Signal lamp information acquisition method and system of networked automobile
By sending authentication requests to the platform in a connected vehicle and integrating the signal light information obtained by the vehicle-side perception device, the problems of difficulty in obtaining signal light information and high demand for cloud platform computing power in the prior art are solved, and high accuracy and stability of signal light information acquisition is achieved.
Patent Information
- Application Number
- CN202510658941.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-21
- Publication Date
- 2025-06-20
AI Technical Summary
The existing technology has difficulties in obtaining accurate signal light information, especially in special scenarios or large-scale connected vehicle access scenarios, cloud control platforms have high computing power demand and poor data stability.
The signal light information is obtained by sending a authentication request to the platform, and fusing it with the signal light information obtained by the vehicle-side sensing device to determine the fused signal light information. This solution integrates signal light information from the cloud and vehicle ends, reducing the computing power demand of the cloud platform and improving the accuracy of signal light information.
In the scenario of large-scale connected vehicle access, the computing power demand of cloud platform is reduced, the accuracy and stability of signal light information is improved, and the needs of high concurrency and low latency are met.
Smart Images

Figure CN120183230A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of vehicle-road cooperation, and particularly to a method and a system for obtaining signal lamp information of a connected vehicle. Background Art
[0002] Currently, when intelligent connected vehicles obtain the states of signal lamps, generally three methods are adopted: The first is to obtain the states of signal lamps through in-vehicle sensors and fusion perception algorithms. For example, connected vehicles rely on sensors equipped on their own, such as cameras and lidar, and combine fusion perception algorithms to detect and identify traffic lights. However, in some special scenarios, it is difficult to achieve the expected functions only through vehicle-end perception. For example, when a connected vehicle passes through a continuous traffic light-controlled intersection at a very close distance, it may be difficult to detect due to complex scenarios; in environments with low visibility, such as foggy and rainy days, the sensing ability of sensors is limited; strong light (such as direct sunlight) obstructs the vision and interferes with the sensors' recognition of signal lamps; when the in-vehicle sensors are blocked, covered, damaged or uncalibrated, the states of signal lamps cannot be accurately obtained either.
[0003] The second is to obtain the states of signal lamps from the roadside. For example, a roadside unit (RSU) first obtains the signal lamp state information from the roadside signal lamp control system through a signal lamp transmission and acquisition device, and then sends it to the on-vehicle unit by means of DSRC / LTE-V. However, this solution requires both connected vehicles and the roadside to be equipped with dedicated communication devices. Since it involves the transformation of a large number of connected vehicles and roadside facilities, it is difficult to popularize.
[0004] The third is to obtain the states of signal lamps from a cloud control platform. The vehicle-road-cloud fusion perception and information service work are concentrated in the cloud, which makes the cloud control platform face huge computing power requirements. On the other hand, the traffic light information data pushed to connected vehicles lacks pertinence, and the association with the driving behaviors of connected vehicles is not close enough, and the stability is poor.
[0005] Therefore, how to enable connected vehicles to obtain accurate signal lamp information while effectively reducing the computing power requirements of the cloud control platform so that it can better meet the scenarios of large-scale access of connected vehicles is an urgent problem to be solved currently. Summary of the Invention
[0006] In view of this, in order to overcome at least one of the above problems, an embodiment of the present invention provides a method for obtaining signal lamp information of a connected vehicle, including the following steps: Send a first authentication request to the platform; In response to successful authentication, receive the first signal lamp information returned by the platform; Obtain second signal lamp information through the sensing devices of the connected vehicle; Determine the fused signal light information based on the first signal light information and the second signal light information.
[0007] In some embodiments, sending a first authentication request to the platform further includes: sending a first authentication request to the enterprise-level platform; In response to successful authentication, receiving the first signal light information returned by the platform further includes: In response to successful authentication, receiving the address of the city-level platform returned by the enterprise-level platform; Send the connected vehicle status information to the city-level platform based on the address; Receive the first signal light information returned by the city-level platform based on the connected vehicle status information.
[0008] In some embodiments, before sending a first authentication request to the enterprise-level platform, the following steps are further included in the enterprise-level platform: Receive the signal light service subscription request sent by the connected vehicle; Verify the request; In response to successful verification, store the subscription information carried in the request and update the subscription list; Synchronously update the subscription list and the corresponding subscription information to the city-level platform.
[0009] In some embodiments, before sending the connected vehicle status information to the city-level platform based on the address, the following steps are further included in the city-level platform: Receive the second authentication request sent by the connected vehicle; Verify the second authentication request based on the subscription list and the subscription information; In response to successful verification, return verification success to the connected vehicle.
[0010] In some embodiments, before receiving the first signal light information returned by the city-level platform based on the connected vehicle status information, the following steps are further included in the city-level platform: Receive the connected vehicle status information sent by the connected vehicle; Obtain and send the first signal light information to the connected vehicle based on the connected vehicle status information.
[0011] In some embodiments, obtaining the first signal light information based on the connected vehicle status information further includes: Determine the connected vehicle position information and the driving direction based on the connected vehicle status information; Use the connected vehicle position information and the driving direction to determine the signal light data set in front of the connected vehicle; Determine the first signal light information based on the connected vehicle position information and the position information in the signal light dataset.
[0012] In some embodiments, determining the first signal light information based on the connected vehicle position information and the position information in the signal light dataset further includes: Determine the first signal light that the connected vehicle is about to pass based on the distance between each signal light position information in the signal light dataset and the connected vehicle; Determine the corresponding approach lane based on the distance between the center point of each lane section of the intersection corresponding to the first signal light and the connected vehicle; Determine the first signal light information based on the approach lane and the driving direction of the connected vehicle.
[0013] In some embodiments, determining the fused signal light information based on the first signal light information and the second signal light information further includes: Determine the fused signal light information based on the status of the light state information and the remaining time information in the second signal light information and the first signal light information.
[0014] In some embodiments, determining the fused signal light information based on the status of the light state information and the remaining time information in the second signal light information and the first signal light information further includes: In response to both the light state information and the remaining time information in the second signal light information being missing, use the first signal light information as the fused signal light information; In response to the light state information in the second signal light information not being missing, determine a first weight based on the distance between the connected vehicle and the stop line of the lane at the intersection, and determine a second weight based on the current environment; Use the first weight, the second weight, the probability of each light state in the first signal light information, and the probability of each light state information in the second signal light information to determine the probability of each light state; Use the light state information with the highest probability as the light state information in the fused signal light information; In response to the remaining time information in the second signal light information not being missing, determine the remaining time information in the fused signal light information based on the first weight, the second weight, the remaining time in the first signal light information, and the remaining time information in the second signal light information; In response to the remaining time in the second signal light information being missing, predict the remaining time based on the historical data of the connected vehicle, and determine the remaining time information in the fused signal light information based on the first weight, the second weight, the remaining time information in the first signal light information, and the predicted remaining time.
[0015] Based on the same inventive concept, according to another aspect of the present invention, an embodiment of the present invention further provides a signal light information acquisition system for a connected vehicle, including: Connected vehicles; An enterprise-level platform for receiving a first authentication request sent by a connected vehicle; A city-level platform for sending first signal light information to the connected vehicle after the first authentication request of the connected vehicle passes; The connected vehicle is further configured to obtain second signal light information based on a vehicle-mounted sensing device, and obtain fused signal light information based on the first signal light information and the second signal light information.
[0016] One of the beneficial technical effects of the present invention is as follows: The solution proposed by the present invention authenticates connected vehicles through a platform, and only when the authentication passes will the platform address be returned, avoiding a large number of unnecessary authentication request processes on the platform and reducing the computing power requirements of the platform; The present invention fuses the signal light information obtained from the cloud and the signal light information sensed by the vehicle end, making the signal light information obtained by the connected vehicle more accurate. The method for acquiring signal lights of a connected vehicle proposed by the present invention not only effectively reduces latency, but also distributes the data fusion computing power to the connected vehicle, enabling the cloud platform to serve more connected vehicles under the same computing power, enabling it to better meet the scenario of large-scale connected vehicle access, thereby improving concurrency and stability. Description of the Drawings
[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other embodiments can be obtained based on these drawings without creative efforts.
[0018] Figure 1 It is a schematic flow chart of a method for acquiring signal light information of a connected vehicle provided by an embodiment of the present invention; Figure 2 It is a flow block diagram of a method for acquiring signal light information of a connected vehicle provided by an embodiment of the present invention; Figure 3 It is a schematic diagram of the approach lane at the front intersection of a connected vehicle provided by an embodiment of the present invention. Detailed Embodiments
[0019] To make the purpose, technical solutions, and advantages of the present invention clearer, the following will further describe the embodiments of the present invention in detail with reference to specific embodiments and the accompanying drawings.
[0020] It should be noted that all the expressions using "first" and "second" in the embodiments of the present invention are for distinguishing two entities or parameters with the same name but different identities. It can be seen that "first" and "second" are only for the convenience of expression and should not be construed as a limitation on the embodiments of the present invention. This will not be elaborated one by one in the subsequent embodiments.
[0021] According to one aspect of the present invention, an embodiment of the present invention provides a method for obtaining signal light information of a connected vehicle, as Figure 1 shown, which may include the steps: S1, sending a first authentication request to the platform; S2, in response to successful authentication, receiving the first signal light information returned by the platform; S3, obtaining second signal light information through the sensing device of the connected vehicle; S4, determining the fused signal light information based on the first signal light information and the second signal light information.
[0022] The solution proposed by the present invention authenticates the connected vehicle through the platform. Only after successful authentication will the platform address be returned, avoiding a large number of unnecessary authentication request processes on the platform and reducing the computing power requirements of the platform; the present invention fuses the signal light information obtained from the cloud and the signal light information sensed by the vehicle end, making the signal light information obtained by the connected vehicle more accurate.
[0023] In some embodiments, sending a first authentication request to the platform further includes: sending a first authentication request to the enterprise-level platform; In response to successful authentication, receiving the first signal light information returned by the platform further includes: In response to successful authentication, receiving the address of the city-level platform returned by the enterprise-level platform; Sending the connected vehicle status information to the city-level platform based on the address; Receiving the first signal light information returned by the city-level platform based on the connected vehicle status information.
[0024] Specifically, the platform can be divided into an enterprise-level platform and a city-level platform. The enterprise-level platform authenticates the first authentication request sent by the connected vehicle. If the authentication is successful, the address of the city-level platform is returned, and the connected vehicle then sends the connected vehicle status information to the city-level platform, enabling the city-level platform to generate the first signal light information based on the connected vehicle status information.
[0025] In some embodiments, the method for obtaining signal light information of a connected vehicle may further include the following steps: S1, sending a first authentication request to the enterprise-level platform and receiving the address of the city-level platform returned by the enterprise-level platform; S2. Send the connected vehicle status information to the city-level platform based on the address. S3. Receive the first signal light information returned by the city-level platform based on the connected vehicle status information. S4. Obtain the fused signal light information using the second signal light information obtained by vehicle-side perception and the first signal light information.
[0026] In this way, the connected vehicle is authenticated through the enterprise-level platform. Only when the authentication is passed will the address of the city-level platform be returned. By verifying the identity of the connected vehicle, it is ensured that only authorized connected vehicles can access the city-level platform, preventing unsubscribed connected vehicles or malicious devices from illegally obtaining sensitive traffic data. Moreover, the city-level platform only pushes the real-time signal light information of the area where the connected vehicle is located to the authenticated connected vehicle, avoiding the redundant communication load caused by full-volume data broadcasting and reducing the computing power requirement of the city-level platform. The first signal light information is generated and pushed based on the status information of the connected vehicle in the city-level platform, and then vehicle-cloud data fusion is performed at the vehicle end, making it more convenient for the connected vehicle to obtain the signal light information, reducing the latency. At the same time, the data fusion requirement is shared to the connected vehicle, further reducing the computing power requirement of the city-level platform, enabling the city-level platform to serve more connected vehicles under the same computing power and better meeting the scenario of large-scale connected vehicle access, thereby improving concurrency and stability.
[0027] In some embodiments, before sending the first authentication request to the enterprise-level platform, the following steps are further included in the enterprise-level platform: Receive the signal light service subscription request sent by the connected vehicle; Verify the request; In response to passing the verification, store the subscription information and update the subscription list; Synchronously update the subscription list and the corresponding subscription information to the city-level platform.
[0028] Specifically, as Figure 2 shown, an automotive enterprise signal light data service management system is deployed in the enterprise-level platform (automobile enterprise TSP platform). This system may include a connected vehicle subscription management module, a connected vehicle service authentication module, and a cross-platform mutual recognition module. Among them, the connected vehicle subscription management module can implement functions such as subscription information management, connected vehicle permission allocation, service status monitoring, and billing rule execution. The connected vehicle service authentication module can implement functions such as connected vehicle registration, authentication and authorization, and target address distribution. The cross-platform mutual recognition module can implement functions such as two-way identity verification, cross-platform trust list update, access control, and data encryption.
[0029] Connected vehicles need to subscribe and register for the signal light push service with the enterprise-level platform in advance, that is, the connected vehicle sends a registration request to the vehicle enterprise signal light data service management system. The registration request can carry parameters such as the basic information of the connected vehicle, the personal information of the vehicle owner, and the service subscription information. Relevant modules in the vehicle enterprise signal light data service management system verify the parameters. If the verification passes, a registration success confirmation message is returned to the connected vehicle. At the same time, relevant modules within the vehicle enterprise signal light data service management system store the subscription information and dynamically update the service subscription list of the connected vehicle according to the subscription situation of the connected vehicle.
[0030] As Figure 2 shown, a city-level signal light data service system is deployed in the city-level platform (city-level vehicle-road-cloud integration platform). This system can include a signal light information service push module, a vehicle enterprise subscription management module, and a cross-platform mutual recognition module. Among them, the signal light information service push module can implement functions such as connected vehicle authentication and authorization, connected vehicle location parsing, road network relationship matching, and targeted service information distribution; the vehicle enterprise subscription management module can implement functions such as subscription information management, connected vehicle permission allocation, service status monitoring, and billing rule execution; the cross-platform mutual recognition module can implement functions such as two-way identity verification, cross-platform trust list update, access control, and data encryption.
[0031] Vehicle enterprises can register enterprise accounts in the city-level signal light data service system in advance and submit city-level signal light service applications. Relevant modules in the city-level signal light data service system can review the vehicle enterprise service registration requirements submitted by vehicle enterprises to ensure that the specific requirements for the signal light push service proposed by vehicle enterprises are within the service capabilities of the city-level signal light data service system, and send a registration success notice to the vehicle enterprises that pass the review.
[0032] When a new connected vehicle subscribes to the signal light push service through the vehicle enterprise signal light data service management system of the enterprise-level platform, the vehicle enterprise signal light data service management system can perform a security authentication to the city-level signal light data service system in the city-level platform and initiate a request for authorization to synchronize the service subscription list information of the connected vehicle, so as to synchronize the subscription list and the corresponding subscription information in the enterprise-level platform to the city-level platform. When the city-level platform receives the synchronization request message from the enterprise-level platform, it stores and updates the received service subscription list of the connected vehicle and sends a successful synchronization confirmation message to the enterprise-level platform.
[0033] In some embodiments, the following steps are further included in the enterprise-level platform: Verify the request content carried in the first authentication request using the subscription information in the enterprise-level platform; In response to passing the verification, return the address of the city-level platform to the connected vehicle.
[0034] Specifically, when a connected vehicle needs signal lamp information from the cloud, it can first initiate an authentication request to the enterprise-level platform, that is, initiate a connected vehicle authentication request to the vehicle manufacturer's signal lamp data service management system. The request content may include the vehicle manufacturer to which the connected vehicle belongs, the basic information of the connected vehicle, the personal information of the vehicle owner, and the service demand information. Then, the vehicle manufacturer's signal lamp data service management system can verify the connected vehicle that initiates the authentication by comparing the connected vehicle service subscription list and the stored corresponding subscription information. If the verification is passed, the address of the city-level platform is returned to the connected vehicle.
[0035] It should be noted that the obtained address of the city-level platform can be deleted each time the connected vehicle reaches its destination, or after a preset period. When the signal lamp push service is needed next time, the connected vehicle can re-authenticate to the enterprise-level platform to obtain the address of the city-level platform for the first signal lamp information acquisition. This is not only beneficial to the security of the city-level platform address, but also for the city-level platform and the enterprise-level platform. Each time the connected vehicle re-authenticates to obtain the address, it can better manage and monitor the connected vehicle. Specifically, through time-limited identity verification, each authentication makes the connected vehicle submit the latest status information, preventing invalid devices from occupying resources for a long time. And periodically re-obtaining the address of the city-level platform can block potential attack chains and avoid malicious nodes lurking for a long time. At the same time, the enterprise-level platform generates a new anonymous identifier for the connected vehicle during each authentication to prevent long-term tracking of user trajectories.
[0036] For connected vehicles, periodic address deletion can streamline storage. The address of a single city-level platform may occupy several hundred bytes to several KB of storage space. The deletion operation can release the in-vehicle computer memory and improve the operation efficiency of other functions (such as autonomous driving algorithms). Moreover, if the city-level platform upgrades the interface, the old address may cause compatibility problems. By forcing re-authentication, it can ensure that the connected vehicle always obtains the latest protocol version.
[0037] In some embodiments, before sending the connected vehicle status information to the city-level platform based on the address, the following steps are further included in the city-level platform: Receiving a second authentication request sent by the connected vehicle; Verifying the second authentication request based on the subscription list and subscription information; In response to successful verification, returning verification success to the connected vehicle.
[0038] Specifically, when the connected vehicle passes the authentication and verification of the enterprise-level platform, it sends a second authentication request to the city-level platform based on the address of the city-level platform returned by the enterprise-level platform. Relevant modules of the city-level signal light data service system in the city-level platform can compare the connected vehicle service subscription list and verify the request information of the connected vehicle initiating the authentication. The verification content can include whether the vehicle enterprise to which the connected vehicle belongs has registered the service, whether the connected vehicle has subscribed to the service, and whether the service is within the validity period. If the verification passes, it returns verification success. In this way, the city-level platform does not need to directly connect to a large number of terminal connected vehicles, but aggregates requirements through enterprise-level platforms such as vehicle enterprises and mapping providers, simplifying the interface protocol compatibility challenge.
[0039] After receiving the verification success returned by the city-level platform, the connected vehicle can preset a frequency, for example, at a frequency of 10 Hz, to upload the connected vehicle status information to the city-level platform. The status information can include the connected vehicle coordinates (accuracy, latitude), heading angle, and driving direction (going straight, turning left, turning right, changing lanes to the left, changing lanes to the right).
[0040] In some embodiments, before receiving the first signal light information returned by the city-level platform based on the connected vehicle status information, the following steps are further included in the city-level platform: Receiving the connected vehicle status information sent by the connected vehicle; Obtaining and sending the first signal light information to the connected vehicle based on the connected vehicle status information.
[0041] Specifically, after the city-level platform returns the information of successful verification to the connected vehicle, the connected vehicle sends the connected vehicle status information to the city-level platform. After receiving the connected vehicle status information, the city-level platform can obtain the first signal light information that needs to be sent to the connected vehicle based on the connected vehicle status information.
[0042] In some embodiments, obtaining the first signal light information based on the connected vehicle status information further includes: Determining the connected vehicle position information and driving direction based on the connected vehicle status information; Using the connected vehicle position information and the driving direction to determine the signal light data set in front of the connected vehicle; Determining the first signal light information according to the connected vehicle position information and the position information in the signal light data set.
[0043] Specifically, such as Figure 2As shown in the figure, the traffic signal unified control platform aggregates the signal lamp data of all signal-controlled intersections in the city. The city-level signal lamp data service system can directly obtain the city-level signal lamp data of the entire city range from the traffic signal unified control platform in the format of GA / T 1049.2-2013 through the public security video private network. The signal lamp data can include the area number, signal lamp number, signal lamp position, signal lamp cycle, signal lamp phase, and phase lamp state of each signal-controlled intersection. Then, in the city-level signal lamp data service system, according to the area division, the lamp state and phase information of the signal lamps with the same area number can be respectively stored in the signal lamp data set corresponding to the area number.
[0044] When the city-level platform receives the connected vehicle status information (connected vehicle coordinates, heading angle, driving direction), it can determine the area to which the connected vehicle belongs according to the coordinates in the WGS84 geodetic coordinate system corresponding to the connected vehicle's coordinates. Since each area has a corresponding number, and different area numbers correspond to different signal lamp data sets. The signal lamp data set contains the relevant information of all signal lamps in the area, such as the position of the signal lamp, the signal lamp cycle, the signal lamp phase, and the phase lamp state of the signal lamp. After determining the area number to which the connected vehicle belongs, the corresponding signal lamp data set can be found.
[0045] Since the signal lamp data set corresponding to the area number includes all the signal lamp data of the current area, it is necessary to screen out the subset of signal lamp data in front of the connected vehicle. According to the coordinates and driving direction of the connected vehicle in the WGS84 geodetic coordinate system, combined with the position of the signal lamp in the signal lamp data set, the signal lamp in front of the connected vehicle can be determined, so as to determine the subset of signal lamp data in front of the connected vehicle.
[0046] For example, if the driving direction of the connected vehicle is 90°, and the coordinates of the connected vehicle are (0, 0), if the signal lamp coordinates are (0, 5), then the signal lamp is in front of the connected vehicle; if the signal lamp coordinates are (0, -5), then the signal lamp is behind the connected vehicle.
[0047] In some embodiments, determining the first signal lamp information according to the position of the connected vehicle in the connected vehicle status information and the position of the signal lamp in the signal lamp data subset further includes: Determining the first signal lamp that the connected vehicle is about to pass according to the distance between each signal lamp position in the signal lamp data set and the connected vehicle; Determining the corresponding approach lane according to the distance between the center point of each lane of the intersection corresponding to the first signal lamp and the connected vehicle; Determining the first signal lamp information according to the approach lane and the driving direction of the connected vehicle.
[0048] Specifically, as Figure 3 shown, after determining the signal light data subset, which includes all the signal light data in front of the connected vehicle, it is necessary to further filter out the signal light data of the intersection that the connected vehicle is about to pass through. At this time, the distance between each signal light position in the data subset and the connected vehicle can be traversed and calculated, and the signal light with the smallest distance value is the signal light that the connected vehicle is about to pass through. Thus, the first signal light information is obtained, which may include the area to which the signal light belongs, the signal light number, the signal light position, the current timestamp, the target signal light state (red, green, yellow), and the remaining time.
[0049] For example, if the coordinates of the connected vehicle are (0, 0), and there are signal lights A (0, 5) and B (0, 9) in front of the connected vehicle, since the distance between signal light A and the connected vehicle is closer, signal light A is used as the signal light at the intersection that the connected vehicle is about to pass through.
[0050] After determining the signal light that the vehicle is about to pass through, calculate the distance between the center point of each lane of the intersection corresponding to the signal light and the connected vehicle. The lane corresponding to the center point of the road section with the smallest distance value is the entrance lane of the intersection in front of the connected vehicle.
[0051] For example, if the coordinates of the connected vehicle are (0, 0), and there are three entrance lanes at the current intersection (the center coordinates of each entrance lane are recorded in the signal light position data in the signal light data), calculate the distance between the coordinates of the connected vehicle and the coordinates of each entrance lane in turn, and the one with the smallest distance is used as the entrance lane of the connected vehicle.
[0052] After determining the entrance lane of the connected vehicle, the first signal light information can be determined according to the entrance lane of the intersection in front of the connected vehicle and the driving direction of the connected vehicle. For example, if the connected vehicle is located in the second entrance lane (this entrance lane is for straight driving), and the driving direction of the connected vehicle is also straight, then the first signal light information can be filtered out from the signal light data corresponding to straight driving. The first signal light information may include the area to which the signal light belongs, the signal light position, the current timestamp, the target signal light state (red, green, yellow), and the remaining time.
[0053] In some embodiments, such as Figure 2As shown, a vehicle - end multi - source traffic light data fusion processing system can be deployed in connected vehicles (L2+ intelligent connected vehicles), which can include modules such as data access, data matching, and data compensation. Among them, the data access module can receive the traffic light information pushed by the city - level signal light data service system; the data matching module can be used to perform matching analysis on the traffic light information perceived by the vehicle end and the traffic light information pushed by the city - level signal light data service system; the data compensation module is used to compensate the traffic light information perceived by the vehicle end based on the traffic light information pushed by the city - level signal light data service system. For example, if there is a lack of traffic light information perceived by the vehicle end (such as lack of light color or countdown), the traffic light information pushed by the city - level signal light data service system is used for data compensation to ensure the integrity and accuracy of the traffic light information.
[0054] When the city - level platform filters out the targeted first traffic light information, it can send the targeted first traffic light service information to the connected vehicle at a preset frequency, for example, at a frequency of 10Hz. After receiving the targeted first traffic light information sent by the city - level platform, the connected vehicle can first match according to the position information in the targeted first traffic light information, such as the area where the traffic light belongs, the traffic light number, and the traffic light position, combined with the traffic light position information perceived by the vehicle end. If the match is successful, subsequent compensation and fusion are carried out. Through position matching, it can be determined whether the cloud - targeted first traffic light information fed back by the city - level platform is accurate, thereby further improving the accuracy of data fusion.
[0055] It should be noted that the traffic light information perceived by the vehicle end can be obtained by fusing the external information sensed by the vehicle - end sensors, such as image sensors and various radar sensors.
[0056] In some embodiments, determining the fusion traffic light information based on the first traffic light information and the second traffic light information further includes: Determining the fusion traffic light information based on the state of the light state information and the state of the remaining time information in the second traffic light information and the first traffic light information.
[0057] In some embodiments, obtaining the fusion traffic light information by using the second traffic light information perceived by the vehicle end and the first traffic light information further includes: In response to the lack of both the light state and the remaining time in the second traffic light information, using the first traffic light information as the fusion traffic light information.
[0058] Specifically, when the first signal light information is received, position matching can be performed to extract the current timestamp, the target signal light state, and the remaining time information in the first signal light information. Meanwhile, the vehicle terminal also outputs the second signal light information obtained by fusing vehicle-terminal perception at a frequency of 10 Hz. The second signal light information also includes the current timestamp, the target traffic light state, and the remaining time information. In this way, when the frequencies are the same, the signal light information obtained by fusing vehicle-terminal perception can be matched one by one with the data in the targeted signal light information according to the current timestamp. The vehicle-terminal perceived signal light data is , and the cloud signal light data is Among them: Current timestamp; Target signal light state, s ; Remaining time of the current light state (continuous variable, unit: second).
[0059] When both the light state and the remaining time are missing in the second signal light information obtained by vehicle-terminal perception, the signal light information pushed by the cloud can be used as vehicle-terminal data compensation, that is, the fused signal light information .
[0060] In some embodiments, obtaining the fused signal light information by using the second signal light information obtained by vehicle-terminal perception and the first signal light information further includes: In response to the light state in the second signal light information not being missing, determining a first weight based on the distance between the connected vehicle and the lane stop line of the intersection, and determining a second weight based on the current environment; Using the first weight, the second weight, the probability of each light state in the first signal light information, and the probability of each light state in the second signal light information to determine the probability of each light state; Taking the light state with the highest probability as the light state in the fused signal light information.
[0061] Specifically, if the light state in the second signal light information is not missing, both the first signal light and the second signal light include the probability of each light state, which can be expressed as , where i is either "cloud" or "car", and the three P values respectively represent the probabilities of outputting red, yellow, and green light states. Since the first signal light information is obtained from the city-level platform, the probability of only one light state is 1, and the probabilities of the other two light states are 0. The second signal light information is obtained through vehicle-end recognition and perception, and there may be recognition errors. For example, in a scenario where the yellow light is blocked, the probability that the vehicle-end can recognize the yellow light as the yellow light is 0.65, the probability of recognizing the yellow light as the red light is 0.2, and the probability of recognizing the yellow light as the green light is 0.15, that is, Z car = [0.20, 0.65, 0.15].
[0062] Considering the influence of the distance between the connected vehicle and the stop line at the intersection on the confidence of the cloud signal light, the first weight of the first signal light can be set as:
[0063]
[0064] Considering the influence of the environmental attenuation factor, the second weight corresponding to the second signal light information can be set as:
[0065] In this way, finally, the first weight and the second weight are used to fuse the first signal light information and the second signal light information respectively to obtain the probability of each light state, that is:
[0066]
[0067] Obtain Z fused After that, the light state with the highest probability is used as the light state in the fused signal light information. For example, if , then the green light is used as the light state in the fused signal light information.
[0068] In some embodiments, it further includes: In response to the remaining time in the second signal light information not being missing, the remaining time in the fused signal light information is determined using the first weight, the second weight, the remaining time in the first signal light information, and the remaining time in the second signal light information.
[0069] Specifically, if the remaining time in the second signal light information is not missing, similarly, the first weight and the second weight are used to fuse the first signal light information and the second signal light information respectively to obtain the remaining time in the fused signal light information, that is:
[0070] In some embodiments, it further includes: In response to the absence of the remaining time in the second signal light information, predict the remaining time based on the historical data of the connected vehicle, and determine the remaining time in the fused signal light information by using the first weight, the second weight, the remaining time in the first signal light information, and the remaining time predicted based on the historical data of the connected vehicle.
[0071] Specifically, if the remaining time in the second signal light information is missing, the remaining time can be predicted by combining the historical data of the connected vehicle, and the remaining time in the fused signal light information is obtained by fusing the first signal light information and the second signal light information based on the first weight and the second weight respectively, that is:
[0072] where is the remaining time predicted based on the historical data of the connected vehicle, is the mean historical error (the error can be obtained from the predicted time and the actual time), is the time series correction coefficient.
[0073] The solution proposed in this application can provide urban-level traffic light data service capabilities that meet the requirements of high stability, low latency, and high concurrency, that is: The urban-level signal light data service system directly obtains the urban-level traffic light state and phase information from the traffic signal unified management and control platform through the cloud-to-cloud docking method, which has lower latency and higher stability compared with the method of reading the signal machine phase information from the roadside and then summarizing it to the platform side.
[0074] The registration process of the urban-level traffic light push service is completed in advance by the vehicle enterprise. The urban-level platform obtains the white list of connected vehicles of each enterprise through data synchronization between platforms. Only the connected vehicles within the white list range can obtain the urban-level platform address from the vehicle enterprise side and upload service requests and connected vehicle status data. This authorization-based service acquisition method reduces the concurrency and storage requirements for the urban-level cloud control platform.
[0075] According to the connected vehicle coordinates, heading angle, and driving intention information reported by the connected vehicle, the traffic light logic matching for the driving direction of the connected vehicle at the entrance lane of the intersection in front of the connected vehicle is completed on the urban-level platform side, and the targeted traffic light service information is generated and sent down through the network. Compared with the method of providing intersection-level service information to the connected vehicle on the platform side and having the connected vehicle perform effective traffic light fusion, the accuracy of the traffic light information service is improved.
[0076] Based on the same inventive concept, according to another aspect of the present invention, an embodiment of the present invention further provides a signal light information acquisition system for a connected vehicle, including: Connected vehicle; Enterprise-level platform, configured to receive the first authentication request sent by the connected vehicle; A city-level platform for sending first signal light information to the connected vehicle after the first authentication request of the connected vehicle is passed; The connected vehicle is further configured to obtain second signal light information based on a sensing device on the vehicle end, and obtain fused signal light information based on the first signal light information and the second signal light information.
[0077] Finally, it should be noted that those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods.
[0078] In addition, it should be understood that the computer-readable storage medium (e.g., memory) herein can be a volatile memory or a non-volatile memory, or can include both a volatile memory and a non-volatile memory.
[0079] Those skilled in the art will also understand that the various exemplary logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein can be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability of hardware and software, a general description has been given of the functions of the various illustrative components, blocks, modules, circuits, and steps. Whether this function is implemented as software or hardware depends on the specific application and the design constraints imposed on the overall system. The functions that those skilled in the art can implement in various ways for each specific application, but this implementation decision should not be construed as causing a departure from the scope of the disclosure of the embodiments of the present invention.
[0080] The above are the exemplary embodiments disclosed by the present invention. However, it should be noted that various changes and modifications can be made without departing from the scope of the disclosure of the embodiments of the present invention defined by the claims. The functions, steps, and / or actions of the method claims according to the disclosed embodiments herein do not need to be executed in any specific order. In addition, although the elements disclosed in the embodiments of the present invention can be described or claimed in an individual form, they can also be understood as plural unless clearly limited to the singular.
[0081] It should be understood that, as used herein, unless the context clearly supports an exception, the singular form "a" is also intended to include the plural form. It should also be understood that the "and / or" used herein refers to any and all possible combinations of one or more of the associated listed items.
[0082] The serial numbers of the disclosed embodiments of the present invention above are only for description and do not represent the superiority or inferiority of the embodiments.
[0083] Those of ordinary skill in the art can understand that all or part of the steps to implement the above embodiments can be completed by hardware, or can be completed by instructing relevant hardware through a program. The program can be stored in a computer-readable storage medium, and the above-mentioned storage medium can be a read-only memory, a magnetic disk, an optical disk, etc.
[0084] Those of ordinary skill in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope (including the claims) of the disclosure of the embodiments of the present invention is limited to these examples; under the concept of the embodiments of the present invention, the technical features in the above embodiments or different embodiments can also be combined, and there are many other variations in different aspects of the embodiments of the present invention as described above, which are not provided in detail for the sake of brevity. Therefore, any omission, modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present invention shall be included in the protection scope of the embodiments of the present invention.
Claims
1. A method for acquiring signal light information of a connected vehicle, characterized in that: The following steps are involved: Sending a first authentication request to the platform; In response to the authentication being passed, receiving first signal light information returned by the platform; Acquiring the second signal light information through a sensing device of the connected vehicle; Fused signal light information is determined based on the first signal light information and the second signal light information.
2. The method according to claim 1, characterized in that Sending a first authentication request to the platform further includes: sending the first authentication request to the enterprise-level platform; In response to the authentication being passed, receiving the first signal light information returned by the platform further includes: In response to the authentication being successful, receiving the address of the city-level platform returned by the enterprise-level platform; Sending connected vehicle status information to the city-level platform based on the address; Receive the first signal light information returned by the city-level platform based on the connected vehicle status information.
3. The method according to claim 2, characterized in that Before sending the first authentication request to the enterprise-level platform, the following steps are also performed on the enterprise-level platform: Receiving a signal light service subscription request sent by the connected vehicle; Verifying the request; In response to the verification being passed, storing the subscription information carried in the request and updating the subscription list; The subscription list and corresponding subscription information are synchronously updated to the city-level platform.
4. The method according to claim 2, characterized in that Before sending the connected vehicle status information to the city-level platform based on the address, the method further includes executing the following steps on the city-level platform: Receiving a second authentication request sent by the connected vehicle; verifying the second authentication request based on the subscription list and the subscription information; In response to successful verification, a verification success is returned to the connected vehicle.
5. The method according to claim 2, characterized in that Before receiving the first signal light information returned by the city-level platform based on the connected vehicle status information, the method further includes executing the following steps on the city-level platform: Receiving connected vehicle status information sent by the connected vehicle; The first signal light information is obtained based on the connected vehicle status information and sent to the connected vehicle.
6. The method according to claim 5, characterized in that The method further comprises: obtaining the first signal light information based on the networked vehicle status information; Determine the location information and driving direction of the connected vehicle based on the connected vehicle status information; Determine a data set of signal lights located in front of the connected vehicle using the connected vehicle position information and the driving direction; The first signal light information is determined according to the networked vehicle position information and the position information in the signal light data set.
7. The method according to claim 6, characterized in that Determining first signal light information according to the networked vehicle position information and the position information in the signal light data set further includes: Determine a first signal light that the connected vehicle is about to pass according to the distance between each signal light position information in the signal light data set and the connected vehicle; Determine the corresponding entrance lane according to the distance between the center point of the road section of each lane at the intersection corresponding to the first signal light and the connected vehicle; The first signal light information is determined according to the entrance road and the driving direction of the connected vehicle.
8. The method according to claim 1, characterized in that Determining fused signal light information based on the first signal light information and the second signal light information further includes: The fused signal light information is determined based on a state of the light state information and a state of the remaining time information in the second signal light information and the first signal light information.
9. The method according to claim 8, characterized in that Determining the fused signal light information based on the state of the light state information and the state of the remaining time information in the second signal light information and the first signal light information further includes: In response to the light state information and the remaining time information being both missing in the second signal light information, using the first signal light information as fused signal light information; In response to the light state information in the second signal light information not being missing, determining a first weight based on a distance between the connected vehicle and a lane stop line of an intersection, and determining a second weight based on a current environment; Determine the probability of each light state by using the first weight, the second weight, the probability of each light state in the first signal light information, and the probability of each light state information in the second signal light information; Using the light state information with the highest probability as the light state information in the fused signal light information; In response to the remaining time information in the second signal light information not being missing, determining the remaining time information in the fused signal light information based on the first weight, the second weight, the remaining time in the first signal light information, and the remaining time information in the second signal light information; In response to the missing remaining time in the second signal light information, the remaining time is predicted based on the historical data of the connected vehicle, and the remaining time information in the fused signal light information is determined based on the first weight, the second weight, the remaining time information in the first signal light information, and the predicted remaining time.
10. A signal light information acquisition system for a connected vehicle, characterized in that: include: Connected vehicles; An enterprise-level platform for receiving a first authentication request sent by a connected vehicle; The city-level platform is used to send first signal light information to the connected vehicle after the first authentication request of the connected vehicle is passed; The networked vehicle is also used to obtain second signal light information based on a sensing device on the vehicle side, and obtain fused signal light information based on the first signal light information and the second signal light information.
Citation Information
Patent Citations
Automatic driving traffic signal lamp information acquisition system and method based on vehicle-road cooperation
CN116913116A
Traffic light data fusion method, device and equipment
CN117576903A
Signal lamp data correction method and device, computer readable medium and electronic equipment
CN118430295A
Signal lamp indication method based on V2X information and navigation route, vehicle and storage medium
CN119399975A
Self-adaptive cruise system supporting traffic light recognition and control method
WO2021093853A1