A navigation assistance driving method and device based on a standard navigation map

Abstract

The application relates to a navigation auxiliary driving method and device based on a standard navigation map, and belongs to the technical field of auxiliary driving, wherein the navigation auxiliary driving method based on the standard navigation map comprises the following steps: acquiring offline SD Map data and a destination, generating a road-level navigation path based on the offline SD Map data and the destination; determining the pose of a vehicle on an SD Map road based on vehicle positioning data, vehicle inertial measurement unit data, vehicle wheel speed meter data and road features perceived by the vehicle; generating a virtual lane based on the road-level navigation path, and determining a dynamic driving constraint condition based on the virtual lane and real-time traffic state data; determining a target lane sequence of the vehicle based on the road-level navigation path, and determining a driving track and an action sequence of the vehicle based on the target lane sequence and the dynamic driving constraint condition. The application effectively improves the reliability and accuracy of navigation auxiliary driving.

Description

Technical Field

[0001] This invention relates to the field of driver assistance technology, and in particular to a navigation-assisted driving method and device based on a standard navigation map. Background Technology

[0002] Currently, the mainstream navigation-on-autopilot (NOA) system relies on high-definition maps (HD maps) to achieve lane-level planning and control through centimeter-level lane geometry, topology, and attributes. Map-less solutions rely on pure perception and end-to-end models to complete road reasoning. Standard definition maps (SD maps) used in vehicles only provide road-level paths, points of interest (POIs), road names, and basic traffic rules, but do not provide lane-level geometry and topology.

[0003] Existing NOA relies on high-precision maps, which have high collection / update costs, limited qualifications, and insufficient freshness, and are prone to failure in tunnels, elevated roads, and densely populated urban areas; the topology reasoning error rate is high in complex intersections, construction, backlighting, and heavy rain scenarios, and the safety redundancy is low; general navigation maps only display routes and provide voice guidance, and are not deeply coupled with intelligent driving control, so they cannot support stable navigation; the vehicle navigation route is disconnected from the intelligent driving planning route, which can easily lead to command conflicts, untimely lane changes, and missed exits.

[0004] Therefore, improving the accuracy and reliability of assisted driving has become an urgent technical problem to be solved. Summary of the Invention

[0005] In view of this, it is necessary to provide a navigation-assisted driving method and device based on standard navigation maps to solve the problems of insufficient accuracy and reliability of current navigation-assisted driving.

[0006] To address the aforementioned problems, in a first aspect, the present invention provides a navigation-assisted driving method based on a standard navigation map, comprising: Obtain offline SD Map data and destination, and generate road-level navigation routes based on the offline SD Map data and destination; Based on vehicle positioning data, vehicle inertial measurement unit data, vehicle wheel speed measurement data, and road features perceived by the vehicle, the vehicle's pose on the SD Map road is determined. Virtual lanes are generated based on road-level navigation paths, and dynamic driving constraints are determined based on virtual lanes and real-time traffic status data. The target lane sequence of the vehicle is determined based on the road-level navigation path, and the vehicle's driving trajectory and action sequence are determined based on the target lane sequence and dynamic driving constraints. The vehicle's driving trajectory is used to indicate the navigation trajectory, and the vehicle's action sequence is used to indicate the vehicle's motion state on the navigation trajectory.

[0007] In one possible implementation, generating road-level navigation paths based on offline SD Map data and the destination includes: Constructing a map atlas based on offline SD Map data; Based on the map atlas and the destination, the A* algorithm is used to generate road-level navigation paths.

[0008] In one possible implementation, determining the vehicle's pose on the SD Map road based on vehicle positioning data, vehicle inertial measurement unit data, vehicle wheel speedometer data, and road features perceived by the vehicle includes: Vehicle positioning data, vehicle inertial measurement unit data, vehicle wheel speed sensor data, and road features perceived by the vehicle are projected onto the SD Map to determine the vehicle's longitudinal mileage, lateral offset, and heading on the SD Map road.

[0009] In one possible implementation, generating virtual lanes based on road-level navigation paths includes: Virtual lanes are generated based on the road topology and road attributes of each road on the road-level navigation path.

[0010] In one possible implementation, determining the dynamic driving constraints based on virtual lanes and real-time traffic state data includes: Real-time traffic data is mapped onto the corresponding virtual lanes to determine dynamic driving constraints.

[0011] In one possible implementation, determining the target lane sequence of the vehicle based on the road-level navigation path includes: The target lane sequence for the vehicle is determined based on the road-level navigation path and the current vehicle location.

[0012] In one possible implementation, determining the vehicle's trajectory and action sequence based on the target lane sequence and dynamic driving constraints includes: The road trajectory of the vehicle is determined based on the target lane sequence and dynamic driving constraints, as well as the vehicle's speed, acceleration, and heading on the road trajectory.

[0013] On the other hand, the present invention also provides a navigation-assisted driving device based on a standard navigation map, comprising: The acquisition module is used to acquire offline SD Map data and destination, and generate road-level navigation routes based on the offline SD Map data and destination; The first determining module is used to determine the vehicle's pose on the SD Map road based on vehicle positioning data, vehicle inertial measurement unit data, vehicle wheel speedometer data, and road features perceived by the vehicle. The second determining module is used to generate virtual lanes based on road-level navigation paths and determine dynamic driving constraints based on virtual lanes and real-time traffic status data. The third determination module is used to determine the target lane sequence of the vehicle based on the road-level navigation path, and to determine the vehicle's driving trajectory and action sequence based on the target lane sequence and dynamic driving constraints. The vehicle's driving trajectory is used to indicate the navigation trajectory, and the vehicle's action sequence is used to indicate the vehicle's motion state on the navigation trajectory.

[0014] Secondly, the present invention also provides a driver assistance device, including a memory and a processor, wherein, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the navigation-assisted driving method based on the standard navigation map described in any of the above implementations.

[0015] Thirdly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instructions, which, when executed by a processor, can implement the steps of the navigation-assisted driving method based on a standard navigation map described in any of the above implementations.

[0016] The beneficial effects of this invention are as follows: The navigation-assisted driving method and device based on standard navigation maps provided by this invention first generate a road-level navigation path based on offline SD Map data and the destination, providing basic data for navigation-assisted driving and ensuring its reliability and accuracy. Then, based on vehicle positioning data, vehicle inertial measurement unit data, vehicle wheel speed sensor data, and road features perceived by the vehicle, the vehicle's pose on the SD Map road is determined, further improving the reliability and accuracy of navigation-assisted driving. Next, a virtual lane is generated based on the road-level navigation path, and then dynamic driving constraints are determined based on the virtual lane and real-time traffic status data to constrain vehicle movement, further improving the accuracy of navigation-assisted driving. Finally, the target lane sequence of the vehicle is determined based on the road-level navigation path, and then the vehicle's driving trajectory and action sequence are determined based on the target lane sequence and dynamic driving constraints, realizing navigation-assisted driving. This invention effectively improves the reliability and accuracy of navigation-assisted driving. Attached Figure Description

[0017] Figure 1 A schematic flowchart of an embodiment of the navigation-assisted driving method based on a standard navigation map provided by the present invention; Figure 2 This is a schematic diagram of an embodiment of the cloud-vehicle interaction process provided by the present invention; Figure 3 A schematic diagram of an embodiment of the navigation map solution framework provided by the present invention; Figure 4 A schematic diagram of an embodiment of the navigation assistance driving device based on a standard navigation map provided by the present invention; Figure 5 This is a schematic diagram of an embodiment of the driver assistance device provided by the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0019] In the description of the embodiments of the present invention, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0020] The terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0021] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0022] This invention provides a navigation-assisted driving method and device based on a standard navigation map, which will be described below.

[0023] Figure 1This is a schematic flowchart of an embodiment of the navigation-assisted driving method based on a standard navigation map provided by the present invention, as shown below. Figure 1 As shown, navigation-assisted driving methods based on standard navigation maps include: S101. Obtain offline SD Map data and destination, and generate a road-level navigation path based on the offline SD Map data and destination.

[0024] It should be noted that the navigation-assisted driving method based on standard navigation maps provided by this invention can be applied to autonomous driving scenarios, especially autonomous driving scenarios on urban roads.

[0025] When performing navigation-assisted driving, the assisted driving device (such as the vehicle's onboard computer or portable computer) can first obtain offline SD Map data and destination, and then generate a road-level navigation route based on the offline SD Map data and destination, providing basic data for navigation-assisted driving and ensuring the reliability and accuracy of navigation-assisted driving.

[0026] S102. Based on vehicle positioning data, vehicle inertial measurement unit data, vehicle wheel speedometer data, and road features perceived by the vehicle, determine the vehicle's pose on the SD Map road.

[0027] It should be noted that after determining the road-level navigation path, the driver assistance device can also determine the vehicle's pose on the SD Map road based on vehicle positioning data, vehicle inertial measurement unit data, vehicle wheel speed sensor data, and road features perceived by the vehicle, further improving the reliability and accuracy of the navigation assistance system.

[0028] S103. Generate virtual lanes based on road-level navigation paths, and determine dynamic driving constraints based on virtual lanes and real-time traffic status data.

[0029] It should be noted that, in order to further improve the accuracy of navigation-assisted driving, virtual lanes can be generated based on road-level navigation paths, and then dynamic driving constraints can be determined based on virtual lanes and real-time traffic status data to constrain vehicle driving.

[0030] S104. Determine the target lane sequence of the vehicle based on the road-level navigation path, and determine the vehicle's driving trajectory and action sequence based on the target lane sequence and dynamic driving constraints. The vehicle's driving trajectory is used to indicate the navigation trajectory, and the vehicle's action sequence is used to indicate the vehicle's motion state on the navigation trajectory.

[0031] It should be noted that: Finally, the target lane sequence of the vehicle (i.e., the lane in which the vehicle travels in chronological order) can be determined first based on the road-level navigation path, and then the vehicle's driving trajectory and action sequence can be determined based on the target lane sequence and dynamic driving constraints to realize the vehicle's navigation-assisted driving.

[0032] In summary, the navigation-assisted driving method based on a standard navigation map provided in this invention first generates a road-level navigation path based on offline SD Map data and the destination, providing basic data for navigation-assisted driving and ensuring its reliability and accuracy. Next, based on vehicle positioning data, vehicle inertial measurement unit data, vehicle wheel speed sensor data, and road features perceived by the vehicle, the vehicle's pose on the SD Map road is determined, further improving the reliability and accuracy of navigation-assisted driving. Then, a virtual lane is generated based on the road-level navigation path, and dynamic driving constraints are determined based on the virtual lane and real-time traffic status data to constrain vehicle movement, further improving the accuracy of navigation-assisted driving. Finally, the target lane sequence of the vehicle is determined based on the road-level navigation path, and the vehicle's trajectory and action sequence are determined based on the target lane sequence and dynamic driving constraints, realizing navigation-assisted driving. This invention effectively improves the reliability and accuracy of navigation-assisted driving.

[0033] In some embodiments of the present invention, the generation of road-level navigation paths based on offline SD Map data and the destination includes: Constructing a map atlas based on offline SD Map data; Based on the map atlas and the destination, the A* algorithm is used to generate road-level navigation paths.

[0034] It should be noted that when generating road-level navigation paths based on offline SD Map data and the destination, a map atlas can first be constructed based on the offline SD Map data, and then the road-level navigation path to the destination can be generated on the map atlas using the A* algorithm.

[0035] In some embodiments of the present invention, determining the vehicle's pose on the SD Map road based on vehicle positioning data, vehicle inertial measurement unit data, vehicle wheel speedometer data, and road features perceived by the vehicle includes: Vehicle positioning data, vehicle inertial measurement unit data, vehicle wheel speed sensor data, and road features perceived by the vehicle are projected onto the SD Map to determine the vehicle's longitudinal mileage, lateral offset, and heading on the SD Map road.

[0036] It should be noted that when determining the vehicle's pose on the SD Map road, the vehicle's positioning data, vehicle inertial measurement unit data, vehicle wheel speed sensor data, and road features perceived by the vehicle can be projected onto the SD Map to determine the vehicle's longitudinal mileage, lateral offset, and heading on the SD Map road, which can then be used as the vehicle's pose on the SD Map road.

[0037] In some embodiments of the present invention, generating virtual lanes based on road-level navigation paths includes: Virtual lanes are generated based on the road topology and road attributes of each road on the road-level navigation path.

[0038] It should be noted that when generating virtual lanes based on road-level navigation paths, virtual lanes can be generated according to the road topology and road attributes of each road on the road-level navigation path.

[0039] In some embodiments of the present invention, determining dynamic driving constraints based on virtual lanes and real-time traffic state data includes: Real-time traffic data is mapped onto the corresponding virtual lanes to determine dynamic driving constraints.

[0040] It should be noted that when determining dynamic driving constraints based on virtual lanes and real-time traffic status data, the real-time traffic status data can be mapped onto the corresponding virtual lanes to determine the dynamic driving constraints.

[0041] In some embodiments of the present invention, determining the target lane sequence of the vehicle based on the road-level navigation path includes: The target lane sequence for the vehicle is determined based on the road-level navigation path and the current vehicle location.

[0042] It should be noted that when determining the target lane sequence of a vehicle based on the road-level navigation path, the lanes that the vehicle will travel in can be arranged in chronological order according to the road-level navigation path and the current vehicle position to determine the target lane sequence of the vehicle.

[0043] In some embodiments of the present invention, determining the vehicle's trajectory and action sequence based on the target lane sequence and dynamic driving constraints includes: The road trajectory of the vehicle is determined based on the target lane sequence and dynamic driving constraints, as well as the vehicle's speed, acceleration, and heading on the road trajectory.

[0044] It should be noted that when determining the vehicle's trajectory and action sequence based on the target lane sequence and dynamic driving constraints, the vehicle's road trajectory can be determined based on the target lane sequence and dynamic driving constraints. Then, the vehicle's speed, acceleration, and heading on the road trajectory can be further determined to achieve precise vehicle navigation.

[0045] This invention proposes a navigation assistance solution based on SD Maps: using standard navigation maps as a foundation, it achieves lane-level navigation assistance without relying on high-precision maps through dynamic semantic enhancement, path-lane mapping, multi-source fusion positioning, intent-driven planning, and layered safety control. The core is to transform SD Map road-level information into lane-level guidance executable by intelligent driving, deeply integrating it with onboard perception, positioning, and decision-making to form a low-cost, highly robust, and easily mass-producible navigation assistance solution.

[0046] Combination Figure 2 The system consists of a cloud-based SD Map service unit, a vehicle-side SD Map engine, a fusion positioning unit, an environmental perception unit, a navigation decision unit, a vehicle control unit, and an HMI interaction unit.

[0047] Cloud-based SD Map service unit: Provides incremental updates and real-time dynamic layers for traffic / events / speed limits / construction.

[0048] Vehicle-side SD Map engine: parses road network topology, generates navigation routes, and extracts road semantics and guidance information.

[0049] Fusion positioning unit: GNSS + IMU + wheel speed + visual / radar feature matching, outputting the vehicle's precise pose in the SD Map.

[0050] Environmental perception unit: Camera / millimeter-wave radar / LiDAR (optional) outputs information on obstacles, lane lines, traffic signs, and drivable areas.

[0051] Navigation Decision Unit: Includes path-lane mapping, intent parsing, behavior decision-making, and trajectory planning.

[0052] Vehicle control unit: performs longitudinal ACC / NOA, lateral LKA / lane change, ramp entry / exit, and intersection turning.

[0053] HMI Interaction Unit: Displays navigation status, guidance prompts, and takeover requests.

[0054] Combination Figure 3 The pilot-assisted driving process specifically includes the following steps: 1. SD Map initialization and path planning.

[0055] Load offline SD Map and synchronize dynamic layers in the cloud; receive the destination, generate road-level navigation path, and extract guidance instructions (straight / left turn / right turn / exit / merge), distance, and road attributes (highway / city / ramp / speed limit); use the navigation map for global planning to plan the optimal route between the destination and the end point through the vehicle-side engine SDK.

[0056] 1) Map modeling: Transform the map into nodes and edges.

[0057] Vertex: Decision points such as intersections, ramps, turning points, and points of interest (POIs).

[0058] Edge: The road between two nodes (one-way / two-way, lane, speed limit, toll).

[0059] Weight (Cost): The cost of passage (time priority, distance priority, high speed priority).

[0060] Time: Length / Predicted speed + Congestion / Traffic lights / Construction / Weather.

[0061] Distance: Actual mileage of the road segment.

[0062] Preferences: Increase the weight of highways, avoid ferries / mountain roads / restricted areas.

[0063] 2) Core algorithm for optimal route (graph theory shortest path).

[0064] Dijkstra's algorithm or A* algorithm.

[0065] Layered road network: High-rise buildings (highways / expressways): rough routes across cities / regions.

[0066] Middle layer (main roads): the framework of the urban area.

[0067] Lower level (side roads / lanes): Detailed guidance near the destination.

[0068] Logic: Start with the general direction and then work your way down to the lower levels to fill in the details.

[0069] 3) Road-level path generation (from coarse to fine).

[0070] Global coarse planning: The starting point / end point is mapped to the road network nodes, and the main corridors are calculated using A* in the high-level road network (highway + expressway).

[0071] Hierarchical refinement (tiered road network): Expressway priority: Expressways / fast roads are selected first, with lower weight; City priority: Main roads > Secondary roads > Local roads; Residential areas / industrial parks: Street-level road networks are used to connect to the destination.

[0072] Lane-level (high-precision map): After the global route is determined, lane-level matching is performed on the corresponding road segment, and the output includes detailed guidance such as which lane, when to change lanes, and ramp entrances.

[0073] Dynamic replanning: real-time congestion / accident - instantaneous recalculation of weights + partial detour.

[0074] 2. Multi-source fusion positioning and map matching.

[0075] Using GNSS coarse positioning as the initial value, IMU / wheel speed are used for recursion; visual / radar extraction of road features (guardrails, signs, intersections) is matched with SD Map to correct pose.

[0076] Output: longitudinal mileage, lateral offset, heading, and matching confidence of the vehicle on the SD Map road.

[0077] The navigation map vehicle engine SDK provides meter-level accuracy, and the vehicle-side perception information is fused from multiple sources, using GNSS, IMU, odometer, and sensors.

[0078] First, unify the coordinate system, then calculate the longitudinal mileage, lateral offset, heading, and matching confidence.

[0079] The matching confidence score is obtained by weighted fusion of four types of information: Geometric matching error: The smaller the vertical distance from the projection point to the vehicle, the higher the confidence level.

[0080] Heading difference: The smaller the difference between the vehicle's heading and the road tangent, the higher the confidence level.

[0081] Observational consistency: The lane lines, road signs, and stop lines seen by the camera are matched with the elements in the SD Map. A large number of matches and small errors indicate high confidence.

[0082] Historical continuity: Whether the longitudinal mileage, lateral offset, and heading changes are smooth in the preceding and following frames. Sudden jumps indicate a decrease in confidence, while continuous stability indicates an increase in confidence.

[0083] 3. SD Map dynamic semantic enhancement.

[0084] Map road-level information to virtual lane-level semantics: number of lanes, direction of travel, no-lane-changing zone, stop line, and intersection area.

[0085] Global navigation is provided through SD Map, and the relevant lane geometry and road topology are derived through localization fusion and perception fusion. SD Map provides prior knowledge for prediction, and perception provides the results for verification.

[0086] From the road-level topology and road attributes of the SD Map, virtual lanes are first geometrically reconstructed, then the number of lanes / direction / no lane change / stop line / intersection are semantically mapped, and finally, real-time traffic is integrated to generate dynamic driving constraints.

[0087] Each virtual lane contains: Geometry: centerline, left and right boundaries, sd coordinate system.

[0088] Static semantics: lane number, direction, number of lanes, no-lane-changing zone, stop line, intersection area.

[0089] Dynamic constraints: real-time speed limit, congestion level, availability, and restricted areas.

[0090] 4. Path-lane mapping and intent parsing.

[0091] Convert the navigation path into a lane-level target sequence: current lane - target lane - exit / turn point.

[0092] Analysis of execution intent: lane change timing, merging / exit strategy, intersection traffic priority.

[0093] 5. Navigation decision-making and trajectory planning.

[0094] The SD Map is used as a hard constraint, while perception is used as a dynamic constraint.

[0095] Hard constraints: SD Map provides meter-level accuracy, which is required for road topology, road edges, and POIs.

[0096] Dynamic constraints: Dynamic adjustments at meter-level accuracy, including lane geometry and road topology within the meter-level accuracy range.

[0097] Generate safe, comfortable, and punctual trajectories and action sequences: following, cruise, lane changing, deceleration, and steering.

[0098] 6. Vehicle control and safety safeguards.

[0099] Longitudinal: Vehicle speed / distance control; Lateral: Lane keeping / lane change control; Safety layer: Minimum safe distance, lateral boundary, manual priority, fault degradation.

[0100] 7. HMI and state closed loop.

[0101] Real-time display: navigation status, remaining distance, next action; advance warning of lane change / exit, and request for takeover in case of anomalies.

[0102] The following are examples of specific application scenarios for pilot-assisted driving: Example 1: High-speed navigation assistance (SD Map + pure vision + millimeter wave).

[0103] 1. Plan the highway route and output the main road / ramp / exit information from SD Map.

[0104] 2. Positioning output: longitudinal mileage and lateral offset.

[0105] 3. The sensor outputs lane lines / vehicles in front / guardrails, and the SD Map engine generates virtual lanes.

[0106] 4. The decision-making level shall provide a lane change prompt 1km in advance as required by the navigation system, and execute the lane change 500m in advance.

[0107] 5. The control layer maintains lane / follow / cruise, and automatically reduces speed on ramps.

[0108] 6. In case of an anomaly, the HMI will prompt for takeover, and the system will be downgraded to LCC.

[0109] Example 2: Navigation assistance for urban roads.

[0110] 1. SD Map outputs intersection turning / lane guidance / no stopping / speed limit.

[0111] 2. Location + visual intersection matching to determine the stop line and passage area.

[0112] 3. Mapped to left turn / right turn / straight lane constraints.

[0113] 4. The decision-makers smoothly navigated the intersection following the traffic lights and guidance-generated trajectories.

[0114] 5. The control layer is precise horizontally and smooth vertically, ensuring safety and traffic efficiency.

[0115] Example 3: Dynamic scenario response (construction / congestion / speed limit).

[0116] 1. The construction area is pushed to the cloud, and the SD Map engine updates the restricted areas.

[0117] 2. The system changes lanes in advance to avoid temporary stops.

[0118] 3. Automatic following in congested areas, cruise control resumes in uncongested areas.

[0119] 4. Speed ​​limits are implemented using SD Map + flag fusion to prevent speeding.

[0120] This invention eliminates the costs of high-precision map acquisition / update / compliance, and the hardware supports pure vision + millimeter wave configuration, significantly reducing costs: SD Map provides full coverage and high availability, with stability in tunnels / elevated roads / complex urban intersections superior to map-free solutions; unified planning for navigation and driving ensures more precise execution of lane changes / ramp / intersections, reducing missed exits; reuse of existing SD Maps in the vehicle's infotainment system allows for rapid iteration, wide coverage, and support for continuous OTA upgrades; and the dual constraints of static topology and dynamic perception reduce the risk of perception failure.

[0121] To better implement the navigation-assisted driving method based on standard navigation maps in this invention embodiment, based on the navigation-assisted driving method based on standard navigation maps, correspondingly, as follows: Figure 4 As shown, this embodiment of the invention also provides a navigation-assisted driving device based on a standard navigation map. The navigation-assisted driving device 400 based on a standard navigation map includes: The acquisition module 401 is used to acquire offline SD Map data and destination, and generate road-level navigation paths based on the offline SD Map data and destination; The first determining module 402 is used to determine the vehicle's pose on the SD Map road based on vehicle positioning data, vehicle inertial measurement unit data, vehicle wheel speedometer data, and road features perceived by the vehicle. The second determining module 403 is used to generate virtual lanes based on road-level navigation paths and determine dynamic driving constraints based on virtual lanes and real-time traffic status data. The third determining module 404 is used to determine the target lane sequence of the vehicle based on the road-level navigation path, and to determine the vehicle's driving trajectory and action sequence based on the target lane sequence and dynamic driving constraints. The vehicle's driving trajectory is used to indicate the navigation trajectory, and the vehicle's action sequence is used to indicate the vehicle's motion state on the navigation trajectory.

[0122] The navigation-assisted driving device 400 based on the standard navigation map provided in the above embodiments can realize the technical solutions described in the above embodiments of the navigation-assisted driving method based on the standard navigation map. The specific implementation principles of each module or unit can be found in the corresponding content in the above embodiments of the navigation-assisted driving method based on the standard navigation map, and will not be repeated here.

[0123] like Figure 5 As shown, the present invention also provides a corresponding driver assistance device 500. The driver assistance device 500 includes a processor 501, a memory 502, and a display 503. Figure 5 Only some components of the driver assistance device 500 are shown; however, it should be understood that implementation of all shown components is not required, and more or fewer components may be implemented instead.

[0124] In some embodiments, processor 501 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 502 or process data, such as the navigation-assisted driving method based on a standard navigation map in this invention.

[0125] In some embodiments, processor 501 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 501 may be local or remote. In some embodiments, processor 501 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-cloud, etc., or any combination thereof.

[0126] In some embodiments, memory 502 may be an internal storage unit of the driver assistance device 500, such as a hard disk or memory of the driver assistance device 500. In other embodiments, memory 502 may also be an external storage device of the driver assistance device 500, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the driver assistance device 500.

[0127] Furthermore, the memory 502 may include both internal storage units of the driver assistance device 500 and external storage devices. The memory 502 is used to store application software and various types of data installed on the driver assistance device 500.

[0128] In some embodiments, display 503 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an organic light-emitting diode (OLED) touchscreen. Display 503 is used to display information from the driver assistance device 500 and to display a visual user interface. Components 501-503 of the driver assistance device 500 communicate with each other via a system bus.

[0129] In one embodiment, when processor 501 executes a navigation-assisted driving program based on a standard navigation map stored in memory 502, the following steps may be performed: Obtain offline SD Map data and destination, and generate road-level navigation routes based on the offline SD Map data and destination; Based on vehicle positioning data, vehicle inertial measurement unit data, vehicle wheel speed measurement data, and road features perceived by the vehicle, the vehicle's pose on the SD Map road is determined. Virtual lanes are generated based on road-level navigation paths, and dynamic driving constraints are determined based on virtual lanes and real-time traffic status data. The target lane sequence of the vehicle is determined based on the road-level navigation path, and the vehicle's driving trajectory and action sequence are determined based on the target lane sequence and dynamic driving constraints. The vehicle's driving trajectory is used to indicate the navigation trajectory, and the vehicle's action sequence is used to indicate the vehicle's motion state on the navigation trajectory.

[0130] It should be understood that when the processor 501 executes the navigation assistance driving program based on the standard navigation map in the memory 502, in addition to the functions mentioned above, it can also perform other functions, as can be found in the description of the corresponding method embodiments above.

[0131] Furthermore, this embodiment of the invention does not specifically limit the type of the assisted driving device 500 mentioned. The assisted driving device 500 can be a portable electronic device such as a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, or laptop computer. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic devices can also be other portable electronic devices, such as laptop computers with touch-sensitive surfaces (e.g., touch panels). It should also be understood that in some other embodiments of the invention, the assisted driving device 500 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0132] Accordingly, this application also provides a computer-readable storage medium for storing a computer-readable program or instruction. When the program or instruction is executed by a processor, it can implement the steps or functions of the navigation-assisted driving method based on a standard navigation map provided in the above-described method embodiments.

[0133] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0134] The above provides a detailed description of the navigation-assisted driving method and device based on standard navigation maps provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A navigation-assisted driving method based on a standard navigation map, characterized in that, include: Obtain offline SD Map data and destination, and generate road-level navigation routes based on the offline SD Map data and destination; Based on vehicle positioning data, vehicle inertial measurement unit data, vehicle wheel speed measurement data, and road features perceived by the vehicle, the vehicle's pose on the SD Map road is determined. Virtual lanes are generated based on road-level navigation paths, and dynamic driving constraints are determined based on virtual lanes and real-time traffic status data. The target lane sequence of the vehicle is determined based on the road-level navigation path, and the vehicle's driving trajectory and action sequence are determined based on the target lane sequence and dynamic driving constraints. The vehicle's driving trajectory is used to indicate the navigation trajectory, and the vehicle's action sequence is used to indicate the vehicle's motion state on the navigation trajectory.

2. The navigation-assisted driving method based on a standard navigation map according to claim 1, characterized in that, The method of generating road-level navigation paths based on offline SD Map data and destination includes: Constructing a map atlas based on offline SD Map data; Based on the map atlas and the destination, the A* algorithm is used to generate road-level navigation paths.

3. The navigation-assisted driving method based on a standard navigation map according to claim 1, characterized in that, The process of determining the vehicle's pose on the SD Map road based on vehicle positioning data, vehicle inertial measurement unit data, vehicle wheel speedometer data, and road features perceived by the vehicle includes: Vehicle positioning data, vehicle inertial measurement unit data, vehicle wheel speed sensor data, and road features perceived by the vehicle are projected onto the SD Map to determine the vehicle's longitudinal mileage, lateral offset, and heading on the SD Map road.

4. The navigation-assisted driving method based on a standard navigation map according to claim 1, characterized in that, The generation of virtual lanes based on road-level navigation paths includes: Virtual lanes are generated based on the road topology and road attributes of each road on the road-level navigation path.

5. The navigation-assisted driving method based on a standard navigation map according to claim 1, characterized in that, The determination of dynamic driving constraints based on virtual lanes and real-time traffic status data includes: Real-time traffic data is mapped onto the corresponding virtual lanes to determine dynamic driving constraints.

6. The navigation-assisted driving method based on a standard navigation map according to claim 1, characterized in that, The determination of the vehicle's target lane sequence based on the road-level navigation path includes: The target lane sequence for the vehicle is determined based on the road-level navigation path and the current vehicle location.

7. The navigation-assisted driving method based on a standard navigation map according to claim 1, characterized in that, The process of determining the vehicle's trajectory and action sequence based on the target lane sequence and dynamic driving constraints includes: The road trajectory of the vehicle is determined based on the target lane sequence and dynamic driving constraints, as well as the vehicle's speed, acceleration, and heading on the road trajectory.

8. A navigation-assisted driving device based on a standard navigation map, characterized in that, include: The acquisition module is used to acquire offline SD Map data and destination, and generate road-level navigation routes based on the offline SD Map data and destination; The first determining module is used to determine the vehicle's pose on the SD Map road based on vehicle positioning data, vehicle inertial measurement unit data, vehicle wheel speedometer data, and road features perceived by the vehicle. The second determining module is used to generate virtual lanes based on road-level navigation paths and determine dynamic driving constraints based on virtual lanes and real-time traffic status data. The third determination module is used to determine the target lane sequence of the vehicle based on the road-level navigation path, and to determine the vehicle's driving trajectory and action sequence based on the target lane sequence and dynamic driving constraints. The vehicle's driving trajectory is used to indicate the navigation trajectory, and the vehicle's action sequence is used to indicate the vehicle's motion state on the navigation trajectory.

9. A driver assistance device, characterized in that, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the navigation-assisted driving method based on a standard navigation map as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the navigation-assisted driving method based on a standard navigation map as described in any one of claims 1 to 7.

Images