Vehicle state sensing method and system in cooperative vehicle infrastructure environment

Abstract

The invention discloses a vehicle state sensing method and system in a vehicle-road cooperation environment, and relates to the technical field of intelligent traffic, and the method comprises the steps: collecting the real-time traffic data of a target intersection; establishing a temporary V2X communication link; receiving real-time traffic data and K pieces of real-time vehicle state information of K running vehicles; if the one-dimensional risk detection results of the roadside edge computing device on the real-time traffic data and the K pieces of real-time vehicle state information are set to be 0, compensating the K pieces of real-time vehicle state information by adopting the real-time traffic data to obtain K pieces of compensated vehicle state information, constructing a global dynamic traffic model, and performing track conflict prediction and potential collision risk positioning; and according to the risk avoidance priority, broadcasting the potential collision risk to K running vehicles through a V2X communication link. The technical problems of inaccurate traffic modeling and untimely collision risk identification caused by incomplete vehicle-mounted sensing information in the prior art are solved, and the technical effects of improving the vehicle state sensing accuracy and the collision risk early warning timeliness are achieved.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation technology, specifically to a vehicle status perception method and system in a vehicle-road cooperative environment. Background Technology

[0002] In a vehicle-road cooperative environment, vehicles typically rely on onboard sensing devices to obtain information about their own status and the surrounding environment. However, due to limitations such as line-of-sight obstruction, weather interference, or sensing range, the information obtained by onboard devices suffers from poor timeliness and incompleteness, resulting in incomplete vehicle status information. This makes it difficult to accurately model the dynamic relationships of multiple vehicles in complex scenarios such as intersections, affecting the timely identification and effective avoidance of potential collision risks. Summary of the Invention

[0003] This application provides a vehicle status perception method and system in a vehicle-road cooperative environment, which is used to address the technical problems of inaccurate traffic modeling and untimely collision risk identification caused by incomplete vehicle perception information in existing technologies.

[0004] In view of the above problems, this application provides a vehicle status perception method and system in a vehicle-road cooperative environment.

[0005] The first aspect of this application provides a vehicle status perception method in a vehicle-road cooperative environment, the method comprising:

[0006] A roadside sensor network collects real-time traffic data of a target intersection using millimeter-wave radar. Based on geofencing, the onboard unit (OBU) of vehicles entering the target intersection establishes a temporary V2X communication link with the roadside edge computing device. The roadside edge computing device receives the real-time traffic data and K real-time vehicle status information from K vehicles, where K ≥ 2 and K is a positive integer. If the roadside edge computing device sets the single-dimensional risk detection results of the real-time traffic data and the K real-time vehicle status information to 0, then the real-time traffic data is used to compensate for the K real-time vehicle status information, resulting in K compensated vehicle status information. A global dynamic traffic model is constructed based on the K compensated vehicle status information. Trajectory conflict prediction is performed based on the global dynamic traffic model to locate potential collision risks. According to risk avoidance priority, the potential collision risks are broadcast to the K vehicles via the V2X communication link.

[0007] A second aspect of this application provides a vehicle status perception system in a vehicle-road cooperative environment, the system comprising:

[0008] The system includes the following modules: a traffic data acquisition module for collecting real-time traffic data from a target intersection via millimeter-wave radar using a roadside sensor network; a communication link establishment module for establishing a temporary V2X communication link between the onboard unit (OBU) of a vehicle entering the target intersection and the roadside edge computing device based on a geofence; an information receiving module for receiving the real-time traffic data and K real-time vehicle status information from K vehicles, where K ≥ 2 and K is a positive integer; a compensation module for compensating the K real-time vehicle status information with the real-time traffic data if the roadside edge computing device sets the single-dimensional risk detection results of the real-time traffic data and the K real-time vehicle status information to 0, thus obtaining K compensated vehicle status information; a traffic model construction module for constructing a global dynamic traffic model based on the K compensated vehicle status information; a trajectory conflict prediction module for predicting trajectory conflicts based on the global dynamic traffic model and locating potential collision risks; and a broadcast module for broadcasting the potential collision risks to the K vehicles via the V2X communication link according to risk avoidance priorities.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] This application's roadside sensor network collects real-time traffic data from a target intersection using millimeter-wave radar; based on geofencing, it triggers the onboard unit (OBU) of vehicles entering the target intersection to establish a temporary V2X communication link with the roadside edge computing device; the roadside edge computing device receives the real-time traffic data and K real-time vehicle status information from K vehicles, where K ≥ 2 and K is a positive integer; if the roadside edge computing device sets the single-dimensional risk detection results of the real-time traffic data and the K real-time vehicle status information to 0, then it uses the real-time traffic data to compensate for the K real-time vehicle status information, obtaining K compensated vehicle status information; a global dynamic traffic model is constructed based on the K compensated vehicle status information; trajectory conflict prediction is performed based on the global dynamic traffic model to locate potential collision risks; according to risk avoidance priority, the potential collision risks are broadcast to the K vehicles via the V2X communication link. This invention addresses the technical problems of inaccurate traffic modeling and untimely collision risk identification caused by incomplete vehicle-mounted perception information in existing technologies. By introducing roadside sensor data to compensate for vehicle-mounted vehicle status information and constructing a global dynamic traffic model for trajectory conflict prediction, the invention achieves the technical effect of improving the accuracy of vehicle status perception and the timeliness of collision risk warning. Attached Figure Description

[0011] 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.

[0012] Figure 1 This is a schematic flowchart of a vehicle status perception method in a vehicle-road cooperative environment provided in an embodiment of this application;

[0013] Figure 2 This is a schematic diagram of the vehicle status perception system in a vehicle-road cooperative environment provided in an embodiment of this application.

[0014] Figure labeling: Traffic data acquisition module 11, communication link establishment module 12, information receiving module 13, compensation module 14, traffic model construction module 15, trajectory conflict prediction module 16, broadcasting module 17. Detailed Implementation

[0015] This application provides a vehicle status perception method and system in a vehicle-road cooperative environment. It addresses the technical problems of inaccurate traffic modeling and untimely collision risk identification caused by incomplete vehicle-mounted perception information in existing technologies. By introducing roadside sensor data to compensate for vehicle-mounted vehicle status information and constructing a global dynamic traffic model for trajectory conflict prediction, it achieves the technical effect of improving the accuracy of vehicle status perception and the timeliness of collision risk warning.

[0016] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0017] It should be noted that any variation of the terms "comprising" and "having" is intended to cover non-exclusive inclusion, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to such processes, methods, products, or devices.

[0018] Example 1, as Figure 1 As shown, this application provides a vehicle status perception method in a vehicle-road cooperative environment, the method comprising:

[0019] Step S100: The roadside sensor network collects real-time traffic data of the target intersection using millimeter-wave radar.

[0020] In this embodiment, the side-sensing network collects real-time traffic data of the target intersection using millimeter-wave radar. The millimeter-wave radar detects vehicles within the target intersection by transmitting and receiving electromagnetic signals, acquiring information such as their position, speed, and distance. When the radar signal encounters an object, it is reflected back to the receiver. By measuring the round-trip time of the signal, the precise distance and relative speed of the object are calculated, thereby obtaining real-time traffic data for each vehicle within the target intersection.

[0021] Step S200: Based on the geofence, the on-board OBU of the vehicle entering the target intersection is triggered to establish a temporary V2X communication link with the roadside edge computing device.

[0022] In this embodiment, a temporary V2X communication link is established between the on-board unit (OBU) and the roadside edge computing device when a vehicle enters a target intersection, triggered by a geofencing mechanism. Specifically, geofencing first defines a virtual boundary around the target intersection, and once a vehicle enters this area, the geofencing system triggers an event. The on-board unit (OBU), as an intelligent device within the vehicle, monitors the vehicle's location in real time. When the vehicle enters the virtual boundary, the OBU obtains the vehicle's accurate location using GPS or other positioning systems and sends the current location data to the roadside edge computing device. Upon receiving the vehicle's location data, the roadside edge computing device initiates a V2X (Vehicle-to-Everything) communication link. This is a temporary data transmission connection based on wireless communication technology, enabling rapid information exchange between the vehicle and roadside equipment. Through this communication link, the on-board unit (OBU) and the roadside edge computing device can achieve bidirectional transmission of vehicle status data and real-time traffic information, ensuring efficient interaction between the vehicle and the traffic management system.

[0023] Step S300: The roadside edge computing device receives the real-time traffic data and K real-time vehicle status information of K vehicles, where K≥2 and K is a positive integer.

[0024] In this embodiment, the edge computing device receives real-time traffic data and K real-time vehicle status information from K vehicles, where K ≥ 2 and K is a positive integer. Specifically, the roadside sensor network continuously monitors the traffic conditions at the target intersection using sensors such as millimeter-wave radar, acquiring real-time traffic data, such as vehicle quantity, flow rate, density, and other traffic environment information. Simultaneously, the onboard unit (OBU) monitors and transmits real-time vehicle status information, including location, speed, acceleration, and turn signal status. This vehicle status information is collected in real-time by onboard devices: vehicle location is obtained via GPS, speed and acceleration are provided by onboard sensors (such as vehicle speed sensors and accelerometers), and turn signal status is detected by the vehicle's control system. When K vehicles enter the coverage area of ​​the roadside sensor network, the onboard OBU sends the vehicle status information and current location of each vehicle to the roadside edge computing device via a V2X communication link.

[0025] Step S400: If the roadside edge computing device sets the single-dimensional risk detection results of the real-time traffic data and the K real-time vehicle status information to 0, then the real-time traffic data is used to compensate the K real-time vehicle status information to obtain K compensated vehicle status information.

[0026] In this embodiment, the roadside edge computing device first performs single-dimensional risk detection on the real-time vehicle status information of each vehicle, checking whether there are risks in each dimension (such as vehicle position, speed, acceleration, turn signal status, etc.). For example, the vehicle speed is compared with the speed limit, the acceleration is compared with a preset threshold, the turn signal status is checked to see if it is consistent with the vehicle's direction of travel, and the vehicle position is compared with the lane boundary. If the detection result of any dimension shows that there is a risk, the device will set the corresponding detection result to 1, indicating that there is a potential risk; if the detection results of all dimensions are 0, it means that no abnormal risk has been detected in the current state of the vehicle.

[0027] When all single-dimensional risk detection results are 0, the roadside edge computing device uses real-time traffic data to compensate for the vehicle status information of K vehicles. Real-time traffic data includes traffic flow on the road surface, the position and speed information of other vehicles, etc., which can provide a reference for the compensation process. When a vehicle's status information (such as speed, position, etc.) is incorrect or missing, the roadside edge computing device will use real-time traffic data to compensate for it. For example, based on the traffic flow at the target intersection and the status of adjacent vehicles, the device can infer the possible position or speed of a vehicle. In this way, the device can fuse real-time traffic data with the vehicle status information of K moving vehicles to generate K compensated vehicle status information.

[0028] Furthermore, the method provided in the application embodiments also includes:

[0029] Based on the traffic condition information of the target intersection, traffic-related risk features are matched and invoked; the roadside edge computing device uses the traffic-related risk features to traverse the real-time traffic data and outputs a first risk detection result; based on the location information of the target intersection, driving speeding features are invoked via network; the roadside edge computing device uses the driving speeding features to traverse the K real-time vehicle status information and outputs a second risk detection result; if both the first risk detection result and the second risk detection result are set to 0, the real-time traffic data is used to compensate the K real-time vehicle status information to obtain K compensated vehicle status information.

[0030] In this embodiment, the roadside edge computing device first matches and calls the corresponding traffic-related risk feature template in a local or cloud database based on the monitored current traffic condition information of the target intersection (such as traffic density, road topology, signal status, etc.). Common risk features include two key indicators: insufficient vehicle spacing and vehicles driving in the wrong direction. The vehicle spacing is determined based on whether the Euclidean distance between vehicles is less than a dynamic safety threshold, which is dynamically set according to vehicle speed and traffic environment. Driving in the wrong direction is determined based on whether the angle between the vehicle's actual driving direction and the road topology-defined direction exceeds a set threshold (e.g., 180°±30°). Subsequently, a sliding window traversal method is used to analyze the traffic data sequence transmitted from the radar frame by frame, performing spatial relationship analysis and directional consistency verification for each pair of vehicles, and outputting the first risk detection result.

[0031] After completing the traffic environment risk feature detection, the roadside edge computing device, based on the geographical coordinates of the intersection, connects to the network to obtain the corresponding speed limit standards and driving regulations for that road segment, and calls upon speeding features. At this stage, the speed field is extracted from the real-time vehicle status information of K vehicles, and analyzed using a discrimination method based on the upper and lower threshold ranges of the speed limit. If a vehicle's speed exceeds the set speed limit threshold (e.g., a speed limit of 60 km / h with a tolerance of ±10%), the vehicle is considered to have a speeding risk. The detection method combines timestamps and location data to perform dynamic rate calculation; that is, by dividing the position difference between adjacent moments by the time interval, a more realistic instantaneous speed is obtained. After completing the analysis of the K vehicles, a second risk detection result is generated.

[0032] After receiving the results of the first and second risk detections, a Boolean logic judgment is performed. If none of the K vehicles trigger an alarm in either of the two risk dimensions (i.e., all detection results are 0), it is considered that there is no significant traffic conflict or abnormal behavior at the current intersection, and the conditions for activating the compensation mechanism are met.

[0033] Assuming all risk detection results are 0, real-time traffic data is used to compensate for K real-time vehicle status information. This process begins by extracting the real-time position data of each vehicle from the K real-time vehicle status information. Next, the positions of these vehicles are offset by combining the real-time traffic data to correct position deviations caused by signal interference or sensor errors, generating K compensated vehicle positions. Subsequently, based on these compensated vehicle positions, real-time speed and heading angle information related to each vehicle are extracted from the real-time traffic data. This detection status data is then weighted and fused with the original vehicle status information to ensure greater accuracy of the compensated data. Finally, the compensated vehicle positions are mapped back to the original vehicle status information, outputting K compensated vehicle status information.

[0034] Furthermore, the method provided in the application embodiments also includes:

[0035] The traffic-related risk features include vehicle safety distance constraints and vehicle driving direction constraints; the real-time traffic data is traversed using the vehicle safety distance constraints and vehicle driving direction constraints to locate real-time risk vehicles, which are used as the first risk detection result; if the first risk detection result is set to 1, the real-time V2X communication link of the real-time risk vehicle is invoked based on the K real-time vehicle status information; a risk alarm is sent to the real-time risk vehicle using the real-time V2X communication link.

[0036] In this embodiment, traffic-related risk characteristics include vehicle safety distance constraints and vehicle driving direction constraints. First, the roadside edge computing device acquires real-time traffic data, including the position, speed, acceleration, and driving direction of each vehicle. Vehicle safety distance constraints ensure that the safe distance between adjacent vehicles is not lower than a preset standard by calculating the distance between them. This standard is generally set based on dynamic factors such as vehicle speed, road conditions, and speed changes. If the distance between vehicles is less than the safe distance, it indicates a potential collision risk. Similarly, vehicle driving direction constraints compare the vehicle's actual driving direction with the prescribed driving direction on the road. If a vehicle deviates from the correct driving lane or drives in the wrong direction, its behavior constitutes a potential risk.

[0037] When the roadside edge computing device applies these two constraints to real-time traffic data, it iterates through the relative positions of each vehicle and its surroundings, calculates safe distances, and determines whether the vehicle's driving direction is compliant. If a vehicle's safe distance from the vehicle in front or around it is too small, or if the vehicle is driving in the wrong direction or deviating from its driving path, the device identifies it as a real-time risk vehicle and outputs a first risk detection result. If the detection result is 1, it indicates that a potential risk vehicle has been identified.

[0038] If the initial risk detection result is 1, the roadside edge computing device utilizes K real-time vehicle status information, particularly real-time vehicle position, speed, and acceleration data, to invoke the V2X communication link of the vehicle at risk. The V2X communication link is the data communication interface between vehicles and other vehicles or roadside facilities. Through the V2X communication link, the roadside edge computing device can establish a communication connection with the vehicle at risk and send risk warnings to it in real time. This warning alerts the driver to potential hazards or abnormal situations ahead, allowing them to take appropriate countermeasures and reduce the risk of potential collisions.

[0039] Furthermore, in the method provided in the application embodiment, after sending a risk alarm to the real-time risk vehicle using the real-time V2X communication link, it further includes:

[0040] A preset alarm execution window is established; after the delay in sending a risk alarm to the real-time risk vehicle meets the alarm execution window, the roadside edge computing device receives the updated traffic data transmitted back from the roadside sensor network coverage; the roadside edge computing device uses the traffic-related risk characteristics to determine the existence of associated risks in the updated traffic data.

[0041] In this embodiment, the preset alarm execution window refers to a time range set after a risk alarm is sent to ensure a timely response. This time window is preset by technical experts based on factors such as traffic conditions at the intersection and vehicle reaction time to ensure that the driver has sufficient time to receive the alarm and take appropriate measures. The duration of the alarm execution window typically takes into account variables such as vehicle speed, reaction delay, and road characteristics to ensure that the alarm information is effective and can be handled by the driver in a timely manner.

[0042] After the risk alert is sent to a vehicle at real-time risk within the specified timeframe (meeting the alert execution window), the roadside edge computing device begins receiving updated traffic data from the roadside sensor network. The roadside sensor network includes sensors such as millimeter-wave radar, cameras, and lidar, which collect vehicle information and traffic condition data within the target area and transmit this data to the edge computing device in real time. This updated traffic data includes vehicle location information, speed, acceleration, traffic flow, and road condition changes.

[0043] Upon receiving updated traffic data, the roadside edge computing device combines traffic-related risk characteristics to determine the persistence of associated risks. These characteristics include multi-dimensional features such as safe distance between vehicles, vehicle speed, and direction of travel. For example, the device determines whether a collision risk still exists based on the vehicle's current position and distance from other vehicles; simultaneously, it assesses whether the vehicle has taken appropriate deceleration measures based on vehicle speed and road conditions. The device analyzes these risk characteristics to determine whether potential risks persist. If the risk persists, monitoring continues; if the risk has been eliminated, the risk status is updated and tracking is terminated.

[0044] Furthermore, in the method provided in the application embodiment, the real-time traffic data is used to compensate the K real-time vehicle status information to obtain K compensated vehicle status information, which further includes:

[0045] K real-time vehicle positions are retrieved from the K real-time vehicle status information; the K real-time vehicle positions are verified using the real-time traffic data to perform offset compensation, resulting in K compensated vehicle positions; based on the K compensated vehicle positions, K sets of detection status data are retrieved from the real-time traffic data, wherein the detection status data includes vehicle real-time speed and vehicle heading angle; the K sets of detection status data are mapped, weighted, and fused into the K real-time vehicle status information; the K compensated vehicle positions are used to map and cover the K real-time vehicle status information, and the K compensated vehicle status information is output.

[0046] In this embodiment, K real-time vehicle positions are first extracted from K real-time vehicle status information. The real-time vehicle status information for each vehicle has already been acquired through the onboard unit (OBU) and vehicle sensor system, including data such as the vehicle's real-time position, speed, acceleration, and heading angle. In this step, these acquired real-time vehicle position data are directly accessed and extracted via a V2X communication link or other data acquisition network, ensuring that the device can extract K real-time vehicle positions from the existing data.

[0047] Next, real-time traffic data is used to verify the positions of K real-time vehicles and perform offset compensation. Real-time traffic data is typically collected by roadside sensors (such as millimeter-wave radar) and includes information on the positions of other vehicles, traffic flow, and vehicle speed. During this process, this real-time traffic data is compared with the K real-time vehicle positions to determine if any positional offset exists. If an offset is found, the device compensates for the position of each vehicle using a spatial correction algorithm (such as Kalman filtering or least squares method), thus obtaining K compensated vehicle positions. This compensation process ensures more accurate vehicle positions and reduces the impact of GPS errors or other measurement errors.

[0048] After completing vehicle position compensation, K sets of detection status data are extracted from real-time traffic data based on the K compensated vehicle positions. The detection status data includes the vehicle's real-time speed and heading angle, which are acquired in real-time by onboard sensors (such as vehicle speed sensors, accelerometers, gyroscopes, etc.). The equipment will extract real-time speed and heading angle data related to the K compensated vehicle positions from the real-time traffic data to form K sets of detection status data.

[0049] Finally, the extracted K sets of detection state data are weighted and fused with the K compensated vehicle positions. The weighted fusion process ensures data accuracy by combining the weights of each data point. The device uses data fusion techniques such as weighted averaging or Kalman filtering to fuse the real-time speed, acceleration, and heading angle of each vehicle with the compensated vehicle positions to obtain the final K compensated vehicle state information.

[0050] Step S500: Construct a global dynamic traffic model based on the K compensated vehicle status information.

[0051] In this embodiment, when constructing a global dynamic traffic model based on K compensated vehicle state information, the K compensated vehicle state information are first associated with the lane topology to generate globally bound vehicle state information, ensuring that the dynamic data of each vehicle matches the structure of its lane. Next, this globally bound vehicle state information is used to perform multi-target trajectory tracking on the K vehicles, outputting their respective real-time trajectory sequences. Finally, these real-time trajectory sequences are fitted into the spatial modeling of the target intersection to obtain the final global dynamic traffic model.

[0052] Furthermore, in the method provided in the application embodiments, constructing a global dynamic traffic model based on the K compensated vehicle status information further includes:

[0053] The K compensated vehicle state information is associated with the lane topology to obtain globally bound vehicle state information; multi-target trajectory tracking is performed on the K driving vehicles based on the globally bound vehicle state information to output K real-time trajectory sequences; the K real-time trajectory sequences are fitted to the spatial model of the target intersection to obtain the global dynamic traffic model.

[0054] In this embodiment, K compensated vehicle state information pieces are first associated with lane topology. During this process, spatial mapping technology is used to match the dynamic data such as vehicle position and speed in each compensated vehicle state information piece with the lane topology data of the intersection. Lane topology data includes the geometry of each lane at the intersection, lane connectivity, and traffic flow direction. By mapping the vehicle state information to specific lane locations, the dynamic state of the vehicle in its corresponding lane is accurately reflected, thereby generating globally bound vehicle state information.

[0055] Next, based on the globally bound vehicle status information, multi-target trajectory tracking is performed on K vehicles, outputting K real-time trajectory sequences. In this process, the multi-target trajectory tracking (MOT) algorithm is used to track the dynamic data of the K vehicles in real time, outputting K real-time trajectory sequences representing the driving trajectory of each vehicle.

[0056] Finally, the K real-time trajectory sequences are fitted to the spatial model of the target intersection to obtain a global dynamic traffic model. The device combines the lane topology data of the intersection with the real-time trajectory sequences, using a spatial modeling algorithm to map the vehicle trajectories onto the intersection's geometry. This fitting process considers not only the road geometry but also factors such as traffic signals, lane-changing rules, and traffic flow to ensure that the vehicle's trajectory matches the intersection's layout and traffic rules. Ultimately, this process yields a global dynamic traffic model that reflects traffic flow and vehicle behavior in and around the intersection.

[0057] Step S600: Based on the global dynamic traffic model, predict trajectory conflicts and locate potential collision risks.

[0058] In this embodiment, when predicting trajectory conflicts and locating potential collision risks based on a global dynamic traffic model, the potential collision areas are first determined by predefining the distribution of conflict areas according to the lane connection topology of the target intersection. Then, a CTRA model is used to predict the trajectories of K real-time trajectory sequences, generating K predicted temporal trajectories. Next, these predicted temporal trajectories are analyzed using a spatiotemporal overlap algorithm to extract multiple conflict trajectories falling into the predefined conflict areas. Based on the mapping relationship between these conflict trajectories and the predicted trajectories, multiple vehicles involved are located, and their corresponding vehicle IDs are retrieved. Finally, these vehicle IDs are packaged and output as potential collision risks.

[0059] Furthermore, in the method provided in the application embodiments, the method for predicting trajectory conflicts and locating potential collision risks based on the global dynamic traffic model further includes:

[0060] Based on the predefined conflict area distribution of the lane connection topology of the target intersection, the CTRA model is used to predict the trajectory along the K real-time trajectory sequences to obtain K predicted temporal trajectories. After spatiotemporally overlapping the K predicted temporal trajectories, multiple conflict trajectories falling into the conflict area distribution are extracted. Based on the mapping relationship between the multiple conflict trajectories and the K predicted temporal trajectories, multiple driving vehicles are located. After calling the multiple vehicle IDs of the multiple driving vehicles, the multiple vehicle IDs are packaged as the potential collision risk output.

[0061] In this embodiment, based on the predefined conflict zone distribution of the lane connection topology of the target intersection, the potential collision areas are first determined by analyzing the lane structure and traffic flow of the intersection. Conflict zones typically include areas with high traffic flow, such as lane merging points and lane changing zones, which are considered potential collision risk areas. The spatial distribution of these conflict zones is predefined using lane topology data and intersection geometry.

[0062] Next, the CTRA (Continuous-Time RandomAccess) model is used to predict the trajectories of K real-time trajectory sequences. The CTRA model can predict the trajectory of each vehicle at future moments within a continuous time frame, combining information such as the vehicle's current position, speed, and acceleration. This process considers the vehicle's dynamic behavior and generates K predicted time-series trajectories, each describing the vehicle's travel path over a future period.

[0063] After obtaining K predicted time-series trajectories, these trajectories are analyzed using a spatiotemporal overlap method. The spatiotemporal overlap algorithm compares the predicted trajectory of each vehicle with a predefined conflict area distribution to identify which vehicles' trajectories overlap with the conflict areas. Spatiotemporal overlap refers to spatially matching the predicted trajectory of each vehicle and synchronizing it in the time dimension to extract trajectories that fall into the conflict area, thereby identifying multiple conflict trajectories.

[0064] Next, based on the mapping relationship between multiple conflict trajectories and K predicted time-series trajectories, the involved vehicles are located. By comparing each conflict trajectory with the actual driving trajectory of the vehicle, it is determined which vehicles will collide within the conflict area. At this point, using information such as the vehicle's real-time position, speed, and direction of travel, the vehicle IDs involved in the collision risk are extracted, thus identifying these vehicles.

[0065] Finally, multiple vehicle IDs are packaged together as potential collision risks. These vehicle IDs represent vehicles that may collide at some point in the future.

[0066] Step S700: Based on the risk avoidance priority, broadcast the potential collision risk to the K driving vehicles via the V2X communication link.

[0067] In this embodiment, potential collision risks are broadcast to K vehicles via a V2X communication link based on risk avoidance priorities. Specifically, firstly, the severity and urgency of potential collisions are determined based on collision prediction results. Risk avoidance priorities are assessed based on factors such as the spatial overlap of predicted collision risks, time windows, and relative vehicle speeds; the closer a collision is to occurring, the higher the risk priority. Next, a corresponding emergency response level is assigned to each risk based on its assessed risk priority. For high-priority potential collision risks, immediate warnings are broadcast; while for low-priority risks, notifications may be provided later or through other means.

[0068] Once the risk priority is determined, the roadside system broadcasts relevant risk information to K vehicles via V2X communication links. Detailed information about potential collision risks (such as the predicted time and location of the collision, the IDs of the relevant vehicles, and warning information) is sent in real time to the onboard units of the K vehicles. This allows drivers to be aware of the risks in a timely manner and take necessary evasive action, such as slowing down or changing lanes, thereby reducing the occurrence of potential collisions.

[0069] In summary, the embodiments of this application have at least the following technical effects:

[0070] This application's roadside sensor network collects real-time traffic data from a target intersection using millimeter-wave radar; based on geofencing, it triggers the onboard unit (OBU) of vehicles entering the target intersection to establish a temporary V2X communication link with the roadside edge computing device; the roadside edge computing device receives the real-time traffic data and K real-time vehicle status information from K vehicles, where K ≥ 2 and K is a positive integer; if the roadside edge computing device sets the single-dimensional risk detection results of the real-time traffic data and the K real-time vehicle status information to 0, then it uses the real-time traffic data to compensate for the K real-time vehicle status information, obtaining K compensated vehicle status information; a global dynamic traffic model is constructed based on the K compensated vehicle status information; trajectory conflict prediction is performed based on the global dynamic traffic model to locate potential collision risks; according to risk avoidance priority, the potential collision risks are broadcast to the K vehicles via the V2X communication link. This invention addresses the technical problems of inaccurate traffic modeling and untimely collision risk identification caused by incomplete vehicle-mounted perception information in existing technologies. By introducing roadside sensor data to compensate for vehicle-mounted vehicle status information and constructing a global dynamic traffic model for trajectory conflict prediction, the invention achieves the technical effect of improving the accuracy of vehicle status perception and the timeliness of collision risk warning.

[0071] Example 2, based on the same inventive concept as the vehicle status perception method in the vehicle-road cooperative environment in the previous examples, such as... Figure 2As shown, this application provides a vehicle status perception system in a vehicle-road cooperative environment. The system and method embodiments in this application are based on the same inventive concept. The system includes:

[0072] The system includes: a traffic data acquisition module 11 for collecting real-time traffic data of the target intersection via millimeter-wave radar using a roadside sensor network; a communication link establishment module 12 for establishing a temporary V2X communication link between the on-board unit (OBU) of a vehicle entering the target intersection and the roadside edge computing device based on a geofence; an information receiving module 13 for receiving the real-time traffic data and K real-time vehicle status information from K vehicles, where K ≥ 2 and K is a positive integer; a compensation module 14 for compensating the K real-time vehicle status information with the real-time traffic data if the roadside edge computing device sets the single-dimensional risk detection results of the real-time traffic data and the K real-time vehicle status information to 0, thus obtaining K compensated vehicle status information; a traffic model construction module 15 for constructing a global dynamic traffic model based on the K compensated vehicle status information; a trajectory conflict prediction module 16 for predicting trajectory conflicts based on the global dynamic traffic model and locating potential collision risks; and a broadcast module 17 for broadcasting the potential collision risks to the K vehicles via the V2X communication link according to risk avoidance priorities.

[0073] Furthermore, the system is also used to implement the following functions:

[0074] Based on the traffic condition information of the target intersection, traffic-related risk features are matched and invoked; the roadside edge computing device uses the traffic-related risk features to traverse the real-time traffic data and outputs a first risk detection result; based on the location information of the target intersection, driving speeding features are invoked via network; the roadside edge computing device uses the driving speeding features to traverse the K real-time vehicle status information and outputs a second risk detection result; if both the first risk detection result and the second risk detection result are set to 0, the real-time traffic data is used to compensate the K real-time vehicle status information to obtain K compensated vehicle status information.

[0075] Furthermore, the system is also used to implement the following functions:

[0076] The traffic-related risk features include vehicle safety distance constraints and vehicle driving direction constraints; the real-time traffic data is traversed using the vehicle safety distance constraints and vehicle driving direction constraints to locate real-time risk vehicles, which are used as the first risk detection result; if the first risk detection result is set to 1, the real-time V2X communication link of the real-time risk vehicle is invoked based on the K real-time vehicle status information; a risk alarm is sent to the real-time risk vehicle using the real-time V2X communication link.

[0077] Furthermore, the system is also used to implement the following functions:

[0078] A preset alarm execution window is established; after the delay in sending a risk alarm to the real-time risk vehicle meets the alarm execution window, the roadside edge computing device receives the updated traffic data transmitted back from the roadside sensor network coverage; the roadside edge computing device uses the traffic-related risk characteristics to determine the existence of associated risks in the updated traffic data.

[0079] Furthermore, the system is also used to implement the following functions:

[0080] K real-time vehicle positions are retrieved from the K real-time vehicle status information; the K real-time vehicle positions are verified using the real-time traffic data to perform offset compensation, resulting in K compensated vehicle positions; based on the K compensated vehicle positions, K sets of detection status data are retrieved from the real-time traffic data, wherein the detection status data includes vehicle real-time speed and vehicle heading angle; the K sets of detection status data are mapped, weighted, and fused into the K real-time vehicle status information; the K compensated vehicle positions are used to map and cover the K real-time vehicle status information, and the K compensated vehicle status information is output.

[0081] Furthermore, the system is also used to implement the following functions:

[0082] The K compensated vehicle state information is associated with the lane topology to obtain globally bound vehicle state information; multi-target trajectory tracking is performed on the K driving vehicles based on the globally bound vehicle state information to output K real-time trajectory sequences; the K real-time trajectory sequences are fitted to the spatial model of the target intersection to obtain the global dynamic traffic model.

[0083] Furthermore, the system is also used to implement the following functions:

[0084] Based on the predefined conflict area distribution of the lane connection topology of the target intersection, the CTRA model is used to predict the trajectory along the K real-time trajectory sequences to obtain K predicted temporal trajectories. After spatiotemporally overlapping the K predicted temporal trajectories, multiple conflict trajectories falling into the conflict area distribution are extracted. Based on the mapping relationship between the multiple conflict trajectories and the K predicted temporal trajectories, multiple driving vehicles are located. After calling the multiple vehicle IDs of the multiple driving vehicles, the multiple vehicle IDs are packaged as the potential collision risk output.

[0085] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0086] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0087] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A vehicle status perception method in a vehicle-road cooperative environment, characterized in that, The method includes: Roadside sensor networks collect real-time traffic data at target intersections using millimeter-wave radar; Based on geofencing, the on-board unit (OBU) of a vehicle entering the target intersection establishes a temporary V2X communication link with the roadside edge computing device. The roadside edge computing device receives the real-time traffic data and K real-time vehicle status information of K vehicles, where K≥2 and K is a positive integer; If the roadside edge computing device sets the single-dimensional risk detection results of the real-time traffic data and the K real-time vehicle status information to 0, then the real-time traffic data is used to compensate the K real-time vehicle status information to obtain K compensated vehicle status information. A global dynamic traffic model is constructed based on the K compensated vehicle status information. Based on the global dynamic traffic model, trajectory conflict prediction is performed to locate potential collision risks; Based on risk avoidance priorities, the potential collision risks are broadcast to the K vehicles via a V2X communication link.

2. The vehicle status perception method in a vehicle-road cooperative environment as described in claim 1, characterized in that, The method further includes: Based on the road condition information of the target intersection, traffic-related risk features are matched and invoked; The roadside edge computing device uses the traffic-related risk features to traverse the real-time traffic data and outputs the first risk detection result. Based on the location information of the target intersection, the system retrieves speeding characteristics via network connection. The roadside edge computing device uses the driving speeding features to traverse the K real-time vehicle status information and outputs a second risk detection result; If both the first risk detection result and the second risk detection result are set to 0, then the real-time traffic data is used to compensate the K real-time vehicle status information to obtain K compensated vehicle status information.

3. The vehicle status perception method in a vehicle-road cooperative environment as described in claim 2, characterized in that, The method further includes: The traffic-related risk characteristics include vehicle safety distance constraints and vehicle driving direction constraints; The real-time traffic data is traversed using the vehicle safety distance constraint and the vehicle driving direction constraint to locate real-time risk vehicles, which are used as the first risk detection result. If the first risk detection result is set to 1, then the real-time V2X communication link of the real-time risk vehicle is invoked based on the K real-time vehicle status information. The real-time V2X communication link is used to send risk warnings to the real-time risk vehicle.

4. The vehicle status perception method in a vehicle-road cooperative environment as described in claim 3, characterized in that, The method then includes sending a risk alarm to the real-time risk vehicle using the real-time V2X communication link, followed by: Preset alarm execution window; After the delay in sending a risk alarm to the real-time risk vehicle meets the alarm execution window, the roadside edge computing device receives the updated traffic data transmitted back from the roadside sensor network. The roadside edge computing device uses the traffic-related risk characteristics to determine the continuation of associated risks in the updated traffic data.

5. The vehicle status perception method in a vehicle-road cooperative environment as described in claim 2, characterized in that, The method involves using the real-time traffic data to compensate for the K real-time vehicle status information to obtain K compensated vehicle status information, the method comprising: From the K real-time vehicle status information, retrieve the K real-time vehicle locations; The real-time traffic data is used to verify the K real-time vehicle positions for offset compensation, resulting in K compensated vehicle positions. Based on the K compensated vehicle positions, K sets of detection status data are retrieved from the real-time traffic data, wherein the detection status data includes the vehicle's real-time speed and vehicle heading angle; The K sets of detection status data are mapped and weighted and fused into the K real-time vehicle status information, and the K compensated vehicle position mappings are used to cover the K real-time vehicle status information, and the K compensated vehicle status information is output.

6. The vehicle status perception method in a vehicle-road cooperative environment as described in claim 1, characterized in that, The method for constructing a global dynamic traffic model based on the K compensated vehicle status information includes: The K compensated vehicle status information are associated with the lane topology to obtain globally bound vehicle status information; Based on the globally bound vehicle status information, multi-target trajectory tracking is performed on the K driving vehicles, and K real-time trajectory sequences are output; The K real-time trajectory sequences are fitted to the spatial model of the target intersection to obtain the global dynamic traffic model.

7. The vehicle status perception method in a vehicle-road cooperative environment as described in claim 6, characterized in that, Based on the global dynamic traffic model, trajectory conflict prediction is performed to locate potential collision risks. The method includes: The distribution of conflict zones is predefined based on the lane connection topology of the target intersection; The CTRA model is used to predict the trajectory along the K real-time trajectory sequences to obtain K predicted time-series trajectories. After spatiotemporally overlapping the K predicted temporal trajectories, multiple conflict trajectories falling into the conflict region distribution are extracted; Based on the mapping relationship between the multiple conflict trajectories and the K predicted time-series trajectories, multiple vehicles are located; After calling the multiple vehicle IDs of the multiple driving vehicles, the multiple vehicle IDs are packaged as the potential collision risk output.

8. A vehicle status perception system in a vehicle-road cooperative environment, characterized in that, The system is used to execute the vehicle status perception method in a vehicle-road cooperative environment as described in any one of claims 1-7, and the system includes: The traffic data acquisition module is used by the roadside sensor network to collect real-time traffic data of the target intersection via millimeter-wave radar. The communication link establishment module is used to trigger the on-board OBU of the vehicle entering the target intersection to establish a temporary V2X communication link with the roadside edge computing device based on the geofence. The information receiving module is used by the roadside edge computing device to receive the real-time traffic data and K real-time vehicle status information of K vehicles, where K≥2 and K is a positive integer; The compensation module is used to compensate the K real-time vehicle status information with the real-time traffic data if the roadside edge computing device sets the single-dimensional risk detection results of the real-time traffic data and K real-time vehicle status information to 0, so as to obtain K compensated vehicle status information. The traffic model construction module is used to construct a global dynamic traffic model based on the K compensated vehicle status information. The trajectory conflict prediction module is used to predict trajectory conflicts based on the global dynamic traffic model and locate potential collision risks. The broadcast module is used to broadcast the potential collision risks to the K vehicles via a V2X communication link according to the risk avoidance priority.

Images