Fork road path positioning method and device

Abstract

The invention provides a fork road path positioning method and device, and relates to the technical field of artificial intelligence, in particular to the technical fields of image processing, map navigation, automatic driving, intelligent traffic and the like. The specific implementation scheme is as follows: in response to detecting that a target vehicle travels to a preset distance range of a fork road, determining a traveling road section where the target vehicle is located; in response to determining that the driving road section is changed, determining driving road information of the target vehicle based on the plurality of vehicle front images of the target vehicle; and determining a target driving path of the target vehicle at the fork road based on the driving road information and the reference road information of the plurality of branch roads included in the fork road. According to the mode, the timeliness and reliability of determining the target driving path are improved.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to the fields of image processing, map navigation, autonomous driving, intelligent transportation, etc., and particularly relates to a method and device for path positioning at a fork in the road. Background Art

[0002] In the scenario of a small divergence road, it is usually dependent on GPS (Global Positioning System) data to determine the actual driving path of a vehicle. Summary of the Invention

[0003] Embodiments of the present disclosure provide a method, device, equipment, and storage medium for path positioning at a fork in the road.

[0004] In a first aspect, embodiments of the present disclosure provide a method for path positioning at a fork in the road. The method includes: in response to detecting that a target vehicle travels within a preset distance range of a fork in the road, determining the driving section where the target vehicle is located; in response to determining that the driving section has changed, determining the driving road information of the target vehicle based on a plurality of front vehicle images of the target vehicle; and determining the target driving path of the target vehicle at the fork in the road based on the driving road information and the reference road information of a plurality of divergence roads included in the fork in the road.

[0005] In a second aspect, embodiments of the present disclosure provide a device for path positioning at a fork in the road. The device includes: a section determination module, an image determination module, and a path determination module. Among them, the section determination module is configured to, in response to detecting that a target vehicle travels within a preset distance range of a fork in the road, determine the driving section where the target vehicle is located; the image determination module is configured to, in response to determining that the driving section has changed, determine the driving road information of the target vehicle based on a plurality of front vehicle images of the target vehicle; and the path determination module is configured to determine the target driving path of the target vehicle at the fork in the road based on the driving road information and the reference road information of a plurality of divergence roads included in the fork in the road.

[0006] In a third aspect, embodiments of the present disclosure provide an electronic device, which includes one or more processors; a storage device, on which one or more programs are stored. When the one or more programs are executed by the one or more processors, the one or more processors implement the method for path positioning at a fork in the road according to any embodiment of the first aspect.

[0007] In a fourth aspect, embodiments of the present disclosure provide a computer-readable medium, on which a computer program is stored. When the program is executed by a processor, it implements the method for path positioning at a fork in the road according to any embodiment of the first aspect.

[0008] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program which, when executed by a processor, implements the fork path positioning method according to any one of the embodiments of the first aspect.

[0009] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 is an exemplary system architecture diagram to which the present disclosure can be applied;

[0011] Figure 2 is a flowchart of an embodiment of the fork path positioning method according to the present disclosure;

[0012] Figure 3 is a flowchart of another embodiment of the fork path positioning method according to the present disclosure;

[0013] Figure 4 is a schematic diagram of an application scenario of the fork path positioning method according to the present disclosure;

[0014] Figure 5 is a schematic diagram of an embodiment of the fork path positioning device according to the present disclosure;

[0015] Figure 6 is a schematic diagram of the structure of a computer system of an electronic device suitable for implementing the embodiments of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to assist understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for clarity and conciseness, descriptions of well-known functions and structures are omitted below.

[0017] It should be noted that, without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other. The present disclosure will be described in detail below with reference to the drawings and in combination with the embodiments.

[0018] Figure 1 shows an exemplary system architecture 100 to which the fork path positioning method of the present disclosure can be applied.

[0019] As Figure 1As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0020] Users can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc.

[0021] The terminal devices 101, 102, 103 can be hardware or software. When the terminal devices 101, 102, 103 are software, they can be installed in the above-listed electronic devices. They can be implemented as multiple software or software modules, or can be implemented as a single software or software module. Specific limitations are not made here.

[0022] The server 105 can be a server that provides various services. For example, in response to detecting that a target vehicle has traveled within a preset distance range of an intersection, determine the driving section where the target vehicle is located; in response to determining that the driving section has changed, based on multiple front vehicle images of the target vehicle, determine the driving road information of the target vehicle; based on the driving road information and the reference road information of multiple diverging roads included in the intersection, determine the target driving path of the target vehicle at the intersection.

[0023] It should be noted that the server 105 can be hardware or software. When the server 105 is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules (such as those used to provide intersection path positioning services), or can be implemented as a single software or software module. Specific limitations are not made here.

[0024] It should be pointed out that the intersection path positioning method provided by the embodiments of the present disclosure can be executed by the server 105, or can be executed by the terminal devices 101, 102, 103, or can be executed by the server 105 and the terminal devices 101, 102, 103 in cooperation with each other. Correspondingly, each part (such as each unit, subunit, module, sub-module) included in the intersection path positioning device can be all set in the server 105, or can be all set in the terminal devices 101, 102, 103, or can be respectively set in the server 105 and the terminal devices 101, 102, 103.

[0025] It should be understood, Figure 1 The numbers of terminal devices, networks, and servers in [[ ]] are only illustrative. According to the implementation requirements, there can be any number of terminal devices, networks, and servers.

[0026] Figure 2 Flow 200 shows an embodiment of the fork path positioning method. The fork path positioning method may specifically include the following steps:

[0027] Step 201, in response to detecting that the target vehicle travels within a preset distance range of the fork, determine the driving section where the target vehicle is located.

[0028] In this embodiment, the execution entity (for example, Figure 1 the server 105 or the terminal devices 101, 102, 103) can determine whether the target vehicle travels within a preset distance range of the fork according to the external environment data (buildings, terrain, etc.) and / or road data (for example, traffic signs, markings, etc.), positioning data, etc. collected via the sensor devices of the target vehicle, such as GPS, GNSS (Global Navigation Satellite System), etc., or can also determine whether the target vehicle travels within a preset distance range of the fork according to the positioning information collected via the sensor devices, such as lidar, etc. This application does not make any limitations in this regard.

[0029] Specifically, if the execution entity detects a road sign indicating the existence of a fork ahead via lidar, it can determine that the target vehicle travels within a preset distance range of the fork.

[0030] Among them, the preset distance can be 30 meters, 50 meters, etc. This application does not make any limitations in this regard.

[0031] Further, if the target vehicle travels within a preset distance range of the fork, the execution entity can determine the driving section where the target vehicle is located according to at least one of the information such as positioning information, road data, and external environment data.

[0032] Step 202, in response to determining that the driving section has changed, determine the driving road information of the target vehicle based on multiple front images of the target vehicle.

[0033] In this embodiment, the execution entity can detect in real time or regularly whether the driving section of the target vehicle has changed. If it is determined that the driving section of the target vehicle has changed, that is, it is determined that the target vehicle has entered a diverging road of the fork, the execution entity can obtain multiple front images of the target vehicle via the image acquisition device installed on the target vehicle, such as a front view camera, a driving recorder, etc., and determine the driving road information of the target vehicle according to the multiple front images of the target vehicle.

[0034] Among them, the driving road information of the target vehicle, that is, the road information may include at least one of the following information: the total number of lanes, lane attributes, lane environment, etc.

[0035] Here, there are various ways for the execution entity to determine whether the driving section has changed. For example, if it is detected that the section corresponding to the trajectory of the target vehicle has changed, it can be determined that the driving section has changed; if it is detected that the road data and / or external environment data of the target vehicle have changed, it is determined that the driving section has changed, etc.

[0036] Among them, there are various ways for the execution entity to determine the driving road information of the target vehicle based on multiple front vehicle images of the target vehicle. For example, inputting the multiple front vehicle images into a preset recognition model to generate the driving road information of the target vehicle; using a preset image recognition algorithm, such as CNN (Convolutional Neural Networks), FCN (Fully Convolutional Networks), etc., to recognize the multiple front vehicle images to generate the driving road information of the target vehicle, etc.

[0037] Here, the preset recognition model can be trained based on the front vehicle image samples labeled with driving road information.

[0038] Step 203: Based on the driving road information and the reference road information of the multiple diverging roads included in the fork, determine the target driving path of the target vehicle at the fork.

[0039] In this embodiment, after the execution entity determines the driving road information of the target vehicle, it can match the driving road information with the reference road information of the multiple (for example, two, three, etc.) diverging roads included in the fork, that is, match the road information of the target vehicle with the road information of the diverging roads, and determine the target driving path of the target vehicle at the fork.

[0040] Among them, the diverging roads are used to indicate the roads in different directions branching out from the convergence point of the fork. For example, a two-way fork has two diverging roads.

[0041] Specifically, if the fork has two diverging roads, such as the first diverging road and the second diverging road, the execution entity can respectively match the driving road information with the reference road information of the first diverging road and the reference road information of the second diverging road. If the driving road information matches the reference road information of the first diverging road, it can be determined that the target vehicle has entered the first diverging road of the fork.

[0042] The fork - in - the - road path positioning method provided by the embodiments of the present disclosure determines the driving section where the target vehicle is located after detecting that the target vehicle travels within a preset distance range of the fork - in - the - road. Further, if it is determined that the driving section has changed, based on multiple front - vehicle images of the target vehicle, the driving road information of the target vehicle is determined, and based on the driving road information and the reference road information of multiple diverging roads included in the fork - in - the - road, the target driving path of the target vehicle at the fork - in - the - road is determined. When the driving section where the target vehicle is located changes, the target driving path of the target vehicle is determined in a timely manner according to the front - vehicle images of the target vehicle, overcoming the problem that GPS positioning information is prone to drift and has poor reliability at small - divergence fork - in - the - roads. At the same time, only based on the front - vehicle images of the vehicle after the driving section changes to determine the target driving path, the calculation amount is reduced, and the timeliness and reliability of determining the target driving path are effectively improved.

[0043] In some optional ways, in response to determining that the driving section has changed, based on multiple front - vehicle images of the target vehicle, determining the driving road information of the target vehicle includes: in response to determining that the driving section has changed, determining the change time; based on multiple front - vehicle images collected after the change time, determining the driving road information of the target vehicle.

[0044] In this implementation, the execution entity can collect section data (such as positioning information, external environment data, road data, etc.) for determining whether the driving section of the target vehicle has changed at a preset time interval. If it is detected that the section data collected at the target time is different from the section data collected at the previous time, the execution entity can directly determine the target time as the change time, or can also determine the change time according to any one of the target time and the previous time of the target time. This application does not make a limitation on this.

[0045] Among them, the preset time interval can be determined based on the vehicle speed, vehicle control information, etc. of the target vehicle.

[0046] Specifically, for example, the execution entity determines whether the driving section has changed based on whether the external environment data of the target vehicle has changed. If the execution entity detects that the environment data collected at the target time is different from the environment data collected at the previous time, the execution entity can directly determine the target time as the change time.

[0047] For another example, the execution entity determines whether the driving section has changed based on whether the section corresponding to the trajectory of the target vehicle has changed. If the execution entity detects that the trajectory points collected at the target time are different from the trajectory points collected at the previous time, the execution entity can directly determine the next time of the target time as the change time.

[0048] This implementation method determines the change time in response to determining that the driving section has changed, and determines the driving road information of the target vehicle based on multiple images in front of the vehicle collected after the change time, which helps to determine the accurate node of the section change and improves the timeliness of collecting multiple images in front of the vehicle.

[0049] In some alternative ways, determining the driving section where the target vehicle is located includes: determining the driving section where the target vehicle is located according to the driving trajectory of the target vehicle. The change of the driving section is determined in the following way: in response to determining that the driving section corresponding to the target trajectory point in the driving trajectory is different from the driving section corresponding to the previous trajectory point, it is determined that the driving section has changed.

[0050] In this implementation method, the execution entity can perform trajectory binding processing according to the driving trajectory of the target vehicle, and determine the driving section where the target vehicle is located according to the result of the trajectory binding processing.

[0051] Among them, the driving trajectory is composed of multiple trajectory points. The trajectory point, that is, the recording point, is the longitude and latitude information of the current position recorded by the positioning device at every preset time interval.

[0052] The trajectory binding processing is used to indicate matching the trajectory data with the map data to map the trajectory data onto the map.

[0053] During the driving process of the target vehicle, if the execution entity determines that the driving section corresponding to the target trajectory point in the driving trajectory is different from the driving section corresponding to the previous trajectory point, it can be determined that the driving section of the target vehicle has changed.

[0054] Specifically, if the driving section corresponding to the target trajectory point in the driving trajectory is the first diverging road of the fork, and the driving section corresponding to the previous trajectory point of the target trajectory point is the approaching section or the approach road of the fork, that is, the section where the target vehicle is about to enter the fork, it can be determined that the driving section of the target vehicle has changed.

[0055] This implementation method determines the driving section where the target vehicle is located according to the driving trajectory of the target vehicle. If it is determined that the driving section corresponding to the target trajectory point in the driving trajectory is different from the driving section corresponding to the previous trajectory point, it can be determined that the driving section has changed, which improves the reliability of determining that the driving section has changed.

[0056] In some alternative ways, in response to determining that the driving section corresponding to the target trajectory point is different from the driving section corresponding to the previous trajectory point, determining that the driving section has changed includes: in response to determining that the driving sections corresponding to the target trajectory point and the subsequent continuous preset number of trajectory points are all different from the driving section corresponding to the previous trajectory point of the target trajectory point, it is determined that the driving section has changed.

[0057] In this implementation manner, the execution entity can determine whether the driving sections corresponding to the target trajectory location and the subsequent consecutive preset number of trajectory points are all different from the driving section corresponding to the previous trajectory point of the target trajectory point. If so, it can be determined that the driving section has changed.

[0058] Among them, the preset number can be set according to experience and actual requirements. For example, 4, 5, etc.

[0059] Specifically, in the scenario of a one-to-two fork intersection, the one-to-two fork intersection includes the approach section or approach road G1 of the fork intersection, the first diverging road G2, and the second diverging road G3. If the section corresponding to the target trajectory point is G2, and the driving sections corresponding to the subsequent consecutive preset number of trajectory points of the target trajectory point, such as the first trajectory point, the second trajectory point, and the third trajectory point, are G2, G3, and G2 respectively, and the driving section corresponding to the previous trajectory point of the target trajectory point is G1, that is, the driving sections G2, G2, G3, and G2 corresponding to the target trajectory location and the subsequent consecutive preset number of trajectory points are all different from the driving section G1 corresponding to the previous trajectory point of the target trajectory point. That is, even if there is drift in the trajectory points of the target vehicle, it is a drift between the two diverging roads. That is, the target vehicle has completely entered the diverging roads of the fork intersection (excluding the scenario where the target vehicle jumps between the approach section and the diverging roads of the fork intersection), then it can be determined that the driving section of the target vehicle has changed.

[0060] In this implementation manner, if it is determined that the driving sections corresponding to the target trajectory point and the subsequent consecutive preset number of trajectory points are all different from the driving section corresponding to the previous trajectory point of the target trajectory point, then it can be determined that the driving section has changed, effectively eliminating the error caused by GPS positioning information drift and improving the reliability of determining that the driving section has changed.

[0061] In some alternative manners, in response to determining that the driving section has changed, determining the change time includes: in response to determining that the driving section has changed, determining the change time based on at least one of the first time corresponding to the target trajectory point and the second time corresponding to the previous trajectory point of the target trajectory point.

[0062] In this implementation manner, after the execution entity determines that the driving section has changed, it can determine the change time based on at least one of the first time corresponding to the target trajectory point and the second time corresponding to the previous trajectory point of the target trajectory point.

[0063] Here, the manner for the execution entity to determine the change time can include various methods. For example, directly determining the first time as the change time, determining the first specified time after the first time as the change time, directly determining the second time as the change time, determining any time between the first time and the second time as the change time, and so on.

[0064] Specifically, in one example, the way for the execution entity to determine that the driving section has changed is to determine that the driving section corresponding to the target trajectory point is different from the driving section corresponding to the previous trajectory point, and the intermediate moment between the first moment and the second moment can be determined as the change moment.

[0065] In another example, the way for the execution entity to determine that the driving section has changed is to determine that the driving section corresponding to the target trajectory point is different from the driving section corresponding to the previous trajectory point, and the driving sections corresponding to the target trajectory point and the subsequent continuous preset number of trajectory points are the same. The execution entity can determine the moment corresponding to the last trajectory point among the preset number of trajectory points after the first moment as the change moment.

[0066] This implementation method determines the change moment based on at least one of the first moment corresponding to the target trajectory point and the second moment corresponding to the previous trajectory point of the target trajectory point in response to determining that the driving section has changed, which improves the flexibility of determining the change moment.

[0067] Further refer to Figure 3 which shows Figure 2 Flow 300 of another embodiment of the fork path positioning method shown. In this embodiment, flow 300 of the fork path positioning method may include the following steps:

[0068] Step 301, in response to detecting that the target vehicle travels within a preset distance range of the fork, determine the driving section where the target vehicle is located.

[0069] In this embodiment, for the implementation details and technical effects of step 301, reference can be made to the description of step 201, which will not be elaborated here.

[0070] Step 302, in response to determining that the driving section has changed, determine the driving road information of the target vehicle based on multiple front vehicle images of the target vehicle.

[0071] For the implementation details and technical effects of step 302, reference can be made to the description of step 202, which will not be elaborated here.

[0072] Step 303, in response to determining that the total number of lanes of each of the multiple diverging roads included in the fork is inconsistent, determine the target driving path of the target vehicle at the fork based on the matching result between the total number of lanes of the driving road information and the total number of lanes of each of the multiple diverging roads.

[0073] In this embodiment, the road information may include the total number of lanes. After the executing entity determines the driving road information of the target vehicle, it can determine whether the total number of lanes of each of the multiple diverging roads included in the fork is the same. If not, it can match the total number of lanes of the driving lane information with the total number of lanes of each of the multiple diverging roads included in the fork, and determine the diverging road with a matching result as the target driving path of the target vehicle at the fork.

[0074] Among them, the total number of lanes is used to indicate the total number of lanes for vehicles to drive on a section of road. For example, 3, 4, 5, etc.

[0075] Specifically, if the total number of lanes of the driving road information is 3, and the total number of lanes of the first diverging road and the second diverging road included in the fork are 3 and 5 respectively, then the total number of lanes of the driving road information is the same as that of the first diverging road, that is, the target driving path of the target vehicle at the fork is the first diverging road of the fork.

[0076] In the above embodiment of the present disclosure, if it is determined that the total number of lanes of each of the multiple diverging roads included in the fork is inconsistent, then based on the matching result of the total number of lanes of the driving road information and the total number of lanes of each of the multiple diverging roads, the target driving path of the target vehicle at the fork is determined. That is, when the total number of lanes of the diverging roads at the fork is inconsistent, the target driving path is directly determined according to the matching result of the total number of lanes, effectively saving the calculation amount and further improving the timeliness of determining the target driving path.

[0077] In some alternative ways, the method further includes: in response to determining that the total number of lanes of each of the multiple diverging roads included in the fork is the same, determining the target driving path of the target vehicle at the fork based on the matching result of the lane attributes of the driving road information and the lane attributes of each of the multiple diverging roads.

[0078] In this implementation, the road information may further include lane attributes. After the executing entity determines the driving road information of the target vehicle, it can determine whether the total number of lanes of each of the multiple diverging roads included in the fork is the same. If so, it can match the lane attributes of the driving road information with the lane attributes of each of the multiple diverging roads included in the fork, and determine the diverging road with a matching result as the target driving path of the target vehicle at the fork.

[0079] Among them, the lane attributes may include lane arrows (used to indicate the driving direction of the lane, for example, left turn, straight, right turn, etc.), text markings (used to identify special lanes, for example, bus only, right turn only), etc.

[0080] Specifically, if the lane attribute of the driving road information includes a lane arrow and the lane arrow indicates a left turn, and the lane arrows of the first diverging road and the second diverging road included in the fork respectively indicate a left turn and a right turn, then the lane attribute of the driving road information is consistent with the lane attribute of the first diverging road, that is, the target driving path of the target vehicle at the fork is the first diverging road of the fork.

[0081] This implementation method determines the target driving path of the target vehicle at the fork based on the matching result of the lane attribute of the driving road information and the lane attributes of each of the multiple diverging roads included in the fork if it is determined that the total number of lanes of each of the multiple diverging roads included in the fork is the same, which helps to identify the target driving path of the target vehicle at the fork when the total number of lanes of the multiple diverging roads included in the fork is the same.

[0082] In some alternative ways, the lane attribute includes at least one of the following: curvature, slope, type, width, and ground marking.

[0083] In this implementation method, the lane attribute may include at least one of the following: curvature (used to record the degree of bending of the lane, for example, 0.0017m-1, 0.005m-1, etc.), slope (used to represent the ascending or descending angle of the lane, for example, 3%, 4%, etc.), type (used to distinguish different lanes, for example, straight lane, turning lane, acceleration lane, etc.), width (used to record the actual width of the lane, for example, 6 meters, 8 meters, etc.), and ground marking (used to help identify the legal driving path of the lane, for example, dashed line, solid line, etc.).

[0084] Specifically, if the lane attribute of the driving road information includes a slope and the slope is 3%, and the slopes of the first diverging road and the second diverging road included in the fork are 3% and 4% respectively, then the slope of the driving road information is consistent with the slope of the first diverging road, that is, the target driving path of the target vehicle at the fork is the first diverging road of the fork.

[0085] This implementation method further improves the reliability of determining the target driving path by setting the lane attribute to include one or more of curvature, slope, type, width, and ground marking, and determining the target driving path of the target vehicle at the fork according to the lane attribute when the total number of lanes of the multiple diverging roads included in the fork is the same.

[0086] In some alternative ways, the driving road information of the target vehicle is determined based on multiple front vehicle images of the target vehicle, including: determining the average curvature of the road where the target vehicle is located according to the multiple front vehicle images; and determining the target driving path of the target vehicle at the fork based on the matching result of the lane attribute of the driving lane information and the lane attributes of each of the multiple diverging roads, including: determining the target driving path of the target vehicle at the fork based on the matching result of the average curvature and the curvature of each of the multiple diverging roads included in the fork.

[0087] In this implementation, after obtaining multiple front vehicle images of the target vehicle, the execution entity can respectively determine the curvature of the roads where the multiple target vehicles are located according to the multiple front vehicle images and perform average processing on the multiple curvatures to determine the average curvature.

[0088] Further, the execution entity can respectively match the average curvature with the curvatures of the multiple diverging roads included in the fork, and determine the diverging road with a matching result as the target driving path of the target vehicle at the fork.

[0089] Specifically, if the lane attribute of the driving road information includes curvature, the multiple curvatures determined by the execution entity based on multiple (such as 5) front vehicle images are 0.0015 m-1, 0.0016 m-1, 0.0017 m-1, 0.0018 m-1, and 0.0019 m-1 respectively, the average curvature determined according to the multiple curvatures is 0.0017 m-1, and the curvatures of the first diverging road and the second diverging road included in the fork are 0.0018 m-1 and 0.0017 m-1 respectively, then the average curvature of the driving road information is consistent with the curvature of the second diverging road, that is, the target driving path of the target vehicle at the fork is the second diverging road of the fork.

[0090] This implementation determines the average curvature of the road where the target vehicle is located according to multiple front vehicle images, and determines the target driving path of the target vehicle at the fork based on the matching result of the average curvature and the curvature of each of the multiple diverging roads included in the fork, eliminating random errors and further improving the reliability of the determined target driving path.

[0091] In some alternative ways, the following method is used to determine whether the target vehicle has traveled within a preset distance range of the fork: determining the road network structure where the current position is located in the first map data according to the current position of the target vehicle; determining whether the target vehicle has traveled within a preset distance range of the fork based on the current position and the road network structure; and determining the driving section where the target vehicle is located, including: determining the driving section where the target vehicle is located in the second map data.

[0092] In this implementation, the executing entity can obtain the current position of the target vehicle in real time or periodically via a sensor device, such as GPS, GNSS, etc.

[0093] Furthermore, the executing entity can determine the road network structure of the area where the current position is located in the first map data according to the current position.

[0094] Among them, the road network structure can include multiple road segments and the connection relationships between each road segment.

[0095] Furthermore, the executing entity can determine whether the target vehicle has traveled within a preset distance range of the fork according to the current position and the road network structure.

[0096] After determining that the target vehicle has traveled within a preset distance range of the fork, determine the driving road segment where the target vehicle is located in the second map data.

[0097] Among them, the accuracy of the first map data is less than that of the second map data. For example, the first map data may only include road topologies, and the second map data may include road signs, lane lines, etc.

[0098] Specifically, the first map data can be a low-precision map or a medium-precision map, and the second map data can be a high-precision map or an ultra-high-precision map, etc.

[0099] In this method, due to the low accuracy of the first map data, the first map data can be deployed in the client, which helps to quickly determine whether the target vehicle has traveled within a preset distance range of the fork. The second map data has a high accuracy and can be deployed in the server, which helps to improve the accuracy and reliability of the determined driving road segment.

[0100] In some alternative ways, the method further includes: determining whether the target vehicle has deviated based on the matching result between the target driving path and the planned path of the target vehicle; in response to determining that the target vehicle has deviated, generating a new planned path based on the target driving path and the destination.

[0101] In this implementation, after the executing entity determines the target driving path, it can match the target driving path with the planned path to obtain a matching result. If the target driving path is not on the current plan of the target vehicle, it is considered that the matching result between the target driving path and the planned path is unmatched, and further, it can be determined that the target vehicle has deviated.

[0102] After the executing entity determines that the target vehicle has deviated, it can correct the current planned path according to the target driving path and the destination, generate a new planned path, and use the new planned path to guide the target vehicle into the correct path.

[0103] In addition, after determining that the target vehicle yaws, the execution entity may output a yaw warning message.

[0104] Among them, the output method of the warning message may include various types, for example, sound warning, visual warning, vibration warning, etc.

[0105] This implementation method determines whether the target vehicle yaws based on the matching result of the target driving path and the planned path of the target vehicle. If it is determined that the target vehicle yaws, a new planned path is generated based on the target driving path and the destination, which helps to correct the planned path in a timely manner.

[0106] In some optional ways, determining the target driving path of the target vehicle at the fork based on the driving road information and the reference road information of the multiple diverging roads included in the fork includes: determining the first driving path of the target vehicle at the fork based on the driving road information and the reference road information of the multiple diverging roads included in the fork; determining the second driving path of the target vehicle at the fork based on the positioning information of the target vehicle; determining the third driving path of the target vehicle at the fork based on the inertial measurement information of the target vehicle; and determining the target driving path of the target vehicle at the fork based on the first driving path, the second driving path, and the third driving path.

[0107] In this implementation method, the execution entity may determine the first driving path of the target vehicle at the fork according to the driving road information and the reference road information of the multiple diverging roads included in the fork.

[0108] Furthermore, the execution entity may determine the positioning information of the target vehicle according to sensor devices such as GPS and GNSS, and determine the second driving path of the target vehicle at the fork according to the positioning information of the target vehicle.

[0109] Furthermore, the execution entity may determine the inertial measurement information of the target vehicle according to the IMU (Inertial Measurement Unit), and determine the third driving path of the target vehicle at the fork according to the inertial measurement information.

[0110] Further, the execution entity can directly determine the target driving path based on the first driving path, the second driving path, and the third driving path (for example, if the first driving path, the second driving path, and the third driving path are all the first diverging roads at a fork, the target driving path can be determined as the first diverging road), or can determine the target driving path of the target vehicle at the fork based on the first driving path, the second driving path, the third driving path, and the confidence levels corresponding to each path (for example, the first driving path and the second driving path are both the first diverging roads at a fork, the third driving path is the second diverging road at the fork, and the confidence levels corresponding to the first driving path and the second driving path are higher than the confidence level corresponding to the third driving path, then the first driving path and the second driving path can be determined as the target driving path, that is, the first diverging road at the fork is determined as the target driving path), and this application does not make any limitations in this regard.

[0111] Among them, the confidence levels corresponding to each path can be determined based on external environments such as road conditions information and weather information.

[0112] This implementation method jointly determines the target driving path through the first driving path determined based on the driving road information and the reference road information of multiple diverging roads included in the fork, the second driving path determined based on GPS, and the third driving path determined based on IMU, realizes the fusion of multi-source data, and further improves the accuracy of the determined target driving path.

[0113] In some alternative ways, based on multiple front vehicle images of the target vehicle, determining the driving road information of the target vehicle includes: based on multiple front vehicle images of the target vehicle collected by a driving recorder, determining the driving road information of the target vehicle.

[0114] In this implementation method, the execution entity can collect multiple front vehicle images of the target vehicle via a driving recorder installed on the target vehicle, and determine the driving road information of the target vehicle at the fork according to the multiple front vehicle images.

[0115] Among them, a driving recorder is a device installed in a vehicle (usually installed at the top center of the front windshield or on the right side near the rearview mirror), used to record videos and audios during the vehicle's driving process to record various situations during the driving process. The front vehicle images collected by the driving recorder can be color images or grayscale images.

[0116] This implementation method determines the driving road information of the target vehicle based on multiple front vehicle images of the target vehicle collected by a driving recorder, utilizes the characteristics that the driving recorder is set at a relatively high position and is usually set in front of the vehicle, can determine the road information in a timely manner, and effectively improves the timeliness of road recognition.

[0117] Continue to refer to Figure 4, Figure 4 It is a schematic diagram of the application scenario of the fork path positioning method according to this embodiment.

[0118] The execution entity can determine the current position of the target vehicle 401 via GPS, and determine the road network structure of the area where the current position is located in the pre-stored map according to the current position. According to the current position and the road network structure, it is determined whether the target vehicle 401 has traveled within a preset distance range of a fork (for example, an elevated fork, and the fork includes a first diverging road 402 and a second diverging road 403), for example, 30 meters or 20 meters away from the fork. If so, the driving section where the target vehicle is located is determined according to the trajectory of the target vehicle, such as the approach road. Further, if it is determined based on the driving trajectory of the target vehicle that the driving section has changed (for example, from the approach road to the first diverging road 402 of the fork), then based on the multiple images in front of the vehicle collected by the on-vehicle image device, such as a driving recorder, the driving road information of the target vehicle 401 is determined. The road information may include the total number of lanes and the lane attributes. If the total number of lanes of the multiple diverging roads included in the fork is inconsistent, such as the total number of lanes of the first diverging road and the second diverging road are 3 and 2 respectively, then the total number of lanes of the driving road information of the target vehicle is respectively matched with the total number of lanes of the first diverging road and the total number of lanes of the second diverging road to obtain a matching result, and the target driving path is determined based on the matching result, that is, the second diverging road 403 is determined as the target driving path.

[0119] In addition, if the total number of lanes of the first diverging road and the second diverging road included in the fork is the same, then the lane attributes of the driving lane information are respectively matched with the lane attributes of the first diverging road and the lane attributes of the second diverging road to obtain a matching result, and the target driving path is determined based on the matching result.

[0120] Further referring to Figure 5 , as an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a fork path positioning device, and this device embodiment corresponds to Figure 2 the method embodiment shown.

[0121] As Figure 5 shown, the fork path positioning device 500 of this embodiment includes: a section determination module 501, an image determination module 502, and a path determination module 503.

[0122] Among them, the section determination module 501 is configured to determine the driving section where the target vehicle is located in response to detecting that the target vehicle has traveled within a preset distance range of the fork.

[0123] An image determination module 502, configured to determine driving road information of a target vehicle based on a plurality of front-vehicle images of the target vehicle in response to determining that a driving section has changed.

[0124] A path determination module 503, configured to determine a target driving path of the target vehicle at a fork based on the driving road information and reference road information of a plurality of diverging roads included in the fork.

[0125] In some alternative implementations of this embodiment, the image determination module further includes: a time determination unit, configured to determine a change time in response to determining that a driving section has changed; an image determination unit, configured to determine the driving road information of the target vehicle based on a plurality of front-vehicle images collected after the change time.

[0126] In some alternative implementations of this embodiment, the path determination module is further configured to: determine a driving section where the target vehicle is located according to the driving trajectory of the target vehicle; and determine that the driving section has changed in the following manner: in response to determining that the driving section corresponding to a target trajectory point in the driving trajectory is different from the driving section corresponding to the previous trajectory point, determine that the driving section has changed.

[0127] In some alternative implementations of this embodiment, determining that the driving section has changed in response to determining that the driving section corresponding to a target trajectory point in the driving trajectory is different from the driving section corresponding to the previous trajectory point includes: in response to determining that the driving sections corresponding to the target trajectory point and a subsequent continuous preset number of trajectory points are all different from the driving section corresponding to the previous trajectory point of the target trajectory point, determine that the driving section has changed.

[0128] In some alternative implementations of this embodiment, the time determination unit is further configured to determine a change time based on at least one of a first time corresponding to the target trajectory point and a second time corresponding to the previous trajectory point of the target trajectory point in response to determining that the driving section has changed.

[0129] In some alternative implementations of this embodiment, the path determination unit is further configured to, in response to determining that the total number of lanes of each of the plurality of diverging roads included in the fork is inconsistent, determine the target driving path of the target vehicle at the fork based on a matching result between the total number of lanes of the driving road information and the total number of lanes of each of the plurality of diverging roads.

[0130] In some alternative implementations of this embodiment, the path determination unit is further configured to: in response to determining that the total number of lanes of each of the plurality of diverging roads included in the fork is the same, determine the target driving path of the target vehicle at the fork based on a matching result between the lane attributes of the driving lane information and the lane attributes of each of the plurality of diverging roads.

[0131] In some alternative embodiments of the present embodiment, the lane attributes include at least one of the following: curvature, slope, type, width, and road markings.

[0132] In some alternative embodiments of the present embodiment, the image determination module is further configured to determine the average curvature of the road where the target vehicle is located based on a plurality of images in front of the vehicle; and the path determination module is further configured to determine the target driving path of the target vehicle at the fork based on the matching result between the average curvature and the curvatures of the multiple diverging roads included in the fork.

[0133] In some alternative embodiments of the present embodiment, the section determination module is further configured to determine the road network structure where the current position is located in the first map data according to the current position of the target vehicle; based on the current position and the road network structure, determine whether the target vehicle has traveled within a preset distance range of the fork; and determine the driving section where the target vehicle is located, including: determining the driving section where the target vehicle is located in the second map data.

[0134] In some alternative embodiments of the present embodiment, the path determination module further includes a first determination unit, a second determination unit, a third determination unit, and a target determination unit, where the first determination unit is configured to determine the first driving path of the target vehicle at the fork based on the driving road information and the reference road information of the multiple diverging roads included in the fork; the second determination unit is configured to determine the second driving path of the target vehicle at the fork based on the positioning information of the target vehicle; the third determination unit is configured to determine the third driving path of the target vehicle at the fork based on the inertial measurement information of the target vehicle; the target determination unit is configured to determine the target driving path of the target vehicle at the fork based on the first driving path, the second driving path, and the third driving path.

[0135] In some alternative embodiments of the present embodiment, the device further includes: a yaw recognition module, and a path planning module, where the yaw recognition module is configured to determine whether the target vehicle yaws based on the matching result between the target driving path and the planned path of the target vehicle; the path planning module is configured to generate a new planned path based on the target movement path and the destination in response to determining that the target vehicle yaws.

[0136] In some alternative embodiments of the present embodiment, the image determination module is further configured to determine the driving road information of the target vehicle based on a plurality of images in front of the vehicle collected by a driving recorder.

[0137] In the technical solution of the present disclosure, the acquisition, storage, and application of the user's personal information involved all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0138] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0139] Figure 6 FIG. shows a schematic block diagram of an exemplary electronic device 600 that can be used to implement embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, for example, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, for example, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely exemplary and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0140] As Figure 6 shown, the device 600 includes a computing unit 601 that can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0141] A plurality of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0142] The computing unit 601 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 executes the various methods and processes described above, such as the method for fork path positioning. For example, in some embodiments, the method for fork path positioning can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the method for fork path positioning described above can be executed. Alternatively, in other embodiments, the computing unit 601 can be configured to execute the method for fork path positioning in any other suitable manner (e.g., by means of firmware).

[0143] Various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), systems-on-a-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0144] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0145] In the context of this disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0146] In order to provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0147] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0148] A computer system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The relationship between the client and the server is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to address the deficiencies of high management difficulty and weak business scalability existing in traditional physical hosts and virtual private server (VPS) services. The server can also be a server of a distributed system or a server combined with a blockchain.

[0149] According to the technical solution of the embodiment of the present disclosure, the timeliness and reliability of path positioning at a fork are effectively improved.

[0150] It should be understood that various forms of the processes shown above can be used, steps can be reordered, added or deleted. For example, the steps recited in the present disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution provided by the present disclosure can be achieved, and no limitation is imposed herein.

[0151] The above specific embodiments do not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

1. A method for locating a fork in a road, comprising: In response to detecting that the target vehicle is traveling within a preset distance range of the fork in the road, determining a driving section where the target vehicle is located; In response to determining that the driving section has changed, determining driving road information of the target vehicle based on a plurality of vehicle front images of the target vehicle; A target driving path of the target vehicle at the fork in the road is determined based on the driving road information and reference road information of a plurality of diverging roads included in the fork in the road.

2. The method according to claim 1, wherein: In response to determining that the driving section has changed, determining the driving road information of the target vehicle based on a plurality of vehicle front images of the target vehicle, includes: In response to determining that the driving section has changed, determining a change time; Based on a plurality of vehicle front images collected after the change time, the driving road information of the target vehicle is determined.

3. The method according to claim 2, wherein: Determining the driving section where the target vehicle is located includes: Determine the driving section of the target vehicle according to the driving trajectory of the target vehicle; The change of the driving section is determined by the following method: In response to a driving section corresponding to a target trajectory point in the driving trajectory being different from a driving section corresponding to a previous trajectory point, it is determined that the driving section has changed.

4. The method according to claim 3, wherein: In response to determining that the driving section corresponding to the target track point in the driving track is different from the driving section corresponding to the previous track point, determining that the driving section has changed includes: In response to determining that the driving sections corresponding to the target trajectory point and a subsequent preset number of continuous trajectory points are all different from the driving section corresponding to the previous trajectory point of the target trajectory point, it is determined that the driving section has changed.

5. The method according to claim 3 or 4, wherein: In response to determining that the driving section has changed, determining the change time includes: In response to determining that the driving section has changed, a change time is determined based on at least one of a first time corresponding to the target trajectory point and a second time corresponding to a previous trajectory point of the target trajectory point.

6. The method according to claim 1, wherein: The road information includes the total number of lanes. Based on the driving road information and reference road information of a plurality of diverging roads included in the fork, determining a target driving path of the target vehicle at the fork includes: In response to determining that the total number of lanes of each of the multiple divergent roads included in the fork is inconsistent, a target driving path of the target vehicle at the fork is determined based on a matching result of the total number of lanes of the driving road information and the total number of lanes of each of the multiple divergent roads.

7. The method according to claim 6, wherein the road information further includes lane attributes, and further includes: In response to determining that the total number of lanes of the plurality of divergent roads included in the fork is consistent, a target driving path of the target vehicle at the fork is determined based on a matching result of the lane attributes of the driving lane information and the lane attributes of the plurality of divergent roads.

8. The method according to claim 5, wherein: The lane attributes include at least one of the following: curvature, slope, type, width, and ground markings.

9. The method according to claim 8, wherein: The lane attribute includes curvature, and determining the driving road information of the target vehicle based on the plurality of vehicle front images of the target vehicle includes: Determining a mean curvature of a road on which the target vehicle is located based on the plurality of vehicle front images; and The determining of a target driving path of the target vehicle at the fork in the road based on the matching result of the lane attribute of the driving lane information and the lane attributes of each of the plurality of divergent roads comprises: Based on the matching result of the curvature mean value and the curvatures of each of the plurality of diverging roads included in the fork, a target driving path of the target vehicle at the fork is determined.

10. The method according to claim 1, wherein determining whether the target vehicle has traveled to within a preset distance range of the fork in the road is performed by: According to the current position of the target vehicle, determining the road network structure where the current position is located in the first map data; Based on the current position and the road network structure, determining whether the target vehicle has traveled to within a preset distance range of the fork in the road; And the determining of the driving section where the target vehicle is located includes: A driving section of a target vehicle in second map data is determined, wherein the accuracy of the first map data is less than that of the second map data.

11. The method according to claim 1, wherein: The step of determining a target driving path of the target vehicle at the fork in the road based on the driving road information and reference road information of a plurality of diverging roads included in the fork in the road comprises: Determining a first driving path of the target vehicle at the fork in the road based on the driving road information and reference road information of a plurality of diverging roads included in the fork in the road; Determining a second driving path of the target vehicle at the fork in the road based on the positioning information of the target vehicle; Determining a third driving path of the target vehicle at the fork in the road based on the inertial measurement information of the target vehicle; A target driving path of the target vehicle at the fork in the road is determined based on the first driving path, the second driving path, and the third driving path.

12. The method according to any one of claims 1 to 11, further comprising: Determining whether the target vehicle is off course based on a matching result between the target driving path and the planned path of the target vehicle; In response to determining that the target vehicle is off course, a new planned path is generated based on the target driving path and a destination.

13. The method according to any one of claims 1 to 11, wherein: The determining of the driving road information of the target vehicle based on the plurality of vehicle front images of the target vehicle comprises: Based on a plurality of vehicle front images of the target vehicle collected by a driving recorder, the driving road information of the target vehicle is determined.

14. A fork in the road path positioning device, comprising: a road section determination module, configured to determine a driving section where the target vehicle is located in response to detecting that the target vehicle is traveling within a preset distance range of a fork in the road; an image determination module configured to determine the driving road information of the target vehicle based on a plurality of vehicle front images of the target vehicle in response to determining that the driving road section has changed; The path determination module is configured to determine a target driving path of the target vehicle at the fork in the road based on the driving road information and reference road information of a plurality of divergent roads included in the fork in the road.

15. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 13.

16. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 13.

17. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 13.

Images