suitable for environments requiring real-time performance, such as autonomous driving, while maintaining data accuracy.

[0094] The data processing unit performs object classification and segmentation to analyze preprocessed graph-based point cloud data. Object classification and segmentation are executed using a CNN-based deep learning model. For example, the CNN model can be pre-trained using ModelNet-40, a standard dataset for 3D object recognition. Through this, the data processing unit processes real-time data while having learned the features of various 3D objects.

[0095] CNN models are largely composed of convolutional layers for feature extraction and pooling layers for computational efficiency. First, multiple (e.g., three) convolutional layers perform operations on the input alpha complex matrix to extract unique geometric features hidden within the connection structure of the points. Subsequently, pooling layers reduce the size of the extracted feature maps to shrink the feature space, thereby minimizing the amount of computation while preserving the core information of the data.

[0096] The data processing unit that has gone through the above process outputs an object label and a segmentation mask. Here, the object label refers to the result of classifying the object, such as whether the detected object is a vehicle or a pedestrian, and the segmentation mask refers to specific area information indicating exactly which area the object occupies in three-dimensional space.

[0097] The object classification and segmentation process may also be performed by the intelligent object recognition and prediction module described later.

[0098] The intelligent object recognition and prediction module performs object detection. For example, it identifies, labels, and classifies objects within the environment (e.g., vehicles, pedestrians, obstacles). Additionally, the intelligent object recognition and prediction module performs path prediction and collision avoidance. This is an essential element for autonomous driving, where the movement paths of detected objects are predicted using prediction algorithms. Furthermore, the intelligent object recognition and prediction module performs adaptable thresholding. Specifically, by adjusting object recognition thresholds based on environmental factors such as speed, distance, and object size, the possibility of false positives can be reduced.

[0099] The intelligent object recognition and prediction module includes a Real-Time Object Detection Pipeline. The Real-Time Object Detection Pipeline is configured to perform the following detailed components and functions.

[0100] The real-time object detection pipeline includes object detection by an inference engine. The inference engine receives granular point cloud data generated by the data processing unit, generates bounding boxes for each object, and performs object detection based on these boxes to clearly identify the types of objects and their boundaries within the point cloud data.

[0101] The real-time object detection pipeline includes a collision prediction algorithm for ensuring driving safety and avoiding collisions. The algorithm is designed to predict the movement of identified objects and is based on a linear motion model, but calculates the predicted trajectory of the object by applying a Kalman filter for trajectory smoothing based on environmental data.

[0102] The real-time object detection pipeline includes alert thresholding to prevent false positives during the object detection process and enhance the accuracy of alerts. Alert thresholding includes setting a threshold for issuing an alert based on proximity and speed information with respect to the target object, and minimizing unnecessary alerts and ensuring system reliability by adjusting the threshold in real-time according to changes in the driving environment.

[0103] The intelligent object recognition and prediction module integrates the predicted trajectory of an object and the collision prediction results to output trajectory information and collision warning information. The intelligent object recognition and prediction module can assign priorities to the trajectory information and collision warning information according to certain criteria.

[0104] The communication module performs real-time data exchange with external systems. For example, the communication module relays processed data, including detected object information and predicted paths, to other systems (e.g., nearby autonomous vehicles, urban infrastructure) via specific communication protocols, such as V2X (Vehicle-to-Everything) communication protocols and / or 3GPP-based communication protocols. Additionally, the communication module transmits warnings regarding potential hazards or anomalies, enabling real-time response across connected devices. Based on data prioritization assigned by the intelligent object recognition and prediction module, high-urgency data, such as collision warnings, is prioritized over lower-priority data, thereby optimizing bandwidth.

[0105] The communication module is configured to support, for example, IEEE 802.11p-based DSRC (Dedicated Short-Range Communications), 5G NR-V2X, LTE, and / or communication standards after 6G.

[0106] The communication module applies differentiated compression algorithms based on the importance of the data to be transmitted. For example, the communication module applies lossless compression to high-priority data where data integrity is essential, such as collision warnings, and lossy compression to general data of relatively lower importance.

[0107] The communication module includes an Alert Messaging System for real-time response to emergency situations. The Alert Messaging System places real-time alerts and / or collision prediction information into a high-priority queue to ensure immediate broadcasting. The transmitted messages have a structured format based on JSON (JavaScript Object Notation) or XML (eXtensible Markup Language) that includes timestamps, geographic location data, and object classification information. Furthermore, to maintain temporal consistency between interconnected heterogeneous systems, all transmitted data undergoes a data synchronization process that aligns with a GPS (Global Positioning System)-based global clock.

[0108] The central controller manages interactions between all modules through system coordination, ensures data synchronization, and optimizes resource allocation. Additionally, the central controller optimizes the balance between precision analysis and processing speed through Adaptive Processing Control, which dynamically adjusts processing based on computational load. Furthermore, the central controller monitors system status, implements fault tolerance by diverting data in the event of component failure, and ensures continuous operation.

[0109] The central controller performs real-time coordination and load balancing to efficiently manage computational resources across the entire system. Specifically, the central controller includes a scheduler to dynamically assign priorities to data processing and transmission tasks based on computational load and sensor data latency. Additionally, in high-load scenarios, it performs dynamic scaling to adjust the processing power allocated to data processing units.

[0110] The central controller performs fault detection and monitoring to ensure the operational reliability of the system. It continuously monitors the status of each hardware and software component and executes fault detection mechanisms that immediately switch inputs to redundant sensors or reroute data transmission paths when a failure is detected. Furthermore, in the event of data synchronization issues between systems, it guarantees uninterrupted continuous system operation through error handling processes, such as verifying duplicate data or performing rollbacks to restore the system to a previous state.

[0111] FIG. 8 is a flowchart illustrating the operation of a device including the system described through FIG. 7. The device performing the operation of FIG. 8 may correspond to a wireless device, i.e., a terminal (100) or a base station (200), described through FIG. 9 to 12, or it may correspond to a device independent of the terminal or base station. The operation of the communication module (703) of FIG. 7 may be performed by the transceiver (106, 206) of FIG. 10, the communication unit (110) of FIG. 11, or the transceiver (114) of FIG. 11. A program for performing the operation described through FIG. 6 to 8 may be stored in the memory (104, 204) of FIG. 10 or the memory unit (130) of FIG. 11, and may be executed by the processor (102, 202) of FIG. 10 or by the control unit (120) of FIG. 11.

[0112] Referring to FIG. 8, the device acquires point cloud data (S801), performs object classification, object recognition, and / or path prediction of the object based on the point cloud data (S803), and can transmit information generated as a result of performing object classification, object recognition, and / or path prediction of the object (S805).

[0113] In step S801, point cloud data acquisition may include the device collecting data from a LiDAR sensor and a stereo camera included in a sensor module, fusing the collected data, and formatting it into point cloud data. The format of the point cloud data may be, for example, PLY or LAS.

[0114] The device performs preprocessing on the source of acquired point cloud data, such as noise removal, balancing of point density, and integration of LiDAR sensor data and stereo camera data (using a Kalman filter).

[0115] In step S803, the device converts the (preprocessed) point cloud data into a graph. For this graph conversion, one of the following algorithms may be used: the Alpha complex, the Cech complex, or the VR (Vietoris Rips) complex. As previously described, distance information between nodes within the point cloud data is derived based on geodesic paths, which are actual paths that travel along the surface of objects. Additionally, the connectivity between nodes and the geodesic path-based distance information are structured and stored in the form of an adjacency matrix that allows for computation. The minimum travel cost between two probability distributions is measured using the Wasserstein distance and can be used to compare the structural patterns of objects within the point cloud with differences in distribution. Scikit-Learn may be used for the Wasserstein distance calculation.

[0116] In step S803, the device performs object classification and segmentation by processing the adjacency matrix through a CNN-based deep learning model. For the output of the deep learning model, the device performs labeling, predicts the movement path of the object based on the object label and location, and performs collision prediction through threshold settings. Priorities can be assigned to collision predictions. TensorFlow or PyTorch may be used for deploying the CNN-based deep learning model.

[0117] In step S805, the data generated in step S803 is packaged. A single data package may include object recognition information, object classification information, movement path information, and / or collision prediction information. Priorities may be assigned to each data package, and the priority for the data package may be determined based on the priority of collision prediction. For cooperative driving and risk recognition of autonomous vehicles, robots, etc., the device transmits the data package to other devices (and / or systems) based on priority.

[0118] Although not explicitly stated, the device continuously monitors each operation and performs resource allocation coordination and load management for each operation. In the event of failure of some components within the device, it activates backup components or reroutes data paths between internal components to ensure fault tolerance.

[0119] FIG. 9 illustrates an example of a communication system (1) to which the implementations of the present specification apply. Referring to FIG. 9, the communication system (1) to which the present specification applies includes a wireless device, a BS, and a network. Here, a wireless device refers to a device that performs communication using wireless access technology (e.g., 5G NR (New RAT), LTE (e.g., E-UTRA)) and may be referred to as a communication / wireless / 5G device. Although not limited thereto, a wireless device may include a robot (100a), a vehicle (100b-1, 100b-2), an XR (eXtended Reality) device (100c), a hand-held device (100d), a home appliance (100e), an IoT (Internet of Thing) device (100f), and an AI device / server (400). For example, a vehicle may include a vehicle equipped with wireless communication capabilities, an autonomous vehicle, a vehicle capable of performing inter-vehicle communication, etc. Here, vehicles may include UAVs (Unmanned Aerial Vehicles) (e.g., drones). XR devices include AR (Augmented Reality) / VR (Virtual Reality) / MR (Mixed Reality) devices and may be implemented in the form of HMDs (Head-Mounted Devices), HUDs (Head-Up Displays) equipped in vehicles, televisions, smartphones, computers, wearable devices, home appliances, digital signage, vehicles, robots, etc. Portable devices may include smartphones, smartpads, wearable devices (e.g., smartwatches, smart glasses), computers (e.g., laptops, etc.). Home appliances may include TVs, refrigerators, washing machines, etc. IoT devices may include sensors, smart meters, etc. For example, BS and networks may be implemented as wireless devices, and specific wireless devices may operate as BS / network nodes to other wireless devices.

[0120] Wireless devices (100a to 100f) can be connected to a network (300) via a BS (200). Artificial Intelligence (AI) technology may be applied to the wireless devices (100a to 100f), and the wireless devices (100a to 100f) can be connected to an AI server (400) via the network (300). The network (300) can be configured using a 3G network, a 4G (e.g., LTE) network, or a 5G (e.g., NR) network. The wireless devices (100a to 100f) may communicate with each other via the BS (200) / network (300), but they may also communicate directly (e.g., sidelink communication) without using the BS / network. For example, vehicles (100b-1, 100b-2) can communicate directly (e.g., V2V (Vehicle to Vehicle) / V2X (Vehicle to everything) communication). Also, IoT devices (e.g., sensors) can communicate directly with other IoT devices (e.g., sensors) or other wireless devices (100a to 100f).

[0121] Wireless communication / connection (150a, 150b) may be established between wireless devices (100a~100f) / BS (200) and BS (200) / wireless devices (100a~100f). Here, the wireless communication / connection may be established through uplink / downlink communication (150a) and sidelink communication (150b) (or D2D communication) using various wireless access technologies (e.g., 5G NR). Through the wireless communication / connection (150a, 150b), wireless devices and BS / wireless devices may transmit / receive wireless signals to / from each other. To this end, based on various proposals of the present specification, at least some of the following may be performed: a process for setting various configuration information for transmitting / receiving wireless signals, a process for various signal processing (e.g., channel encoding / decoding, modulation / demodulation, resource mapping / demapping, etc.), and a resource allocation process.

[0122] FIG. 10 is a block diagram illustrating examples of communication devices capable of performing the method according to the present specification. Referring to FIG. 10, a first wireless device (100) and a second wireless device (200) can transmit and / or receive wireless signals through various wireless access technologies (e.g., LTE, NR). Here, {the first wireless device (100), the second wireless device (200)} may correspond to {wireless device (100x), BS (200)} and / or {wireless device (100x), wireless device (100x)} of FIG. 9.

[0123] The first wireless device (100) includes one or more processors (102) and one or more memories (104), and may additionally include one or more transceivers (106) and / or one or more antennas (108). The processor (102) controls the memory (104) and / or transceivers (106) and may be configured to implement the functions, procedures and / or methods described / suggested below. For example, the processor (102) may process information within the memory (104) to generate a first information / signal and then transmit a wireless signal containing the first information / signal through the transceiver (106). Additionally, the processor (102) may receive a wireless signal containing a second information / signal through the transceiver (106) and then store information obtained from the signal processing of the second information / signal in the memory (104). Memory (104) may be connected to the processor (102) and may store various information related to the operation of the processor (102). For example, memory (104) may store software code containing instructions for performing some or all of the processes controlled by the processor (102) or for performing the procedures and / or methods described / suggested below. Here, the processor (102) and memory (104) may be part of a communication modem / circuit / chip designed to implement wireless communication technology (e.g., LTE, NR). A transceiver (106) may be connected to the processor (102) and may transmit and / or receive wireless signals through one or more antennas (108). The transceiver (106) may include a transmitter and / or receiver. The transceiver (106) may be interchangeably used with an RF (Radio Frequency) unit. In this specification, a wireless device may mean a communication modem / circuit / chip.

[0124] The second wireless device (200) includes one or more processors (202) and one or more memories (204), and may additionally include one or more transceivers (206) and / or one or more antennas (208). The processor (202) controls the memory (204) and / or transceivers (206) and may be configured to implement the functions, procedures and / or methods described / suggested below. For example, the processor (202) may process information within the memory (204) to generate a third information / signal and then transmit a wireless signal containing the third information / signal through the transceiver (206). Additionally, the processor (202) may receive a wireless signal containing a fourth information / signal through the transceiver (206) and then store information obtained from the signal processing of the fourth information / signal in the memory (204). Memory (204) may be connected to the processor (202) and may store various information related to the operation of the processor (202). For example, memory (204) may store software code containing instructions for performing some or all of the processes controlled by the processor (202) or for performing the procedures and / or methods described / suggested below. Here, the processor (202) and memory (204) may be part of a communication modem / circuit / chip designed to implement wireless communication technology (e.g., LTE, NR). A transceiver (206) may be connected to the processor (202) and may transmit and / or receive wireless signals through one or more antennas (208). The transceiver (206) may include a transmitter and / or receiver. The transceiver (206) may be interchangeably used with an RF unit. In this specification, a wireless device may mean a communication modem / circuit / chip.

[0125] The wireless communication technology implemented in the wireless device (100, 200) of this specification may include LTE, NR, and 6G, as well as Narrowband Internet of Things for low-power communication. In this case, for example, NB-IoT technology may be an example of LPWAN (Low Power Wide Area Network) technology and may be implemented according to standards such as LTE Cat NB1 and / or LTE Cat NB2, but is not limited to the names mentioned above. Additionally, or generally, the wireless communication technology implemented in the wireless device (100, 200) of this specification may perform communication based on LTE-M technology. In this case, for example, LTE-M technology may be an example of LPWAN technology and may be referred to by various names such as eMTC (enhanced Machine Type Communication). For example, LTE-M technology may be implemented in at least one of various standards such as 1) LTE CAT 0, 2) LTE Cat M1, 3) LTE Cat M2, 4) LTE non-BL (non-Bandwidth Limited), 5) LTE-MTC, 6) LTE Machine Type Communication, and / or 7) LTE M, and is not limited to the names mentioned above. Additionally or generally, wireless communication technology implemented in the wireless device (XXX, YYY) of this specification may include at least one of ZigBee, Bluetooth, and Low Power Wide Area Network (LPWAN) with consideration for low-power communication, and is not limited to the names mentioned above. As an example, ZigBee technology can create personal area networks (PANs) related to small / low-power digital communication based on various standards such as IEEE 802.15.4 and may be referred to by various names.

[0126] Hereinafter, hardware elements of the wireless device (100, 200) will be described in more detail. Although not limited thereto, one or more protocol layers may be implemented by one or more processors (102, 202). For example, one or more processors (102, 202) may implement one or more layers (e.g., functional layers such as a physical (PHY) layer, a medium access control (MAC) layer, a radio link control (RLC) layer, a packet data convergence protocol (PDCP) layer, a radio resource control (RRC) layer, and a service data adaptation protocol (SDAP) layer). One or more processors (102, 202) may generate one or more protocol data units (PDU) and / or one or more service data units (SDU) according to the functions, procedures, proposals and / or methods disclosed in this document. One or more processors (102, 202) may generate messages, control information, data, or information according to the functions, procedures, proposals, and / or methods disclosed in this document. One or more processors (102, 202) may generate a signal (e.g., baseband signal) containing a PDU, SDU, message, control information, data, or information according to the functions, procedures, proposals, and / or methods disclosed in this document and provide it to one or more transceivers (106, 206). One or more processors (102, 202) may receive a signal (e.g., baseband signal) from one or more transceivers (106, 206) and may obtain a PDU, SDU, message, control information, data, or information according to the functions, procedures, proposals, and / or methods disclosed in this document.

[0127] One or more processors (102, 202) may be referred to as a controller, microcontroller, microprocessor, or microcomputer. One or more processors (102, 202) may be implemented by hardware, firmware, software, or a combination thereof. For example, one or more Application Specific Integrated Circuits (ASICs), one or more Digital Signal Processors (DSPs), one or more Digital Signal Processing Devices (DSPDs), one or more Programmable Logic Devices (PLDs), or one or more Field Programmable Gate Arrays (FPGAs) may be included in one or more processors (102, 202). The functions, procedures, proposals, and / or methods disclosed in this document may be implemented using firmware or software, and the firmware or software may be implemented to include modules, procedures, functions, etc. Firmware or software configured to perform the functions, procedures, proposals, and / or methods disclosed in this document may be included in one or more processors (102, 202) or stored in one or more memories (104, 204) and driven by one or more processors (102, 202). The functions, procedures, proposals, and / or methods disclosed in this document may be implemented using firmware or software in the form of code, instructions, and / or sets of instructions.

[0128] One or more memories (104, 204) may be connected to one or more processors (102, 202) and may store various forms of data, signals, messages, information, programs, code, instructions, and / or commands. One or more memories (104, 204) may be composed of ROM, RAM, EPROM, flash memory, hard drive, registers, cache memory, computer read storage media, and / or combinations thereof. One or more memories (104, 204) may be located inside and / or outside of one or more processors (102, 202). Additionally, one or more memories (104, 204) may be connected to one or more processors (102, 202) through various technologies such as wired or wireless connections.

[0129] One or more transceivers (106, 206) may transmit user data, control information, wireless signals / channels, etc., as mentioned in the methods and / or operation flowcharts, etc., of this document to one or more other devices. One or more transceivers (106, 206) may receive user data, control information, wireless signals / channels, etc., as mentioned in the functions, procedures, proposals, methods and / or operation flowcharts, etc., disclosed in this document from one or more other devices. For example, one or more transceivers (106, 206) may be connected to one or more processors (102, 202) and may transmit and / or receive wireless signals. For example, one or more processors (102, 202) may control one or more transceivers (106, 206) to transmit user data, control information, or wireless signals to one or more other devices. Additionally, one or more processors (102, 202) may control one or more transceivers (106, 206) to receive user data, control information, or wireless signals from one or more other devices. Additionally, one or more transceivers (106, 206) may be connected to one or more antennas (108, 208), and one or more transceivers (106, 206) may be configured to transmit and / or receive user data, control information, wireless signals / channels, etc., as mentioned in the functions, procedures, proposals, methods, and / or operation flowcharts disclosed in this document through one or more antennas (108, 208). In this document, one or more antennas may be multiple physical antennas or multiple logical antennas (e.g., antenna ports). One or more transceivers (106, 206) can convert the received wireless signal / channel, etc. from an RF band signal to a baseband signal in order to process the received user data, control information, wireless signal / channel, etc. using one or more processors (102, 202).One or more transceivers (106, 206) can convert user data, control information, wireless signals / channels, etc. processed using one or more processors (102, 202) from baseband signals to RF band signals. To this end, one or more transceivers (106, 206) may include (analog) oscillators and / or filters.

[0130] FIG. 11 illustrates another example of a wireless device capable of performing implementation(s) of the present specification. Referring to FIG. 11, the wireless device (100, 200) corresponds to the wireless device (100, 200) of FIG. 10 and may be composed of various elements, components, units / parts, and / or modules. For example, the wireless device (100, 200) may include a communication unit (110), a control unit (120), a memory unit (130), and an additional component (140). The communication unit may include a communication circuit (112) and transceiver(s) (114). For example, the communication circuit (112) may include one or more processors (102, 202) of FIG. 10 and / or one or more memories (104, 204). For example, the transceiver(s) (114) may include one or more transceivers (106, 206) and / or one or more antennas (108, 208) of FIG. 10. The control unit (120) is electrically connected to the communication unit (110), the memory unit (130), and additional components (140) and controls the general operation of the wireless device. For example, the control unit (120) may control the electrical / mechanical operation of the wireless device based on a program / code / command / information stored in the memory unit (130). Additionally, the control unit (120) may transmit information stored in the memory unit (130) to the outside (e.g., another communication device) via a wireless / wired interface through the communication unit (110), or store information received from the outside (e.g., another communication device) via a wireless / wired interface through the communication unit (110) in the memory unit (130).

[0131] The additional configuration (140) can be configured in various ways depending on the type of wireless device. For example, the additional configuration (140) may include at least one of a power unit / battery, an input / output unit (I / O unit), a driving unit, and a computing unit. Although not limited thereto, the wireless device may be implemented in the form of a robot (Fig. 9, 100a), a vehicle (Fig. 9, 100b-1, 100b-2), an XR device (Fig. 9, 100c), a portable device (Fig. 9, 100d), a home appliance (Fig. 9, 100e), an IoT device (Fig. 9, 100f), a UE for digital broadcasting, a hologram device, a public safety device, an MTC device, a medical device, a fintech device (or financial device), a security device, a climate / environment device, an AI server / device (Fig. 9, 400), a BS (Fig. 9, 200), a network node, etc. Wireless devices can be used in a movable or fixed location depending on the use—e.g., service.

[0132] In FIG. 11, various elements, components, units / parts, and / or modules within the wireless device (100, 200) may be entirely interconnected via a wired interface, or at least partially connected via a communication unit (110). For example, within the wireless device (100, 200), the control unit (120) and the communication unit (110) may be connected via a wire, and the control unit (120) and the first unit (e.g., 130, 140) may be connected wirelessly via the communication unit (110). Additionally, each element, component, unit / part, and / or module within the wireless device (100, 200) may include one or more additional elements. For example, the control unit (120) may be composed of one or more sets of processors. For example, the control unit (120) may be composed of a set of communication control processors, application processors, ECUs (Electronic Control Units), graphics processing processors, memory control processors, etc. As another example, the memory unit (130) may be composed of RAM (Random Access Memory), DRAM (Dynamic RAM), ROM (Read Only Memory), flash memory, transitory memory, non-transitory memory, and / or a combination thereof.

[0133] In this specification, at least one memory (e.g., 104 or 204) may store instructions or programs, and said instructions or programs may, when executed, cause at least one processor operablely connected to said at least one memory to perform operations according to some embodiments or implementations of this specification.

[0134] In this specification, a computer-readable (non-transient) storage medium may store at least one instruction or computer program, and when executed by at least one processor, said at least one instruction or computer program may cause said at least one processor to perform operations according to some embodiments or implementations of this specification.

[0135] In this specification, a processing device or apparatus may include at least one processor and at least one computer memory connectable to said at least one processor. said at least one computer memory may store instructions or programs, and said instructions or programs, when executed, may cause at least one processor operablely connected to said at least one memory to perform operations according to some embodiments or implementations of this specification.

[0136] In this specification, a computer program may include program code stored on at least one computer-readable (non-transient) storage medium and, when executed, perform operations according to some implementations of this specification or cause at least one processor to perform operations according to some implementations of this specification. The computer program may be provided in the form of a computer program product. The computer program product may include at least one computer-readable (non-transient) storage medium.

[0137] A communication device of this specification comprises at least one processor; and at least one computer memory operably connected to said at least one processor and storing instructions that, when executed, cause said at least one processor to perform operations according to the examples(s) of this specification described below.

[0138] As described above, the embodiments of this specification can be applied to various wireless communication systems.

Claims

1. A step of acquiring point cloud data based on sensing data collected through multiple sensors; A step of generating information about an object based on the above point cloud data; A step of transmitting information about the above object; comprising, method.

2. In Paragraph 1, The above multi-sensor includes a LiDAR sensor and a stereo camera, and The above point cloud data is obtained through the combination of data collected from the lidar sensor and data collected from the stereo camera using a linear filter. method.

3. In Paragraph 1, Information regarding the above object includes information regarding the shape, surface, and contour of the above object. method.

4. In Paragraph 1, The generating step comprises converting the point cloud data into a graph form based on one of the Alpha complex algorithm, the Cech complex algorithm, or the VR (Vietoris Rips) complex algorithm. method.

5. In Paragraph 1, The above generating step includes storing distance information between nodes constituting the point cloud data in the form of an adjacency matrix, and The above distance information is geodetic path-based information, method.

6. In Paragraph 4, The above generating step includes calculating the similarity between different point cloud data converted into the graph form based on Wasserstein distance, method.

7. In Paragraph 5, Based on the distance between specific two nodes among the above nodes exceeding a threshold, a connection line composed of the specific two nodes is excluded from the calculation, method.

8. In Paragraph 4, The above generating step includes recognizing or classifying the object based on the output of a CNN (Convolutional Neural Network) model that takes the graph-shaped point cloud data as input. method.

9. In Paragraph 8, The above CNN model extracts geometric features of the graph-shaped point cloud data and reduces the feature space by reducing the size of the feature map constructed based on the geometric features. method.

10. In Paragraph 8, The generating step comprises labeling the recognized or classified object and performing a segmentation mask for the three-dimensional region occupied by the object. method.

11. In Paragraph 1, Information regarding the above object includes information regarding the expected trajectory and collision probability of the above object. method.

12. In Paragraph 11, Information regarding the above object, which is prioritized based on the collision possibility, method.

13. At least one processor; and It includes at least one memory connected to the at least one processor to be operable, and storing instructions that cause the at least one processor to perform a specific operation when executed. The above specific operation is: A step of acquiring point cloud data based on sensing data collected through multiple sensors; A step of generating information about an object based on the above point cloud data; A step of transmitting information about the above object; comprising, device.

14. In Paragraph 13, The above device is a terminal or a base station, device.

15. A computer-readable non-volatile storage medium comprising at least one computer program that causes a device including at least one processor to perform an operation, wherein the operation is: A step of acquiring point cloud data based on sensing data collected through multiple sensors; A step of generating information about an object based on the above point cloud data; A step of transmitting information about the above object; comprising, Storage medium.

Images