A method, system and medium for generating a lane-level navigation map

Abstract

The application provides a lane-level navigation map generation method, system and medium. The generation method is applied to a lane-level navigation map generation system deployed on a vehicle. The generation method comprises the following steps: using a calculation unit, in the case that the vehicle drives into a complex road section, creating a current road map corresponding to the vehicle based on positioning information of the vehicle and road information of the complex road section obtained from an acquisition unit; using the calculation unit, creating a first road map with a lane driving direction of a first lane and a second road map with a lane driving direction of a second lane based on the current road map; the first lane is a lane where the vehicle drives; the second lane is a lane where a preceding vehicle driving in a front area of the vehicle drives; and using the calculation unit, fusing the first road map and the second road map to obtain a lane-level navigation map with multiple lane driving directions corresponding to the complex road section. The application can improve the efficiency and accuracy of constructing the lane-level navigation map.

Description

Technical Field

[0001] This application relates to the technical field of automotive driver assistance systems, specifically to a method, system, and medium for generating lane-level navigation maps. Background Technology

[0002] Current advanced driver assistance systems (ADAS) primarily rely on high-precision navigation maps to determine the vehicle's driving path and corresponding lanes. Related technologies typically involve image acquisition to identify lane direction markings on road signs, or driving through all lanes requiring mapping to collect corresponding road information to construct high-precision navigation maps for complex road sections such as intersections and forks. However, this approach can be problematic in complex road sections with large areas of blank lane lines or incorrect road signs, leading to lower map accuracy, long learning cycles, and large amounts of data to store, resulting in time-consuming and costly map construction. Summary of the Invention

[0003] The purpose of this application is to provide a method, system, and medium for generating lane-level navigation maps, in order to solve the problems of low accuracy, long production time, and high production cost in the construction of high-precision navigation maps in complex road sections in the prior art. It can construct a lane-level navigation map with multiple lane directions corresponding to the complex road section based on a first road map with the lane direction of the vehicle and a second road map with the lane direction of the preceding vehicle, based on a single trip of the vehicle, i.e. when the vehicle is traveling on a complex road section. This can improve the efficiency and accuracy of constructing lane-level navigation maps, i.e., high-precision navigation maps.

[0004] To achieve the above objectives, this application provides a method for generating lane-level navigation maps. This method is applied to a lane-level navigation map generation system deployed on a vehicle. The lane-level navigation map generation system includes a computing unit and a data acquisition unit. The generation method includes:

[0005] Using the computing unit, when the vehicle enters a complex road section, a current road map corresponding to the vehicle is created based on the vehicle's location information and the road information of the complex road section obtained from the acquisition unit;

[0006] Using the computing unit, based on the current road map, a first road map with a first lane and a second road map with a second lane are created; wherein, the first lane is the lane in which the vehicle travels; and the second lane is the lane in which the vehicle in front travels in the area in front of the vehicle.

[0007] Using the computing unit, the first road map and the second road map are fused to obtain a lane-level navigation map with multiple lane driving directions corresponding to the complex road segment.

[0008] In some embodiments of this application, the lane-level navigation map generation system further includes a navigation map unit. Before the calculation unit creates a current road map corresponding to the vehicle based on the vehicle's positioning information and the road information of the complex road segment obtained from the acquisition unit when the vehicle enters a complex road segment, the method further includes: using the calculation unit to acquire the navigation map road information corresponding to the vehicle during its driving process collected by the navigation map unit; and using the calculation unit to determine that the vehicle has entered the complex road segment based on the navigation map road information characterizing the road attributes as complex road conditions.

[0009] In this way, by further confirming whether a vehicle has entered a complex road section based on the road information collected by the navigation map unit, the judgment ability of the computing unit can be improved, thus providing a basis for subsequent related calculations.

[0010] In some embodiments of this application, the step of using the computing unit to create a current road map corresponding to the vehicle when the vehicle enters a complex road section, based on the vehicle's positioning information obtained from the acquisition unit and the road information of the complex road section, includes: using the computing unit to create the current road map based on the vehicle's positioning information acquired by the acquisition unit as a reference point, and based on the navigation map road information acquired by the navigation map unit and the road information acquired by the acquisition unit when the vehicle enters a complex road section.

[0011] In this way, by using computing units, road information of complex road sections and road information of navigation maps are fused with the real-time driving information (location information) of vehicles to generate a current road map with higher accuracy and more matching the current driving situation of vehicles.

[0012] In some embodiments of this application, the lane-level navigation map generation system further includes: a turn signal acquisition unit; before using the calculation unit to create a first road map with a first lane and a second road map with a second lane based on the current road map, the method further includes: using the calculation unit to acquire the turn signal status of the vehicle acquired by the turn signal acquisition unit and the preceding vehicle information acquired by the acquisition unit; the step of using the calculation unit to create the first road map with a first lane and the second road map with a second lane based on the current road map includes: using the calculation unit to create the first road map based on the turn signal status and the current road map; and using the calculation unit to create the second road map based on the preceding vehicle information and the current road map.

[0013] In this way, by creating a first road map for the vehicle based on the turn signal status and the current road map, and creating a second road map for the preceding vehicle based on the preceding vehicle information and the current road map, the accuracy of the corresponding road map generation can be improved. This provides a parameter basis for the subsequent creation of lane-level navigation maps with multiple lane driving directions for complex road sections.

[0014] In some embodiments of this application, the step of using the computing unit to create the first road map based on the turn signal status and the current road map includes: using the computing unit to obtain the turn signal activation information carried in the turn signal status; and using the computing unit to create the first road map by fusing the activation information and the current road map with the vehicle's positioning information.

[0015] In this way, based on the vehicle's turn signal activation information, the vehicle's positioning information and the current road map are integrated to construct a first road map showing the vehicle's driving direction in the lane it is traveling in. This makes the first road map constructed based on the vehicle's driving information (turn signal activation information and positioning information) more accurate.

[0016] In some embodiments of this application, the step of using the computing unit to create a second road map based on the preceding vehicle information and the current road map includes: using the computing unit to obtain the positioning information of the preceding vehicle in the preceding vehicle information; and using the computing unit to create a second road map based on the current road map, the positioning information of the preceding vehicle, and the positioning information of the vehicle.

[0017] In this way, based on the location information of the preceding vehicle, the location information of the vehicle itself, and the current road map, a second road map is constructed that shows the driving direction of the preceding vehicle in the lane it is traveling in. Thus, by referring to the driving information of the preceding vehicle and the driving information of the vehicle itself, the accuracy of the constructed second road map is improved.

[0018] In some embodiments of this application, the generation method further includes: using the computing unit to transmit the lane-level navigation map to the vehicle's control unit via a communication bus, so that the control unit controls the vehicle to drive in the complex road section based on the lane-level navigation map.

[0019] In this way, by communicating with the vehicle's control unit through the vehicle's communication bus, the vehicle can be controlled to drive on complex road sections based on the calculated lane-level navigation map, thereby improving the vehicle's driving efficiency on complex road sections.

[0020] In some embodiments of this application, the lane-level navigation map generation system further includes a high-precision map unit, and the generation method further includes: using the computing unit to send the lane-level navigation map to the high-precision map unit, so that the high-precision map unit updates the initial high-precision navigation map based on the lane-level navigation map to obtain the updated high-precision navigation map; wherein, the initial high-precision navigation map is the high-precision navigation map corresponding to the complex road segment.

[0021] In this way, the calculation unit can be used to update or adjust the high-precision navigation map generated by the high-precision map unit, so as to make the final lane-level navigation map (high-precision navigation map) more accurate.

[0022] This application embodiment also provides a lane-level navigation map generation system, which is deployed on a vehicle, and includes:

[0023] The acquisition unit is configured to acquire the vehicle's location information and the road information of the complex road section;

[0024] The computing unit is configured to create a current road map corresponding to the vehicle based on the vehicle's positioning information and the road information of the complex road section when the vehicle enters a complex road section.

[0025] The computing unit is further configured to create a first road map with a lane travel direction having a first lane and a second road map with a lane travel direction having a second lane based on the current road map; wherein, the first lane is the lane in which the vehicle travels; and the second lane is the lane in which the vehicle in front travels in the area in front of the vehicle.

[0026] The computing unit is also configured to fuse the first road map and the second road map to obtain a lane-level navigation map with multiple lane driving directions corresponding to the complex road segment.

[0027] Correspondingly, this application embodiment also provides a computer storage medium storing computer-executable instructions, which, when executed, can implement any of the lane-level navigation map generation methods described above.

[0028] The beneficial effects of the embodiments of this application are as follows:

[0029] This technology addresses the issues of low accuracy, long production time, and high cost in existing technologies for building high-precision navigation maps on complex road sections. It can construct a lane-level navigation map with multiple lane directions for a single vehicle trip, i.e., when a vehicle is traveling on a complex road section, based on a first road map showing the lane direction of the vehicle and a second road map showing the lane direction of the vehicle in front. This improves the efficiency and accuracy of building lane-level navigation maps, i.e., high-precision navigation maps. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein:

[0031] Figure 1 A flowchart illustrating a method for generating lane-level navigation maps provided in this application embodiment;

[0032] Figure 2 A flowchart illustrating another method for generating lane-level navigation maps provided in this application embodiment;

[0033] Figure 3 A flowchart illustrating another method for generating lane-level navigation maps provided in this application embodiment;

[0034] Figure 4 A system framework diagram of a system corresponding to the lane-level navigation map generation method provided in the embodiments of this application;

[0035] Figure 5 A framework diagram illustrating the execution flow of a lane-level navigation map generation method provided in this application embodiment to generate relevant information;

[0036] Figure 6 This is a schematic diagram of the composition structure of a lane-level navigation map generation system provided in an embodiment of this application. Detailed Implementation

[0037] The embodiments of this application will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be understood that the preferred embodiments are only for illustrating this application and are not intended to limit the scope of protection of this application.

[0038] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0039] In the following description, the terms "first, second, third" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first, second, third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which embodiments of this application belong. The terminology used herein is for descriptive purposes only and is not intended to limit the scope of embodiments of this application.

[0041] To address the problems mentioned in the background art, this application provides a method, system, and medium for generating lane-level navigation maps. This solves the problems of low accuracy, long production time, and high cost in existing technologies for building high-precision navigation maps on complex road sections. It can construct a lane-level navigation map with multiple lane directions for a single vehicle trip, i.e., when a vehicle is traveling on a complex road section, based on a first road map showing the lane direction of the vehicle and a second road map showing the lane direction of the preceding vehicle. This improves the efficiency and accuracy of constructing lane-level navigation maps, i.e., high-precision navigation maps.

[0042] This application provides a method for generating lane-level navigation maps. This method is applied to a lane-level navigation map generation system deployed on a vehicle. The lane-level navigation map generation system includes a computing unit and a data acquisition unit, such as... Figure 1 The diagram shown is a flowchart illustrating a method for generating lane-level navigation maps according to an embodiment of this application; refer to... Figure 1 The following explanation is provided:

[0043] Step S101: Using the computing unit, when the vehicle enters a complex road section, a current road map corresponding to the vehicle is created based on the vehicle's positioning information and the road information of the complex road section obtained from the acquisition unit.

[0044] In some embodiments of this application, the lane-level navigation map generation system can be deployed on a vehicle. Correspondingly, the system can use its internal acquisition unit to collect vehicle positioning information, road information corresponding to complex road sections, etc. At the same time, the computing unit inside the lane-level navigation map generation system can perform fusion calculation on the vehicle positioning information and road information collected by the acquisition unit.

[0045] It should be noted that the lane-level navigation map generation system includes a data acquisition unit that can transmit the collected information to the computing unit via the vehicle's data bus.

[0046] The vehicle's location information may include absolute coordinates, as well as longitude, latitude, elevation, and time.

[0047] Here, complex road sections can be: intersections, roundabouts, forks in the road, merging sections, etc.

[0048] In some embodiments of this application, the current road map corresponding to the vehicle may be a road map of the current road of the vehicle (corresponding to the vehicle provided in the embodiments of this application) with lane-level accuracy.

[0049] Here, road information for complex road sections includes, but is not limited to: the position, type, and shape attributes of fixed road elements such as lane lines, curbs, guardrails, traffic light poles, streetlight poles, traffic signs, and traffic stops relative to vehicles; as well as the position, type, and shape attributes of movable road elements such as traffic cones and temporary signs relative to vehicles. This information can further include lane line position, lane line type, lane line trajectory, lane line start and end points, curb position, curb height, curb trajectory, curb start and end points, guardrail position, guardrail type, guardrail trajectory, guardrail start and end points, traffic light pole position, streetlight number and position, traffic sign type, traffic sign position, traffic stop type, traffic stop position, traffic cone type, traffic cone position, temporary sign type, and temporary sign position. It can also include lane line color, traffic light indicator type, curb color, guardrail color, traffic sign color, traffic stop color, traffic cone color, and temporary sign color.

[0050] Here, the acquisition unit may include a vehicle positioning unit and a road perception unit. The vehicle positioning unit may be a combined positioning module consisting of a Global Navigation Satellite System (GNSS), Real-time Kinematic (RTK), Inertial Measurement Unit (IMU), and wheel speed sensors. It integrates information from the satellite positioning system, differential positioning base station, vehicle inertial navigation system, and vehicle wheel speed sensors to provide lane-level absolute positioning coordinates for vehicle 2, including longitude, latitude, elevation, and time. The road perception unit may consist of a forward-facing lidar, a forward-facing camera, and a forward-facing millimeter-wave radar. This road perception unit is used to acquire road information.

[0051] Step S102: Using the computing unit, based on the current road map, create a first road map with a first lane and a second road map with a second lane and a lane direction.

[0052] Wherein, the first lane is the lane in which the vehicle travels; the second lane is the lane in which the vehicle in front of the vehicle travels.

[0053] In some embodiments of this application, based on the current road map determined by the computing unit, a first road map with a lane driving direction of a first lane and a second road map with a lane driving direction of a second lane can be created. This can be achieved by creating the first road map with a lane driving direction based on the current road map and the vehicle's turn signal status, combined with the vehicle's location information in the current road map; or by creating the second road map with a lane driving direction based on the current road map, the location information of the preceding vehicle, and the combined location information of the preceding vehicle in the current road map.

[0054] Here, the area in front of the vehicle can refer to the area collected by the data collection unit of the lane-level navigation map generation system deployed on the vehicle, with the vehicle's direction of travel as the reference view. At the same time, the vehicle in front of the vehicle in the area in front of the vehicle can include vehicles traveling in the same direction as the vehicle or vehicles traveling in the opposite direction. The number of vehicles in front can be one, two or more.

[0055] Step S103: Using the computing unit, the first road map and the second road map are fused to obtain a lane-level navigation map with multiple lane driving directions corresponding to the complex road segment.

[0056] In some embodiments of this application, a computing unit is used to fuse a first road map and a second road map; wherein, the fusion can be based on the coordinate information carried in the first road map and the second road map respectively, so as to obtain a lane-level navigation map with a multi-lane driving path created for a single trip when the vehicle is driving in a complex road section.

[0057] Here, the lane-level navigation map corresponding to the complex road segment with multiple driving directions can include the driving path corresponding to each road (not limited to: one-way or two-way driving) in the complex road segment, as well as the lane driving direction information corresponding to each driving segment.

[0058] In this way, by relying solely on the data acquisition and computing units within the lane-level navigation map generation system deployed on the vehicle, a lane-level navigation map with multiple lane directions can be constructed for a single vehicle trip, i.e. when the vehicle is traveling on a complex road segment. Based on a first road map showing the lane direction of the vehicle and a second road map showing the lane direction of the vehicle in front, the lane-level navigation map corresponding to the complex road segment can be constructed. This improves the efficiency and accuracy of constructing lane-level navigation maps, i.e., high-precision navigation maps.

[0059] In some embodiments of this application, where the lane-level navigation map generation system further includes a navigation map unit, a computing unit can also be used to identify complex road sections based on the navigation map road information collected by the navigation map unit during vehicle travel. That is, in the lane-level navigation map generation method provided in this application embodiment, the following step S201 can be executed before step S101. For example... Figure 2 The diagram shown is a flowchart illustrating another method for generating lane-level navigation maps according to an embodiment of this application; see reference. Figure 1 and Figure 2 The following explanation is provided:

[0060] Step S201: Using the computing unit, obtain the navigation map road information corresponding to the vehicle during driving, collected by the navigation map unit.

[0061] In some embodiments of this application, a computing unit may be used to obtain the navigation map road information corresponding to the vehicle during driving, collected by the navigation map unit; wherein, the navigation map road information includes, but is not limited to, road attributes; and the vehicle may be identified as having entered an intersection, roundabout, fork in the road, merging section, etc., based on the road attributes.

[0062] Step S202: Using the computing unit, based on the road information of the navigation map, the road attributes are characterized as complex road conditions, and it is determined that the vehicle has entered the complex road section.

[0063] In some embodiments of this application, a computing unit is used to characterize the road attributes as complex road conditions based on navigation map road information, that is, the road conditions where the vehicle is currently located are complex road conditions, so as to determine that the vehicle has entered a complex road section.

[0064] In this way, by further confirming whether a vehicle has entered a complex road section based on the road information collected by the navigation map unit, the judgment ability of the computing unit can be improved, thus providing a basis for subsequent related calculations.

[0065] Correspondingly, when the navigation map road information is obtained, a computing unit can be used to create the current road map based on the navigation map road information and the road information, using the vehicle's positioning information as a reference point. That is, step S101 provided in the above embodiment can be implemented through the following step 203:

[0066] Step S203: Using the computing unit, when the vehicle enters a complex road section, the current road map is created based on the navigation map road information collected by the navigation map unit and the road information collected by the acquisition unit, with the vehicle's positioning information collected by the acquisition unit as a reference point.

[0067] In some embodiments of this application, a computing unit is directly used to fuse navigation map road information and road information of complex road sections with the vehicle's positioning information as a reference point to generate a new road map, namely the current road map corresponding to the vehicle.

[0068] In this way, by using computing units, road information of complex road sections and road information of navigation maps are fused with the real-time driving information (location information) of vehicles to generate a current road map with higher accuracy and more matching the current driving situation of vehicles.

[0069] In some embodiments of this application, when the lane-level navigation map generation system further includes a turn signal acquisition unit, a calculation unit can first acquire the turn signal status of the vehicle acquired by the turn signal acquisition unit and the preceding vehicle information acquired by the acquisition unit. Then, the calculation unit uses the turn signal status and the current road map to create a first road map, and uses the preceding vehicle information and the current road map to create a second road map. That is, in the lane-level navigation map generation method provided in the embodiments of this application, the following step S301 can also be performed before executing step S102. Figure 3 The diagram shown is a flowchart illustrating another method for generating lane-level navigation maps according to an embodiment of this application; see reference. Figure 1 and Figure 3 The following explanation is provided:

[0070] Step S301: Using the calculation unit, obtain the turn signal status of the vehicle collected by the turn signal acquisition unit and the information of the preceding vehicle collected by the acquisition unit.

[0071] In some embodiments of this application, the turn signal acquisition unit can acquire the status information of the vehicle lights deployed on the vehicle, wherein the vehicle lights can be deployed at any location on the vehicle. The turn signal status includes: turn signal on, off, left turn signal on, right turn signal on, etc.

[0072] The data acquisition unit can collect not only road information for complex road sections, but also information about vehicles ahead. This information includes, but is not limited to, the type and number of the vehicle ahead, its real-time position relative to the current vehicle, and its color.

[0073] It should be noted that the vehicle's turn signals include, but are not limited to, turn signals deployed on the left and right sides of the vehicle.

[0074] Correspondingly, based on the turn signal status and the information of the vehicle in front obtained by the calculation unit, the following steps S302 and S303 can be further executed:

[0075] Step S302: Using the computing unit, create the first road map based on the turn signal status and the current road map.

[0076] In some feasible embodiments of this application, a computing unit can first analyze the turn signal activation information carried in the turn signal, and then create the first road map based on the activation information, the current road map, and the positioning information of vehicle 2. That is, step S302 provided in the above embodiment can be implemented by the following steps S3021 and S3022 (not shown in the figure):

[0077] Step S3021: Using the calculation unit, obtain the turn signal activation information carried in the turn signal status;

[0078] Step S3022: Using the computing unit, based on the activation information and the current road map, the first road map is created by fusing it with the vehicle's positioning information.

[0079] In some embodiments of this application, the turn signal activation information includes: activation start and end times, and which direction the light is activated (left or right light).

[0080] In this way, based on the vehicle's turn signal activation information, the vehicle's positioning information and the current road map are integrated to construct a first road map showing the vehicle's driving direction in the lane it is traveling in. This makes the first road map constructed based on the vehicle's driving information (turn signal activation information and positioning information) more accurate.

[0081] Step S303: Using the computing unit, create the second road map based on the preceding vehicle information and the current road map.

[0082] In some feasible embodiments of this application, a computing unit can be used to first obtain the positioning information of the preceding vehicle from the preceding vehicle information, and then, based on the positioning information of the preceding vehicle, the positioning information of the vehicle, and the current road map, construct a second road map with the driving direction of the lane in which the preceding vehicle is traveling. That is, step S303 provided in the above embodiment can be implemented by the following steps S3031 and S3032 (not shown in the figure):

[0083] Step S3031: Using the computing unit, obtain the positioning information of the preceding vehicle from the preceding vehicle information;

[0084] Step S3032: Using the computing unit, a second road map is created based on the current road map, the positioning information of the preceding vehicle, and the positioning information of the vehicle.

[0085] In some embodiments of this application, the location information of the preceding vehicle, the distance between the preceding vehicle and the vehicle's location information, and the azimuth difference can be determined according to actual needs.

[0086] The computing unit can be used to determine the relative position information of the preceding vehicle to the vehicle based on the positioning information of the preceding vehicle and the positioning information of the vehicle, and then construct the second road map based on the relative position information and the current road map.

[0087] In this way, based on the location information of the preceding vehicle, the location information of the vehicle itself, and the current road map, a second road map is constructed that shows the driving direction of the preceding vehicle in the lane it is traveling in. Thus, by referring to the driving information of the preceding vehicle and the driving information of the vehicle itself, the accuracy of the constructed second road map is improved.

[0088] In this way, by creating a first road map for the vehicle based on the turn signal status and the current road map, and creating a second road map for the preceding vehicle based on the preceding vehicle information and the current road map, the accuracy of the corresponding road map generation can be improved. This provides a parameter basis for the subsequent creation of lane-level navigation maps with multiple lane driving directions for complex road sections.

[0089] Based on the above description, the lane-level navigation map generation method provided in this application embodiment can also perform the following step A:

[0090] Step A: Using the computing unit, the lane-level navigation map is transmitted to the vehicle's control unit via the vehicle's communication bus, so that the control unit controls the vehicle to drive in the complex road section based on the lane-level navigation map.

[0091] In some embodiments of this application, the computing unit is further configured to send the calculated lane-level navigation map to the vehicle control unit via the vehicle's communication bus, so that the vehicle control unit can control the vehicle to drive in complex road sections based on the received lane-level navigation map.

[0092] In this way, by communicating with the vehicle's control unit through the vehicle's communication bus, the vehicle can be controlled to drive on complex road sections based on the calculated lane-level navigation map, thereby improving the vehicle's driving efficiency on complex road sections.

[0093] Meanwhile, in the lane-level navigation map generation system, which also includes a high-precision map unit, a computing unit can be used to send the lane-level navigation map to the high-precision map unit, so that the high-precision map unit updates the initial high-precision navigation map based on the lane-level navigation map to obtain the updated high-precision navigation map. That is, the lane-level navigation map generation method provided in this application embodiment can also perform the following step B:

[0094] Step B: Using the computing unit, the lane-level navigation map is sent to the high-precision map unit, so that the high-precision map unit updates the initial high-precision navigation map based on the lane-level navigation map, and obtains the updated high-precision navigation map.

[0095] The initial high-precision navigation map is the high-precision navigation map corresponding to the complex road segment.

[0096] Here, the vehicle (lane-level navigation map generation system) can also be equipped with high-precision map units, which are used to generate high-precision navigation maps corresponding to complex road sections when the vehicle is driving on complex road sections. Then, the computing unit can use the calculated lane-level navigation map to update or adjust the high-precision navigation map generated by the high-precision map unit, so that the final lane-level navigation map (high-precision navigation map) is more accurate.

[0097] The method for generating lane-level navigation maps described above will be explained below with reference to a specific embodiment. However, it is worth noting that this specific embodiment is only for better illustrating the embodiments of this application and does not constitute an improper limitation on the embodiments of this application.

[0098] Current advanced driver assistance systems (ADAS) rely on navigation routes from maps and high-definition maps to determine the target driving path and lane. However, ADAS systems based on high-definition maps are limited by the mapping cycle and cost. Mapping complex road sections such as intersections and forks requires identifying lane directions and paths; currently, lane direction identification is achieved through two main methods:

[0099] Option 1 involves using cameras and other sensors to identify the lane direction markings on road signs. This requires the cameras to match the applicable roads and lanes for each road sign at the intersection. Since there are many lane direction markings at intersections and forks, there may be mismatches of road signs. In addition, for road sections with large areas of blank lane lines, such as intersections and forks, this option cannot obtain the path to the corresponding target lane, thus making it impossible to complete the road network mapping.

[0100] Option 2 requires driving the vehicle through all the lanes that need to be mapped, collecting the vehicle's driving path and direction, and identifying the driving direction markings in the lanes using sensors such as cameras. If it is necessary to collect the driving direction of each lane, the user needs to complete the driving coverage of each lane, which has the problems of long learning cycle and large amount of data to store.

[0101] Based on the above description, to alleviate the current limitations of high-precision map production progress, navigation maps required for advanced driver assistance functions can be pre-built by learning user driving routes and road information. This application provides a method for generating lane-level navigation maps. This method is deployed (equipped) in a vehicle as a lane-level navigation map generation system. This system may include: an Electronic Control Unit (ECU) computing unit 401, a navigation map unit 402, a vehicle turn signal acquisition unit 403, a combined positioning unit 404 consisting of GNSS+RTK+IMU+wheel speed sensors, a forward-sensing lidar 405, a forward-sensing camera 406, a forward-sensing millimeter-wave radar 407, a vehicle bus 408, and a high-precision map unit 409, such as... Figure 4 The diagram shows a system framework diagram of a system corresponding to the lane-level navigation map generation method provided in the embodiments of this application.

[0102] The navigation map unit 402 can provide road-level road information, including whether the road attributes are intersections, roundabouts, forks, or merging sections.

[0103] The vehicle turn signal acquisition unit 403 can provide the on / off information of the left and right turn signals in the vehicle.

[0104] The combined positioning unit 404, consisting of GNSS, RTK, IMU, and wheel speed sensors, integrates information from satellite positioning systems, differential positioning base stations, vehicle inertial navigation systems, and vehicle wheel speed sensors to provide lane-level absolute positioning coordinates for the vehicle, including longitude, latitude, elevation, and time.

[0105] The forward-facing LiDAR 405 provides road information and information about vehicles ahead. Road information includes the position, type, and shape of fixed road elements such as lane lines, curbs, guardrails, traffic light poles, streetlights, traffic signs, and traffic stops relative to the vehicle. It also includes the position, type, and shape of movable road elements such as traffic cones and temporary signs relative to the vehicle. Specifically, this includes lane line position, lane line type, lane line trajectory, lane line start and end points; curb position, curb height, curb trajectory, curb start and end points; guardrail position, guardrail type, guardrail trajectory, guardrail start and end points; traffic light pole position, streetlight number and position; traffic sign type, traffic sign position; traffic stop type, traffic stop position; traffic cone type, traffic cone position; and temporary sign type and temporary sign position. Information about vehicles ahead includes the vehicle type, vehicle number, and real-time position of the vehicle relative to the vehicle.

[0106] The forward-facing camera 406 provides road information and information about vehicles ahead. The road information includes road details identified by the LiDAR, and may also include color information for road elements that the LiDAR cannot recognize, specifically lane line colors, traffic light indicator types, curb colors, guardrail colors, traffic sign colors, bus stop colors, traffic cone colors, and temporary sign colors. The information about vehicles ahead also includes their colors.

[0107] The forward-facing millimeter-wave radar 407 provides information about the road the vehicle is traveling on and the vehicle ahead, including road information and vehicle ahead information identified by lidar.

[0108] The high-precision map module 409 provides attribute information on whether the road where the vehicle is located is covered by a high-precision map.

[0109] The ECU computing unit 401 acquires information from the navigation map unit 402, the vehicle turn signal acquisition unit 403, the high-precision map unit 409, the combined positioning unit 404 consisting of GNSS+RTK+IMU+wheel speed sensors, the forward-sensing lidar 405, the forward-sensing camera 406, and the forward-sensing millimeter-wave radar 407, and learns and records the first road map corresponding to the vehicle's driving path. Figure 1 The second road corresponding to the travel path of the vehicle in front Figure 2 and create a first road that integrates Figure 1 Second Road Figure 2 The corresponding lane-level road Figure 3 .

[0110] The vehicle bus 408 obtains information from various units for the ECU computing unit 401, and converts the lane-level road map created by the ECU computing unit 401 into a single unit. Figure 3 It is uploaded to the vehicle bus 408 for use by the backend demand side of the intelligent driving algorithm module inside the vehicle.

[0111] Correspondingly, this application also provides a framework diagram of the execution flow for generating relevant information using the lane-level navigation map generation method, which can be referred to. Figure 5 As shown:

[0112] First, such as Figure 5 The ECU calculation unit 401 shown obtains navigation map road information 501 from the navigation map unit 402, obtains vehicle positioning information 502 from the combined positioning unit 404 consisting of GNSS+RTK+IMU+wheel speed sensor, and combines the road information 503 to 505 obtained by the forward-aware lidar 405, the forward-aware camera 406, and the forward-aware millimeter-wave radar 407 to create the current road map 507 for the vehicle.

[0113] Here, it should be noted that the ECU calculation unit 401 determines whether the current road requires the initiation of the corresponding lane-level navigation map generation step. Specifically, the ECU calculation unit 401 obtains road-level navigation map information from the navigation map unit 402, including whether the road attributes are intersections, roundabouts, forks, or merging sections. If the road where the vehicle is located is an intersection, fork, or similar location, the ECU calculation unit 401 initiates calculations on various information collected by the relevant acquisition units, namely the combined positioning unit 404 consisting of GNSS+RTK+IMU+wheel speed sensors, the forward-sensing lidar 405, the forward-sensing camera 406, and the forward-sensing millimeter-wave radar 47.

[0114] Secondly, the ECU calculation unit 401 obtains the vehicle turn signal switch information from the vehicle turn signal acquisition unit 403, and combines it with the current road map 507 of the vehicle to perform the vehicle driving path learning 511, that is, to create a road map 511 with the lane driving direction of the vehicle driving lane.

[0115] Then, the ECU calculation unit 401 simultaneously obtains the preceding vehicle information 508 to 510 from the forward-sensing lidar 405, the forward-sensing camera 406, and the forward-sensing millimeter-wave radar 407, and combines it with the current road map 507 of the vehicle to perform the vehicle's driving path learning 512, so as to create a road map 512 with the lane driving direction of the preceding vehicle.

[0116] Finally, the ECU calculation unit 401 merges the road map 511 of the lane in which the vehicle is traveling and the road map 512 of the lane in which the preceding vehicle is traveling, to create a road map 513 with a multi-lane driving path in a single trip.

[0117] Thus, the lane-level navigation map generation system provided in this application embodiment, when mounted on a vehicle, can complete the fusion of road paths into a lane-level map within a single vehicle trip. This involves mapping the current lane and adjacent lanes, solving the problem in related technologies where road path mapping requires multiple trips in different lanes, resulting in low learning efficiency. This reduces mapping costs and time consumption. In this way, multiple lane directions for intersections, roundabouts, forks, and merging sections can be created during a single trip, changing the current situation where only the current lane's driving path can be learned in a single trip. This improves the efficiency of driving path learning, allowing the backend navigation module to quickly obtain road maps that meet the navigation requirements.

[0118] This application provides a lane-level navigation map generation system, which is deployed on a vehicle, such as... Figure 6 As shown, the lane-level navigation map generation system 1 includes:

[0119] The acquisition unit 11 is configured to acquire the vehicle's location information and the road information of the complex road section;

[0120] The computing unit 12 is configured to create a current road map corresponding to the vehicle based on the vehicle's positioning information and the road information of the complex road section when the vehicle enters a complex road section.

[0121] The computing unit 12 is further configured to create a first road map with a lane travel direction having a first lane and a second road map with a lane travel direction having a second lane based on the current road map; wherein, the first lane is the lane in which the vehicle travels; and the second lane is the lane in which the vehicle in front travels in the area in front of the vehicle.

[0122] The computing unit 12 is also configured to fuse the first road map and the second road map to obtain a lane-level navigation map with multiple lane driving directions corresponding to the complex road segment.

[0123] It should be noted that the description of the lane-level navigation map generation system in this embodiment is similar to that of the method embodiment described above, and has similar beneficial effects. For technical details not disclosed in the system embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0124] Correspondingly, this application embodiment further provides a computer program product, which includes computer-executable instructions. After the computer-executable instructions are executed, they can implement the lane-level navigation map generation method provided in this application embodiment.

[0125] Accordingly, this application embodiment further provides a computer storage medium storing computer-executable instructions, which, when executed by a processor, implement the lane-level navigation map generation method provided in the above embodiment.

[0126] The descriptions of the lane-level navigation map generation system and storage medium embodiments above are similar to the descriptions of the method embodiments above, and have similar technical descriptions and beneficial effects. Due to space limitations, please refer to the descriptions of the method embodiments above, and therefore will not be repeated here. For technical details not disclosed in the lane-level navigation map generation system and storage medium embodiments provided in this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0127] It should be understood that the phrase "an embodiment" or "one embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of the present application. Therefore, "in one embodiment" or "one embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of the present application, the sequence number of the above-described processes does not imply the order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The sequence numbers of the above-described embodiments are merely for descriptive purposes and do not represent the superiority or inferiority of the embodiments. It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0128] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0129] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0130] Furthermore, in the embodiments of this application, all functional units can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in a combination of hardware and software functional units. Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0131] The above description is merely a specific implementation of the embodiments of this application, but the protection scope of the embodiments of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the embodiments of this application should be included within the protection scope of the embodiments of this application. Therefore, the protection scope of the embodiments of this application should be determined by the protection scope of the claims.

Claims

1. A method for generating lane-level navigation maps, characterized in that, The generation method is applied to a lane-level navigation map generation system deployed on a vehicle. The lane-level navigation map generation system includes a calculation unit, a data acquisition unit, and a turn signal acquisition unit. The generation method includes: Using the computing unit, when the vehicle enters a complex road section, a current road map corresponding to the vehicle is created based on the vehicle's location information and the road information of the complex road section obtained from the acquisition unit; The calculation unit is used to obtain the turn signal status of the vehicle collected by the turn signal acquisition unit and the information of the vehicle in front collected by the acquisition unit. Using the computing unit, a first road map with a lane travel direction of a first lane is created based on the turn signal status and the current road map; wherein, the first lane is the lane in which the vehicle travels; Using the computing unit, a second road map with a lane travel direction having a second lane is created based on the preceding vehicle information and the current road map; wherein, the second lane is the lane in which the preceding vehicle travels in the area in front of the vehicle; Using the computing unit, the first road map and the second road map are fused to obtain a lane-level navigation map with multiple lane driving directions corresponding to the complex road segment.

2. The generation method according to claim 1, characterized in that, The lane-level navigation map generation system further includes a navigation map unit. Before the calculation unit creates a current road map corresponding to the vehicle based on the vehicle's location information and the road information of the complex road section obtained from the acquisition unit when the vehicle enters a complex road section, the method further includes: The computing unit is used to obtain the navigation map road information corresponding to the vehicle during its driving process, which is collected by the navigation map unit. Using the aforementioned computing unit, based on the road information in the navigation map representing complex road conditions, it is determined that the vehicle has entered the complex road segment.

3. The generation method according to claim 2, characterized in that, The computing unit, when the vehicle enters a complex road section, creates a current road map corresponding to the vehicle based on the vehicle's location information obtained from the acquisition unit and the road information of the complex road section, including: Using the computing unit, when the vehicle enters a complex road section, the current road map is created based on the positioning information of the vehicle collected by the acquisition unit, the road information of the navigation map collected by the navigation map unit, and the road information collected by the acquisition unit, with the vehicle's positioning information collected by the acquisition unit as a reference point.

4. The generation method according to claim 1, characterized in that, The step of using the computing unit to create the first road map based on the turn signal status and the current road map includes: The calculation unit is used to obtain the turn signal activation information carried in the turn signal status; Using the computing unit, based on the activation information and the current road map, the first road map is created by fusing it with the vehicle's positioning information.

5. The generation method according to claim 1, characterized in that, The step of using the computing unit to create the second road map based on the preceding vehicle information and the current road map includes: The computing unit is used to obtain the location information of the preceding vehicle from the preceding vehicle information; Using the computing unit, a second road map is created based on the current road map, the location information of the preceding vehicle, and the location information of the vehicle.

6. The generation method according to any one of claims 1 to 3, characterized in that, The method further includes: Using the aforementioned computing unit, the lane-level navigation map is transmitted to the vehicle's control unit via the vehicle's communication bus, so that the control unit can control the vehicle to drive in the complex road section based on the lane-level navigation map.

7. The generation method according to any one of claims 1 to 3, characterized in that, The lane-level navigation map generation system further includes: a high-precision map unit, and the method further includes: Using the aforementioned computing unit, the lane-level navigation map is sent to the high-precision map unit, so that the high-precision map unit updates the initial high-precision navigation map based on the lane-level navigation map, thereby obtaining the updated high-precision navigation map. The initial high-precision navigation map is the high-precision navigation map corresponding to the complex road segment.

8. A system for generating lane-level navigation maps, characterized in that, The lane-level navigation map generation system is deployed on the vehicle, and the lane-level navigation map generation system includes: The acquisition unit is configured to acquire the vehicle's location information and road information for complex road sections; The turn signal acquisition unit is configured to acquire status information of the lights deployed on the vehicle; The computing unit is configured to create a current road map corresponding to the vehicle based on the vehicle's positioning information and the road information of the complex road section when the vehicle enters a complex road section. The calculation unit is further configured to acquire the turn signal status of the vehicle acquired by the turn signal acquisition unit and the preceding vehicle information acquired by the acquisition unit; using the calculation unit, based on the turn signal status and the current road map, to create a first road map with a first lane and a lane travel direction; wherein the first lane is the lane in which the vehicle is traveling; and using the calculation unit, based on the preceding vehicle information and the current road map, to create a second road map with a second lane and a lane travel direction; wherein the second lane is the lane in which the preceding vehicle is traveling in the area in front of the vehicle. The computing unit is also configured to fuse the first road map and the second road map to obtain a lane-level navigation map with multiple lane driving directions corresponding to the complex road segment.

9. A computer storage medium, characterized in that, The computer storage medium stores computer-executable instructions, which, when executed, enable the generation method of lane-level navigation map as described in any one of claims 1 to 7.

Images