Internet of vehicles sensing data transmission method and device

Abstract

The invention provides an Internet of Vehicles sensing data transmission method and device, and relates to the technical field of automatic driving. The method comprises the following steps: a road test communication unit broadcasts sensing data acquired by road sensing equipment and sends first indication information; the vehicle end receives first indication information broadcasted and sent by the road test communication unit and sends a sensing data request; the vehicle side judges whether Decoder network weight needs to be updated according to the weight information version number of the vehicle side, and when the weight information version number of the vehicle side does not meet the effective version number, the vehicle side receives Decoder network weight information, obtains the version number and updates the local version number; the drive test communication unit broadcasts and sends second indication information; and based on the second indication information, the vehicle end receives the perception semantic features at the corresponding time-frequency positions, and the received perception semantic features are recovered to original perception information through the received Decoder network weight information. According to the invention, the transmission efficiency can be improved, and the reliability under a low signal-to-noise ratio is enhanced.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a method and apparatus for transmitting vehicle-to-everything (V2X) perception data. Background Technology

[0002] With the rapid development of intelligent connected vehicles and vehicle-road cooperative systems, connected autonomous driving based on roadside multimodal perception has become a core path to overcome the bottleneck of single-vehicle intelligence. Current mainstream architectures deploy three types of heterogeneous perception devices—LiDAR, millimeter-wave radar, and cameras—on both sides of the road. The raw perception data is broadcast to the vehicle via a wireless air interface, such as the 5G NR-V2XPC5 interface, through the roadside units. The vehicle integrates the global perception data from the roadside with its own positioning information to achieve beyond-line-of-sight target recognition, blind wind risk warning, and high-precision positioning enhancement. This model significantly reduces the vehicle's dependence on high-cost perception hardware, such as 128-line LiDAR, and compensates for the inherent limitations of onboard sensors, such as limited line-of-sight and susceptibility to obstruction, through an "omniscient perspective," improving system robustness in complex scenarios, including extreme weather conditions such as dense smoke and strong sunlight.

[0003] However, multimodal sensing data transmission faces severe air interface resource challenges: (1) Data surge pressure: Within the coverage area of ​​a single RSU, multiple heterogeneous data sources such as lidar point cloud >1Mbps / sensor, high-definition video stream >20Mbps / channel and millimeter-wave radar target matrix >500Kbps are transmitted concurrently, resulting in a sharp decline in air interface spectrum efficiency; (2) Stringent QoS requirements: Autonomous driving decision-making requires end-to-end latency ≤100ms and transmission reliability ≥99.999% (3GPP TR 22.886 standard), while the Doppler frequency shift caused by high-speed vehicle movement (>120km / h) further deteriorates channel conditions; Waste of modal correlation: Traditional transmission schemes process each modal data independently, ignoring cross-modal semantic correlation, such as the spatiotemporal alignment characteristics of lidar point cloud and camera image, resulting in up to 60% redundant transmission (IEEE IV). (2022 measured data); Among them, semantic communication technology is currently regarded as the key to breaking the deadlock: roadside edge computing nodes extract compact semantic feature vectors from perception data through multimodal fusion neural networks, such as BEVFormer and DeepFusion, which can usually be compressed to 5%-10% of the original data volume, transmitting only features rather than the original data. This technology has two core advantages: a leap in bandwidth efficiency, that is, reducing the air interface load by 1-2 orders of magnitude while maintaining perception accuracy; and resistance to channel degradation, with a lower bit error rate than traditional solutions in low signal-to-noise ratio (SNR<0dB) scenarios. However, the shortcomings of existing semantic communication solutions in the deployment of vehicle-to-everything (V2X) include: the disconnect between model weights and semantic feature transmission; specifically, the vehicle needs to be equipped with decoder weight parameters that are strictly matched with the roadside encoder to restore semantic features. However, the lack of a dynamic synchronization mechanism means that the weights of roadside models are frequently updated due to environmental adaptation (such as model switching in rainy or snowy weather) or algorithm iteration (≥5 times per day), while vehicles lack a reliable channel to obtain the weights in real time; resource competition conflicts arise, with weight transmission (approximately 50-200MB per model) competing with high-timeliness semantic features (>10Hz updates) for air interface resources, resulting in excessive latency in the transmission of key perception information; and there is a vacuum in personalized services, meaning that no on-demand subscription mechanism has been established, and vehicles cannot selectively receive specific modalities, such as only image semantics or spatial regions, such as data from a sector area 500m ahead, resulting in resource waste.

[0004] Current technologies mitigate these shortcomings by pre-installing vehicle-mounted model weights, but still face three problems: unsustainable storage overhead (supporting all roadside devices requires storing a terabyte-level weight library, far exceeding the capacity of the vehicle computing platform); complex version management (fragmentation of RSU model versions across vendors, such as incompatibility between vendor A's v3.1 and vendor B's v2.4); and security risks (static weights cannot defend against adversarial attacks). Currently, the 3GPP Rel-18 and ETSI ITS-G5 standards have not defined a semantic communication transmission framework, and mainstream solutions such as MQTT-based weight push or periodic broadcasting cannot meet the deterministic latency requirements of highly dynamic vehicle-to-everything (V2X) scenarios. Summary of the Invention

[0005] To address the problems of excessive transmission overhead and limited transmission capacity under low channel quality in existing technologies, this invention provides a method and apparatus for transmitting sensing data in a vehicle-to-everything (V2X) network. The technical solution is as follows:

[0006] On the one hand, a method for transmitting vehicle-to-everything (V2X) sensing data is provided, which is implemented by a V2X sensing data transmission device, and includes:

[0007] S1. The roadside communication unit broadcasts the sensing data acquired by the road sensing device and sends first indication information; wherein, the first indication information includes: a valid version number, wireless resource information such as Decoder network weight information;

[0008] S2. The vehicle receives the first indication information broadcast by the roadside communication unit and sends a perception data request. The vehicle determines whether it needs to update the Decoder network weight based on its own weight information version number. When the vehicle's own weight information version number does not meet the valid version number, the vehicle receives the radio resource information of the Decoder network weight information, obtains the version number, and updates the local version number.

[0009] S3. The road test communication unit broadcasts and sends a second indication information; wherein, the second indication information includes the time-frequency location of the semantic features of the transmitted sensing data;

[0010] S4. Based on the second instruction information, the vehicle terminal receives the perceptual semantic features in the corresponding radio resource information, and restores the received perceptual semantic features into the original perceptual information through the radio resource information of the received Decoder network weight information.

[0011] Optionally, the first indication information is used to demodulate the time-frequency location of the weighted resources of the semantic feature information of the region;

[0012] The first indication information further includes: demodulation information of the demodulator network weight information, the number of sensing nodes, the three-dimensional spatial position of the nodes, and the data modality of each node;

[0013] The demodulation information of the demodulator network weight information includes: a demodulation reference signal and a demodulation key;

[0014] The sensing nodes include: lidar, millimeter-wave radar, and cameras;

[0015] The valid version number is used by the vehicle to determine whether it needs to update its own weight value.

[0016] Optionally, the second indication information may also include a version number indication, a time-frequency location indication of multimodal semantic features, spatial location coordinates, and a unique vehicle identifier;

[0017] The version number is used to determine whether the indicated time-frequency location semantic features can be demodulated.

[0018] The spatial location coordinates refer to the three-dimensional spatial coordinates of the roadside sensing device and the time-frequency location of the sensing semantic features associated with the spatial location.

[0019] Optionally, the method for indicating the time-frequency location of the perceived semantic features includes: a fusion feature indication method and a separate indication method;

[0020] Among them, the fusion feature indication method refers to performing multimodal fusion of the obtained lidar features, millimeter wave features and image features to obtain perceptual fusion features, and indicating the time and frequency position of the perceptual fusion features;

[0021] Among them, the individual indication method refers to indicating the time-frequency position of a single mode separately.

[0022] Optionally, the second indication information is used to indicate the perceptual semantic features of multiple spatial locations, the time-frequency resource location indicating the weight of the Decoder network, and the time-frequency location of the semantic feature data of the spatial perception node requested by the vehicle.

[0023] The perceptual semantic features of the multiple spatial locations are multiplexed using frequency division, time division, and code division methods.

[0024] Among them, the time-frequency resource location of the Decoder network weights and the time-frequency location of the semantic feature data of the spatial perception node requested by the vehicle need to maintain a minimum time interval.

[0025] Optionally, the time-frequency position of sending the semantic features of the perceived data and the time-frequency position of sending the Decoder network weight information satisfy a minimum time interval.

[0026] Optionally, the first indication information and the Decoder network weight information are kept at a minimum time interval.

[0027] On the other hand, a vehicle-to-everything (V2X) sensing data transmission device is provided, which is applied to the V2X sensing data transmission method. The device includes:

[0028] The road test communication unit is used to broadcast the sensing data acquired by the road sensing device and send a first indication information; wherein the first indication information includes: a valid version number, radio resource information such as Decoder network weight information; and broadcast a second indication information; wherein the second indication information includes the time-frequency location of the semantic features of the transmitted sensing data.

[0029] The vehicle-side terminal receives the first indication information broadcast by the roadside communication unit and sends a sensing data request. Based on its own weight information version number, the vehicle-side terminal determines whether to update the Decoder network weights. When the vehicle-side terminal's own weight information version number does not meet the requirements for a valid version number, the vehicle-side terminal receives the radio resource information of the Decoder network weight information, obtains the version number, and updates its local version number. Based on the second indication information, the vehicle-side terminal receives sensing semantic features in the corresponding radio resource information and uses the received radio resource information of the Decoder network weight information to restore the received sensing semantic features into the original sensing information.

[0030] Optionally, the first indication information is used to demodulate the time-frequency location of the weighted resources of the semantic feature information of the region;

[0031] The first indication information further includes: demodulation information of the demodulator network weight information, the number of sensing nodes, the three-dimensional spatial position of the nodes, and the data modality of each node;

[0032] The demodulation information of the demodulator network weight information includes: a demodulation reference signal and a demodulation key;

[0033] The sensing nodes include: lidar, millimeter-wave radar, and cameras;

[0034] The valid version number is used by the vehicle to determine whether it needs to update its own weight value.

[0035] Optionally, the second indication information may also include a version number indication, a time-frequency location indication of multimodal semantic features, spatial location coordinates, and a unique vehicle identifier;

[0036] The version number is used to determine whether the indicated time-frequency location semantic features can be demodulated.

[0037] The spatial location coordinates refer to the three-dimensional spatial coordinates of the roadside sensing device and the time-frequency location of the sensing semantic features associated with the spatial location.

[0038] Optionally, the method for indicating the time-frequency location of the perceived semantic features includes: a fusion feature indication method and a separate indication method;

[0039] Among them, the fusion feature indication method refers to performing multimodal fusion of the obtained lidar features, millimeter wave features and image features to obtain perceptual fusion features, and indicating the time and frequency position of the perceptual fusion features;

[0040] Among them, the individual indication method refers to indicating the time-frequency position of a single mode separately.

[0041] Optionally, the second indication information is used to indicate the perceptual semantic features of multiple spatial locations, the time-frequency resource location indicating the weight of the Decoder network, and the time-frequency location of the semantic feature data of the spatial perception node requested by the vehicle.

[0042] The perceptual semantic features of the multiple spatial locations are multiplexed using frequency division, time division, and code division methods.

[0043] Among them, the time-frequency resource location of the Decoder network weights and the time-frequency location of the semantic feature data of the spatial perception node requested by the vehicle need to maintain a minimum time interval.

[0044] Optionally, the time-frequency position of sending the semantic features of the perceived data and the time-frequency position of sending the Decoder network weight information satisfy a minimum time interval.

[0045] Optionally, the first indication information and the Decoder network weight information are kept at a minimum time interval.

[0046] On the other hand, a vehicle-to-everything (V2X) sensing data transmission device is provided, the V2X sensing data transmission device comprising: a processor; a memory, the memory storing computer-readable instructions, which, when executed by the processor, implement any of the methods described above for V2X sensing data transmission.

[0047] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, the at least one instruction being loaded and executed by a processor to implement any of the above-described methods for transmitting vehicle-to-everything (V2X) sensing data.

[0048] The beneficial effects of the technical solutions provided by the embodiments of the present invention include at least the following:

[0049] In this embodiment of the invention, the sensing data acquired by the road sensing device is first broadcast via a roadside communication unit, and a first indication message is sent. This first indication message includes a valid version number and radio resource information for the Decoder network weight information. Next, the vehicle receives the first indication message broadcast by the roadside communication unit and sends a sensing data request. The vehicle determines whether to update the Decoder network weight based on its own weight information version number. If the vehicle's own weight information version number does not meet the requirements for a valid version number, the vehicle receives the radio resource information for the Decoder network weight information, obtains the version number, and updates its local version number. The roadside communication unit then broadcasts a second indication message, which includes the time-frequency location of the semantic features of the sensing data. Finally, based on the second indication message, the vehicle receives the sensing semantic features in the corresponding radio resource information and, using the received radio resource information for the Decoder network weight information, restores the received sensing semantic features to the original sensing information.

[0050] This invention proposes a weight-feature joint scheduling mechanism, which resolves resource conflicts between weight updates and feature transmission through dynamic version number management and minimum time interval constraints. It also proposes a time-frequency resource joint indication mechanism, which dynamically allocates weight and feature resources through indication information and supports time-division or frequency-division multiplexing of multimodal data. Furthermore, it designs a multimodal on-demand indication strategy, allowing vehicles to selectively receive fused features or single-modal features, reducing redundant transmission. Using this invention can improve transmission efficiency and enhance reliability under low signal-to-noise ratio conditions. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 This is a flowchart of a vehicle-to-everything (V2X) sensing data transmission method provided in an embodiment of the present invention;

[0053] Figure 2 This is a schematic diagram illustrating the case of different offsets with the same period in a single indication method provided by an embodiment of the present invention;

[0054] Figure 3This is a schematic diagram illustrating a single indication method provided in an embodiment of the present invention, where different periods do not overlap in the frequency domain;

[0055] Figure 4 This is a schematic diagram illustrating a case where different periods partially overlap in the frequency domain in a single indication method provided by an embodiment of the present invention.

[0056] Figure 5 This is a block diagram of a vehicle-to-everything (V2X) sensing data transmission device provided in an embodiment of the present invention;

[0057] Figure 6 This is a schematic diagram of the structure of a vehicle-to-everything (V2X) sensing data transmission device provided in an embodiment of the present invention. Detailed Implementation

[0058] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0059] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0060] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0061] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0062] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0063] This invention provides a method for transmitting vehicle-to-everything (V2X) sensing data. This method can be implemented by a V2X sensing data transmission device, which can be a terminal or a server. Figure 1 The flowchart shown is for a vehicle-to-everything (V2X) sensing data transmission method. The processing flow of this method may include the following steps:

[0064] S1. The roadside communication unit broadcasts the sensing data acquired by the road sensing device and sends first indication information; wherein, the first indication information includes: a valid version number, wireless resource information such as Decoder network weight information.

[0065] In connected autonomous driving or vehicle-to-everything (V2X) systems, three types of sensing devices—LiDAR, millimeter-wave radar, and cameras—are deployed along both sides of the road, along with Roadside Units (RSUs). The sensing data from these devices is transmitted via the RSU and then wirelessly to the vehicles traveling on the road. The vehicles receive the sensing data from the RSU and, combined with their own spatial position, determine the road conditions ahead, thus achieving target perception and recognition.

[0066] The valid version number can be a number or other identifier, represented by V1.

[0067] The Decoder network weight information includes a unified version number, V2.

[0068] The Decoder network weights are associated with one or more corresponding sensor data to demodulate the data.

[0069] Optionally, the first indication information is used to determine the time-frequency location of the weighted resources for demodulating the semantic feature information of this region;

[0070] The first indication information also includes: demodulation information of the demodulator network weight information, the number of sensing nodes, the three-dimensional spatial location of the nodes, and the data modality of each node;

[0071] The demodulation information for demodulating the Decoder network weights includes: a demodulation reference signal and a demodulation key.

[0072] The sensing nodes include: lidar, millimeter-wave radar, and cameras;

[0073] The valid version number is used by the vehicle to determine whether it needs to update its own weight value.

[0074] In one feasible implementation, at the location indicated by the first indication information, the drive test communication unit sends the weight information of the receiving end Decoder network.

[0075] Optionally, the first indication information and the Decoder network weight information are kept at a minimum time interval.

[0076] In order to ensure sufficient processing latency on the vehicle side, the first indication information and the Decoder network weight information need to be guaranteed to have a minimum time interval, which is determined by the vehicle side's processing decoding or decryption capabilities.

[0077] S2. The vehicle receives the first indication information broadcast by the roadside communication unit and sends a perception data request. The vehicle determines whether it needs to update the Decoder network weight based on its own weight information version number. When the vehicle's own weight information version number does not meet the requirements of a valid version number, the vehicle receives the radio resource information of the Decoder network weight information, obtains the version number, and updates the local version number.

[0078] The version number obtained is a unified version number V2.

[0079] S3. The road test communication unit broadcasts and sends a second indication information; wherein, the second indication information includes the time-frequency location of the semantic features of the transmitted sensing data.

[0080] Optionally, the second indication information also includes a version number indication, a time-frequency location indication of multimodal semantic features, spatial location coordinates, and a unique vehicle identifier;

[0081] The version number is used to determine whether the indicated time-frequency location semantic features can be demodulated.

[0082] Among them, the spatial location coordinates are the three-dimensional spatial coordinates of the road test sensing device and the time-frequency location of the sensing semantic features associated with the spatial location.

[0083] The second indication information is sent periodically, and the road test communication unit sends the corresponding perceptual semantic features at the time-frequency position indicated by the second indication information.

[0084] The second instruction information also includes reference information and key information for demodulating or decrypting semantic features on the vehicle side.

[0085] The unique identifier of the vehicle ensures that only that vehicle can effectively demodulate the instruction information and the subsequent corresponding weight information or semantic feature information.

[0086] Optionally, the methods for indicating the time-frequency location of perceived semantic features include: a fusion feature indication method and a separate indication method;

[0087] Among them, the fusion feature indication method refers to performing multimodal fusion of the obtained lidar features, millimeter wave features and image features to obtain perceptual fusion features, and indicating the time and frequency position of the perceptual fusion features;

[0088] Among them, the individual indication method refers to indicating the time-frequency position of a single mode separately.

[0089] In one feasible implementation, the individual indication method includes three approaches; one approach involves configuring the Roadside Communication Unit (RSU) with the same period T for all modes, and different modal sensors corresponding to different offset values ​​within the period, including T1 and T2; such as Figure 2 As shown, multiple identical modal sensor data can be superimposed in the frequency domain; for example, adding point cloud data from multiple LiDARs over a period T can also be superimposed in the frequency domain. The individual indication method proposed in this embodiment allows the vehicle to receive T, T1, T2, and fixed frequency domain position information, and then obtain the corresponding modal data at the corresponding location according to its own needs, thereby reducing indication signaling and improving communication efficiency.

[0090] The second method is as follows: Figure 3 The road test communication unit (RSU) shown is configured with a different period for different modes, and different modes have different periods in the time domain. For example, the period of the lidar point cloud is T1 and the period of the image is T2, and they occupy different frequency domain positions in the frequency domain.

[0091] The third method is as follows: Figure 4 The different modes shown have different periods in the time domain; for example, the period of the lidar point cloud is T1, and the image period is T2, and they can partially overlap in the frequency domain. For example... Figure 4 Since the original positions of the two dashed boxes in the image are occupied by the laser point cloud, the image features do not need to be transmitted, based on the principle that the laser radar point cloud occupies the image point cloud resources.

[0092] In one feasible implementation, the method of fusing feature indications can improve transmission efficiency; the method of separate indications can facilitate on-demand reception with vehicles. For example, if the vehicle only needs image information, it only needs to receive the sensing features of the corresponding time and frequency location for decoding.

[0093] S4. Based on the second instruction information, the vehicle terminal receives the perceptual semantic features in the corresponding radio resource information, and restores the received perceptual semantic features into the original perceptual information through the radio resource information of the received Decoder network weight information.

[0094] Optionally, the second indication information is used to indicate the perceptual semantic features of multiple spatial locations, the time-frequency resource location indicating the weight of the Decoder network, and the time-frequency location of the semantic feature data of the spatial perception node requested by the vehicle.

[0095] Among them, the perceptual semantic features of multiple spatial locations are multiplexed through frequency division, time division and code division methods;

[0096] Among them, the time-frequency resource location of the Decoder network weights and the time-frequency location of the semantic feature data of the spatial perception node requested by the vehicle need to maintain a minimum time interval.

[0097] The first and second indication information sent by the road test communication unit can be sent together.

[0098] Optionally, the time-frequency position of sending the semantic features of the perceived data and the time-frequency position of sending the Decoder network weight information satisfy a minimum time interval.

[0099] The minimum time interval is mainly determined by the processing capability of the vehicle. This is because it takes a lot of time for the vehicle to receive weight information and then decode the features using the weight information. A fixed value can be defined in advance, or the vehicle can report its own processing capability level in advance through the uplink, and the road test communication unit can determine the time interval according to different capability levels.

[0100] In one feasible implementation, the embodiments of the present invention are mainly applied in intelligent connected vehicle architectures to realize semantic communication transmission of sensing data. The embodiments provided by the present invention are for a scenario where the roadside communication unit sends data on demand, i.e., the vehicle requests the roadside communication unit to send data. The specific implementation process includes: the roadside communication unit sends a first indication message via the downlink, indicating the sensing node information within its service area; the vehicle receives the first indication message and sends a sensing data request in the uplink; the roadside communication unit sends a second indication message in the downlink; the vehicle receives Decoder network weight information according to the second indication message and applies the received Decoder network weight information; the vehicle receives the requested semantic feature data according to the second indication message and uses the Decoder network weight information to restore the received sensing semantic features into the original sensing information. In this embodiment, the roadside communication unit sends data only on demand for a single vehicle request and does not perform periodic sending.

[0101] In this embodiment of the invention, the sensing data acquired by the road sensing device is first broadcast via a roadside communication unit, and a first indication message is sent. This first indication message includes a valid version number and radio resource information for the Decoder network weight information. Next, the vehicle receives the first indication message broadcast by the roadside communication unit and sends a sensing data request. The vehicle determines whether to update the Decoder network weight based on its own weight information version number. If the vehicle's own weight information version number does not meet the requirements for a valid version number, the vehicle receives the radio resource information for the Decoder network weight information, obtains the version number, and updates its local version number. The roadside communication unit then broadcasts a second indication message, which includes the time-frequency location of the semantic features of the sensing data. Finally, based on the second indication message, the vehicle receives the sensing semantic features in the corresponding radio resource information and, using the received radio resource information for the Decoder network weight information, restores the received sensing semantic features to the original sensing information.

[0102] This invention proposes a weight-feature joint scheduling mechanism, which resolves resource conflicts between weight updates and feature transmission through dynamic version number management and minimum time interval constraints. It also proposes a time-frequency resource joint indication mechanism, which dynamically allocates weight and feature resources through indication information and supports time-division or frequency-division multiplexing of multimodal data. Furthermore, it designs a multimodal on-demand indication strategy, allowing vehicles to selectively receive fused features or single-modal features, reducing redundant transmission. Using this invention can improve transmission efficiency and enhance reliability under low signal-to-noise ratio conditions.

[0103] Figure 5 This is a block diagram illustrating a vehicle-to-everything (V2X) sensing data transmission device according to an exemplary embodiment. The device is used in a V2X sensing data transmission method. (Refer to...) Figure 5 The device includes a roadside communication unit 510 and a vehicle terminal 520. Among them:

[0104] The road test communication unit 510 is used to broadcast the sensing data acquired by the road sensing device and send first indication information; wherein, the first indication information includes: a valid version number and the time, frequency and location of the Decoder network weight information; and broadcast second indication information; wherein, the second indication information includes radio resource information of the semantic features of the sensing data.

[0105] The vehicle terminal 520 is used to receive the first indication information broadcast by the roadside communication unit and send a perception data request. The vehicle terminal determines whether it needs to update the Decoder network weight based on its own weight information version number. When the vehicle terminal's own weight information version number does not meet the requirements of a valid version number, the vehicle terminal receives the radio resource information of the Decoder network weight information, obtains the version number, and updates the local version number. Based on the second indication information, the vehicle terminal receives the perception semantic features in the corresponding radio resource information, and restores the received perception semantic features to the original perception information through the radio resource information of the received Decoder network weight information.

[0106] Optionally, the first indication information is used to demodulate the time-frequency location of the weighted resources of the semantic feature information of the region;

[0107] The first indication information further includes: demodulation information of the demodulator network weight information, the number of sensing nodes, the three-dimensional spatial position of the nodes, and the data modality of each node;

[0108] The demodulation information of the demodulator network weight information includes: a demodulation reference signal and a demodulation key;

[0109] The sensing nodes include: lidar, millimeter-wave radar, and cameras;

[0110] The valid version number is used by the vehicle to determine whether it needs to update its own weight value.

[0111] Optionally, the second indication information may also include a version number indication, a time-frequency location indication of multimodal semantic features, spatial location coordinates, and a unique vehicle identifier;

[0112] The version number is used to determine whether the indicated time-frequency location semantic features can be demodulated.

[0113] The spatial location coordinates refer to the three-dimensional spatial coordinates of the roadside sensing device and the time-frequency location of the sensing semantic features associated with the spatial location.

[0114] Optionally, the method for indicating the time-frequency location of the perceived semantic features includes: a fusion feature indication method and a separate indication method;

[0115] Among them, the fusion feature indication method refers to performing multimodal fusion of the obtained lidar features, millimeter wave features and image features to obtain perceptual fusion features, and indicating the time and frequency position of the perceptual fusion features;

[0116] Among them, the individual indication method refers to indicating the time-frequency position of a single mode separately.

[0117] Optionally, the second indication information is used to indicate the perceptual semantic features of multiple spatial locations, the time-frequency resource location indicating the weight of the Decoder network, and the time-frequency location of the semantic feature data of the spatial perception node requested by the vehicle.

[0118] The perceptual semantic features of the multiple spatial locations are multiplexed using frequency division, time division, and code division methods.

[0119] Among them, the time-frequency resource location of the Decoder network weights and the time-frequency location of the semantic feature data of the spatial perception node requested by the vehicle need to maintain a minimum time interval.

[0120] Optionally, the time-frequency position of sending the semantic features of the perceived data and the time-frequency position of sending the Decoder network weight information satisfy a minimum time interval.

[0121] Optionally, the first indication information and the Decoder network weight information are kept at a minimum time interval.

[0122] In this embodiment of the invention, the sensing data acquired by the road sensing device is first broadcast via a roadside communication unit, and a first indication message is sent. This first indication message includes a valid version number and radio resource information for the Decoder network weight information. Next, the vehicle receives the first indication message broadcast by the roadside communication unit and sends a sensing data request. The vehicle determines whether to update the Decoder network weight based on its own weight information version number. If the vehicle's own weight information version number does not meet the requirements for a valid version number, the vehicle receives the radio resource information for the Decoder network weight information, obtains the version number, and updates its local version number. The roadside communication unit then broadcasts a second indication message, which includes the time-frequency location of the semantic features of the sensing data. Finally, based on the second indication message, the vehicle receives the sensing semantic features in the corresponding radio resource information and, using the received radio resource information for the Decoder network weight information, restores the received sensing semantic features to the original sensing information.

[0123] This invention proposes a weight-feature joint scheduling mechanism, which resolves resource conflicts between weight updates and feature transmission through dynamic version number management and minimum time interval constraints. It also proposes a time-frequency resource joint indication mechanism, which dynamically allocates weight and feature resources through indication information and supports time-division or frequency-division multiplexing of multimodal data. Furthermore, it designs a multimodal on-demand indication strategy, allowing vehicles to selectively receive fused features or single-modal features, reducing redundant transmission. Using this invention can improve transmission efficiency and enhance reliability under low signal-to-noise ratio conditions.

[0124] Figure 6 This is a schematic diagram of the structure of a vehicle-to-everything (V2X) sensing data transmission device provided in an embodiment of the present invention, as shown below. Figure 6 As shown, the vehicle-to-everything (V2X) sensing data transmission device may include the above-mentioned Figure 5 The illustrated vehicle-to-everything (V2X) sensing data transmission device. Optionally, the V2X sensing data transmission device 610 may include a first processor 2001.

[0125] Optionally, the vehicle-to-everything (V2X) sensing data transmission device 610 may also include a memory 2002 and a transceiver 2003.

[0126] The first processor 2001, memory 2002, and transceiver 2003 can be connected via a communication bus.

[0127] The following is combined with Figure 6 A detailed introduction to each component of the vehicle-to-everything (V2X) sensing and data transmission device 610 is provided below:

[0128] The first processor 2001 is the control center of the vehicle-to-everything (V2X) sensing and data transmission device 610. It can be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 can be one or more central processing units (CPUs), application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0129] Optionally, the first processor 2001 can perform various functions of the vehicle-to-everything (V2X) sensing data transmission device 610 by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0130] In a specific implementation, as one example, the first processor 2001 may include one or more CPUs, for example... Figure 6 CPU0 and CPU1 are shown in the diagram.

[0131] In a specific implementation, as one example, the vehicle-to-everything (V2X) sensing data transmission device 610 may also include multiple processors, for example... Figure 6The first processor 2001 and the second processor 2004 are shown in the diagram. Each of these processors can be a single-core processor or a multi-core processor. Here, a processor can refer to one or more devices, circuits, and / or processing cores used to process data (such as computer program instructions).

[0132] The memory 2002 is used to store the software program that executes the present invention, and is controlled by the first processor 2001 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0133] Optionally, the memory 2002 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 2002 may be integrated with the first processor 2001 or may exist independently, and may be connected via the interface circuit of the vehicle network sensing data transmission device 610. Figure 6 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0134] The transceiver 2003 is used to communicate with network devices or with terminal devices.

[0135] Alternatively, transceiver 2003 may include a receiver and a transmitter. Figure 6 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0136] Optionally, the transceiver 2003 can be integrated with the first processor 2001, or it can exist independently and be connected to the interface circuit of the vehicle network sensing data transmission device 610. Figure 6 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0137] It should be noted that, Figure 6 The structure of the vehicle-to-everything (V2X) sensing data transmission device 610 shown in the diagram does not constitute a limitation on the router. Actual knowledge structure identification devices may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0138] Furthermore, the technical effects of the vehicle-to-everything (V2X) sensing data transmission device 610 can be referenced from the technical effects of the V2X sensing data transmission method described in the above method embodiments, and will not be repeated here.

[0139] It should be understood that the first processor 2001 in the embodiments of the present invention may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0140] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0141] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0142] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0143] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0144] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0145] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0146] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0147] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0148] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0149] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0150] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0151] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for transmitting sensing data in a vehicle-to-everything (V2X) network, characterized in that, The method includes: S1. The roadside communication unit broadcasts the sensing data acquired by the road sensing device and sends first indication information; wherein, the first indication information includes: a valid version number, wireless resource information such as Decoder network weight information; S2. The vehicle receives the first indication information broadcast by the roadside communication unit and sends a perception data request. The vehicle determines whether it needs to update the Decoder network weight based on its own weight information version number. When the vehicle's own weight information version number does not meet the valid version number, the vehicle receives the radio resource information of the Decoder network weight information, obtains the version number, and updates the local version number. S3. The road test communication unit broadcasts and sends a second indication information; wherein, the second indication information includes the time-frequency location of the semantic features of the transmitted sensing data; S4. Based on the second instruction information, the vehicle terminal receives the perceptual semantic features in the corresponding radio resource information, and restores the received perceptual semantic features into the original perceptual information through the radio resource information of the received Decoder network weight information.

2. The vehicle-to-everything (V2X) sensing data transmission method according to claim 1, characterized in that, The first indication information is used to demodulate the time-frequency position of the weighted resources of the semantic feature information in this region; The first indication information further includes: demodulation information of the demodulator network weight information, the number of sensing nodes, the three-dimensional spatial position of the nodes, and the data modality of each node; The demodulation information of the demodulator network weight information includes: a demodulation reference signal and a demodulation key; The sensing nodes include: lidar, millimeter-wave radar, and cameras; The valid version number is used by the vehicle to determine whether it needs to update its own weight value.

3. The vehicle-to-everything (V2X) sensing data transmission method according to claim 1, characterized in that, The second indication information also includes a version number indication, a time-frequency location indication of multimodal semantic features, spatial location coordinates, and a unique vehicle identifier; The version number is used to determine whether the indicated time-frequency location semantic features can be demodulated. The spatial location coordinates refer to the three-dimensional spatial coordinates of the roadside sensing device and the time-frequency location of the sensing semantic features associated with the spatial location.

4. The vehicle-to-everything (V2X) sensing data transmission method according to claim 3, characterized in that, The methods for indicating the time-frequency location of the perceived semantic features include: a fusion feature indication method and a separate indication method; Among them, the fusion feature indication method refers to performing multimodal fusion of the obtained lidar features, millimeter wave features and image features to obtain perceptual fusion features, and indicating the time and frequency position of the perceptual fusion features; Among them, the individual indication method refers to indicating the time-frequency position of a single mode separately.

5. The vehicle-to-everything (V2X) sensing data transmission method according to claim 1, characterized in that, The second indication information is used to indicate the perceptual semantic features of multiple spatial locations, the time-frequency resource location indicating the weight of the Decoder network, and the time-frequency location of the semantic feature data of the spatial perception node requested by the vehicle. The perceptual semantic features of the multiple spatial locations are multiplexed using frequency division, time division, and code division methods. Among them, the time-frequency resource location of the Decoder network weights and the time-frequency location of the semantic feature data of the spatial perception node requested by the vehicle need to maintain a minimum time interval.

6. The vehicle-to-everything (V2X) sensing data transmission method according to claim 5, characterized in that, The time-frequency position of sending the semantic features of the sensing data and the time-frequency position of sending the Decoder network weight information satisfy a minimum time interval.

7. The vehicle-to-everything (V2X) sensing data transmission method according to claim 1, characterized in that, The first indication information and the Decoder network weight information maintain a minimum time interval.

8. A vehicle-to-everything (V2X) sensing data transmission device, wherein the V2X sensing data transmission device is used to implement the V2X sensing data transmission method as described in any one of claims 1-7, characterized in that, The device includes: The road test communication unit is used to broadcast the sensing data acquired by the road sensing device and send a first indication information; wherein the first indication information includes: a valid version number, radio resource information such as Decoder network weight information; and broadcast a second indication information; wherein the second indication information includes the time-frequency location of the semantic features of the transmitted sensing data. The vehicle-side terminal receives the first indication information broadcast by the roadside communication unit and sends a sensing data request. Based on its own weight information version number, the vehicle-side terminal determines whether to update the Decoder network weights. When the vehicle-side terminal's own weight information version number does not meet the requirements for a valid version number, the vehicle-side terminal receives the radio resource information of the Decoder network weight information, obtains the version number, and updates its local version number. Based on the second indication information, the vehicle-side terminal receives sensing semantic features in the corresponding radio resource information and uses the received radio resource information of the Decoder network weight information to restore the received sensing semantic features into the original sensing information.

9. A vehicle-to-everything (V2X) sensing data transmission device, characterized in that, The vehicle-to-everything (V2X) sensing data transmission device includes: processor; A memory storing computer-readable instructions that, when executed by the processor, implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains program code that can be invoked by a processor to execute the method as described in any one of claims 1 to 7.

Images