A map data processing method, readable storage medium, electronic device and vehicle

Abstract

The application relates to the technical field of route planning, and provides a map data processing method, a readable storage medium, an electronic device and a vehicle. The map data processing method provided by the application comprises the following steps: obtaining high-precision map data of a target road section based on an electronic navigation map and a discrete local high-precision map. The map data processing method provided by the application can guarantee the passability of automatic driving in a complex scene, reduce the data quantity of the high-precision map, reduce the collection and maintenance cost, optimize the timeliness, improve the traffic efficiency and driving safety, and improve the user experience.

Description

Technical Field

[0001] This application relates to the field of route planning technology, and in particular to a map data processing method, a readable storage medium, an electronic device, and a vehicle. Background Technology

[0002] Current autonomous driving solutions primarily utilize maps in two ways: full high-definition map solutions and solutions without high-definition maps. In practical applications, full high-definition maps involve massive amounts of data, incurring high collection and maintenance costs, and struggle to address current issues. This can lead to autonomous driving disengagement or downgrading in areas with such problems, resulting in a degraded user experience. Solutions without high-definition maps, in scenarios such as complex intersections and ramps, may occasionally experience autonomous driving failures, potentially causing traffic accidents, impacting traffic efficiency, and threatening user safety. Summary of the Invention

[0003] This application aims to address the problems in related technologies and proposes a map data processing method, a readable storage medium, an electronic device, and a vehicle.

[0004] The first aspect of this application provides a map data processing method, the method comprising:

[0005] Based on electronic navigation maps, real-time vehicle positioning information, and discrete local high-precision maps, high-precision map data of the target road segment on the current navigation path is determined.

[0006] In some optional implementations, the electronic navigation map includes: an electronic navigation route; and high-precision map data for determining the target road segment on the current navigation route based on the electronic navigation map, real-time vehicle positioning information, and discrete local high-precision maps, including:

[0007] Based on the electronic navigation map, the real-time vehicle positioning information, and the discrete local high-precision map, a high-precision navigation path and a high-precision positioning result are obtained.

[0008] Based on the high-precision navigation path and the high-precision positioning result, the high-precision map data of the target road segment is obtained.

[0009] In some optional implementations, the electronic navigation map includes: an electronic navigation path; the step of obtaining a high-precision navigation path and a high-precision positioning result based on the electronic navigation map, the vehicle's real-time positioning information, and the discrete local high-precision map includes:

[0010] Based on the electronic navigation path and the high-precision map coordinate system, the high-precision navigation path is obtained, wherein the high-precision map coordinate system is the coordinate system in which the discrete local high-precision map is located;

[0011] The high-precision positioning result is obtained based on the real-time vehicle positioning information and the discrete local high-precision map.

[0012] In some optional implementations, a high-precision navigation path is obtained based on the electronic navigation path and the high-precision map coordinate system, including: matching and mapping the electronic navigation path to the high-precision map coordinate system to obtain a high-precision navigation path corresponding to the vehicle's real-time positioning information.

[0013] In some optional implementations, the electronic navigation path matching is mapped to a high-precision map coordinate system to obtain a high-precision navigation path corresponding to the vehicle's real-time positioning information, including:

[0014] The electronic navigation path is mapped to the high-precision map coordinate system to obtain multiple high-precision simulated road segments;

[0015] The high-precision simulation segment that best matches the optimization objective is selected from multiple high-precision simulation segments to obtain the high-precision navigation path.

[0016] In some optional implementations, the electronic navigation path is mapped to the high-precision map coordinate system to obtain multiple high-precision projected road segments, including:

[0017] Using real-time vehicle location information as the observation value and electronic navigation path and high-precision map path as the basis for state transition, the correspondence between electronic navigation path and high-precision map path is probabilistically extrapolated to obtain multiple high-precision extrapolated road segments.

[0018] In some alternative implementations, the optimization objective includes at least one of the following: minimum spatial distance, optimal topological continuity, and most consistent driving direction.

[0019] In some optional implementations, the high-precision map data for determining the target road segment on the current navigation path is determined based on electronic navigation maps, real-time vehicle positioning information, and discrete local high-precision maps, and further includes:

[0020] If a discrete local high-precision map exists on the current navigation path, then based on the electronic navigation map, real-time vehicle positioning information, and the discrete local high-precision map, the high-precision map data of the target road segment is obtained, and the high-precision map data is used as the map data of the target road segment.

[0021] Alternatively, if no discrete local high-precision map exists on the current navigation path, the electronic navigation map will be used as the map data for the target road segment.

[0022] In some alternative implementations, the electronic navigation map includes an electronic navigation route, and the current navigation route is obtained by using the electronic navigation route and the vehicle's real-time positioning information.

[0023] In some alternative implementations, the processing method further includes:

[0024] Based on high-precision map data and electronic navigation maps, a high-precision map of the target is obtained; the high-precision map of the target is then sent to the autonomous driving system.

[0025] In some optional implementations, the high-precision map data includes high-precision road segments, and the electronic navigation map includes electronic road segments; based on the high-precision map data and the electronic navigation map, a target high-precision map is obtained, including:

[0026] By stitching together the high-precision road segments that overlap in geographic space with the electronic road segments, a high-precision map of the target is obtained.

[0027] In some alternative implementations, high-precision road segments that overlap geographically are stitched together with electronic road segments to obtain a target high-precision map, including:

[0028] When the electronic navigation map is switched to high-precision map data, the subsequent roads of the geographically overlapping high-precision road segments are stitched together with the preceding roads of the electronic road segments to obtain the target high-precision map.

[0029] Alternatively, when high-precision map data is switched to electronic navigation map, the preceding road of the geographically overlapping high-precision road segment is stitched together with the subsequent road of the electronic road segment to obtain the target high-precision map.

[0030] A second aspect of this application provides a computer-readable storage medium including a computer program that, when run on a computer device, causes the computer device to perform the map data processing method described above.

[0031] A third aspect of this application provides an electronic device, comprising:

[0032] A memory on which computer programs are stored;

[0033] A processor is used to execute a computer program in memory to implement the map data processing method described above.

[0034] A fourth aspect of this application provides a vehicle, the vehicle comprising:

[0035] As described in the electronic device;

[0036] Alternatively, a processor may be used to execute the map data processing method described above.

[0037] In summary, this application can achieve at least the following technical effects:

[0038] The map data processing method of this application, based on electronic navigation maps, real-time vehicle positioning information, and discrete local high-precision maps, determines the high-precision map data of the target road segment on the current navigation path. On the basis of the electronic navigation map, the electronic navigation map of the target road segment on the current navigation path is combined with the discrete local high-precision map according to the requirements to obtain high-precision map data. This method can ensure the passability of autonomous driving in complex scenarios, reduce the amount of high-precision map data, thereby reducing the cost of data collection and maintenance, optimizing timeliness, improving traffic efficiency and driving safety, and enhancing user experience. Attached Figure Description

[0039] Figure 1 This is the flowchart of the map data processing method in Embodiment 1 of this application. Figure 1 ;

[0040] Figure 2 This is the flowchart of the map data processing method in Embodiment 1 of this application. Figure 2 ;

[0041] Figure 3 This is a schematic diagram of the navigation path in Embodiment 1 of this application. Detailed Implementation

[0042] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0043] In the description of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0044] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0045] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "joining," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0046] In this application, unless otherwise expressly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "on top of," and "over" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0047] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0048] Example 1:

[0049] Embodiment 1 of this application provides a map data processing method, such as... Figure 1 As shown, the method includes:

[0050] Based on electronic navigation maps, real-time vehicle positioning information, and discrete local high-precision maps, high-precision map data of the target road segment on the current navigation path is determined.

[0051] The system first receives a pre-planned electronic navigation map. An electronic navigation map is a digitally stored and displayed map designed to provide users with geographic information and navigation services. It uses the Global Positioning System (GPS) and other satellite positioning systems to determine the user's location and provides functions such as route planning, direction guidance, and distance calculation to help users get from one location to another. Electronic navigation maps typically include road networks, traffic flow, points of interest (POIs), public transportation information, and can adjust the data source according to real-time conditions. Source matching refers to spatially aligning, associating roads, and registering coordinates between electronic navigation maps from different sources, with varying accuracy and data formats, and discrete local high-precision maps, under a unified geospatial reference system, thus establishing a correspondence between map data from different sources.

[0052] Discrete local high-precision maps include at least one of traditional / centralized high-precision maps and crowdsourced high-precision maps. Traditional / centralized high-precision maps are specifically designed for autonomous vehicles and other applications requiring highly accurate location information. Compared to traditional navigation maps, high-precision maps provide more detailed and accurate information, including but not limited to road shapes, lane positions, traffic lights, signs, intersection details, and the three-dimensional structure of the surrounding environment. Crowdsourced high-precision maps rely on a massive number of terminal devices such as autonomous vehicles, ordinary vehicle terminals, and mobile devices as data collection nodes. During vehicle operation, they collect real-time environmental perception data (including but not limited to high-precision map elements such as lane lines, traffic signs, guardrails, intersection topology, and road geometric features), and upload the collected data to a cloud server for fusion, verification, correction, and updating, ultimately forming a lane-level high-precision electronic map. Real-time vehicle positioning information is output in real-time and has lower accuracy, posing a risk of drifting in urban canyons or under overpasses.

[0053] The discrete local high-precision map data for the target road segment is pre-collected and maintained, covering major complex intersections and their surrounding areas within a preset range (e.g., 50-200m), and is non-global and discontinuous. Based on electronic navigation maps and discrete local high-precision maps, the high-precision map data for the target road segment is obtained. Specifically, based on the electronic navigation map, for preset complex intersections (preset road segments, demand road segments, complex road segments) and demand road segments prone to autonomous driving failures, the electronic navigation map of the target road segment is combined with the corresponding discrete local high-precision map to obtain the high-precision map data for the target road segment. This solution significantly reduces the amount of high-precision map data by maintaining only local discrete high-precision maps of complex scenarios, rather than a global, full-network high-precision map. This reduces collection and maintenance costs, optimizes map timeliness, and ensures the passability of autonomous driving in complex scenarios, improving traffic efficiency and driving safety, and enhancing the user experience.

[0054] By constructing a "point-based high-precision data island" mechanism, discrete local high-precision maps are deployed only in complex scenarios such as intersections of urban main roads, merging areas of highway ramps, and tunnel entrances and exits. The coverage area is limited to a preset distance (e.g., 50-200m) before and after the navigation path, forming local high-precision data blocks. This avoids the redundant storage and update overhead of a full-network high-precision map, greatly reducing storage costs. At the same time, the map update cycle can be shortened from monthly to hourly, significantly improving timeliness. This method ensures the perception and decision-making capabilities of key bottleneck areas without relying on full-domain high-precision coverage, solving the path misjudgment and safety risks caused by the lack of lane-level semantics in complex intersections of purely electronic navigation maps.

[0055] Current relevance refers to the ability of maps or geographic databases to reflect the most up-to-date geospatial information possible. With frequent changes in urban structures, landforms, and features, topographic maps or geographic data need to be updated and revised regularly to ensure their timeliness. This ensures that maps or geographic data accurately reflect changes in the real world, thereby improving their usability and accuracy.

[0056] In some alternative implementations, such as Figure 2 As shown, based on electronic navigation maps, real-time vehicle positioning information, and discrete local high-precision maps, the high-precision map data for determining the target road segment on the current navigation path includes:

[0057] Based on electronic navigation maps, real-time vehicle positioning information, and discrete local high-precision maps, high-precision navigation paths and high-precision positioning results are obtained.

[0058] Based on the high-precision navigation path and high-precision positioning results, high-precision map data of the target road segment is obtained.

[0059] High-precision navigation paths are semantically enhanced versions of electronic navigation paths in a high-precision map coordinate system, and may include at least one structured piece of information such as lane-level topology, traffic sign locations, traffic light status, and curb curvature. High-precision positioning results are high-precision positioning information intervals for vehicles in a discrete local high-precision map coordinate system, with the high-precision positioning information intervals being at least at the centimeter level.

[0060] The high-precision navigation path and high-precision positioning results work together to form a dual verification mechanism: the high-precision navigation path provides path semantics, and the high-precision positioning results provide real-time spatial alignment. The fused output "target road segment high-precision map data" provides the autonomous driving system with a local environment model that can be directly used for behavioral decisions. For example, when the vehicle approaches an intersection, the system outputs a high-precision data block containing the lane line types of each branch, stop line positions, pedestrian crossing markings, and traffic light phase cycles. This allows the path planning module to identify the differences between left-turn lanes and straight-ahead mixed lanes, avoiding the mistaken entry into the wrong lane due to relying solely on the "left turn" command.

[0061] In some optional implementations, the electronic navigation map includes: an electronic navigation path; and, based on the electronic navigation map, real-time vehicle positioning information, and discrete local high-precision maps, obtaining a high-precision navigation path and high-precision positioning results, including:

[0062] Based on the electronic navigation path and the high-precision map coordinate system, the high-precision navigation path is obtained. The high-precision map coordinate system is the coordinate system of the discrete local high-precision map.

[0063] High-precision positioning results are obtained based on real-time vehicle location information and discrete local high-precision maps.

[0064] Electronic navigation routes can include high-level semantics such as road numbers, turning instructions, and estimated arrival time.

[0065] Electronic navigation routes, real-time vehicle positioning information, and discrete local high-precision mapping Figure 3 After the user inputs the information, the system first projects the electronic navigation path onto the coordinate system of the discrete local high-precision map, and then uses a heterogeneous matching algorithm to select the high-precision navigation path that matches the navigation path in geographic space.

[0066] High-precision positioning results are obtained based on real-time vehicle location information and high-precision map paths.

[0067] High-precision positioning results are centimeter-level positioning information intervals for vehicles in a discrete local high-precision map coordinate system, which can be achieved through point cloud matching and lane line feature matching. Specifically, environmental features (such as lane lines, curbs, and traffic signs) collected by onboard LiDAR or cameras are iteratively matched with the nearest point in a pre-stored feature library in the discrete local high-precision map. Combined with the high-precision map path, the positioning results are corrected to obtain high-precision positioning results. For example, when a vehicle reaches a tunnel entrance where GNSS signals are lost, the system relies on matching the pre-stored 3D coordinates of lane lines within the tunnel in the high-precision map with visually extracted lane lines to output a high-precision positioning result with a positioning error of <0.15 meters, ensuring that the autonomous driving system can still operate stably in environments without satellite signals.

[0068] Based on the determined high-precision navigation path (e.g., H1, H2, H3, H4, H5) and the real-time output of the original positioning signal (real-time vehicle positioning information), positioning matching calculations are performed on the high-precision map.

[0069] Because the original vehicle positioning signal has a certain degree of drift and error, direct matching in the full-domain high-precision map can easily position the vehicle in non-driving lanes, adjacent lanes, oncoming lanes, or auxiliary roads—areas outside the navigation path—causing the positioning result to deviate from the actual driving trajectory. Simultaneously, full-domain search matching expands the positioning calculation range, increasing the system's computational load and reducing positioning efficiency and real-time performance. However, by using the high-precision navigation path as a positioning constraint, the positioning matching range is strictly limited to the refined road segments H1, H2, H3, H4, and H5 within the high-precision navigation path and their corresponding lanes. Position matching and optimization calculations are only allowed within the planned driving path range, excluding invalid matching areas outside the navigation path, suppressing positioning drift and abnormal jumps, and thus obtaining high-precision positioning results with lane-level accuracy, high stability, and high reliability on the high-precision map.

[0070] In some optional implementations, a high-precision navigation path is obtained based on the electronic navigation path and the high-precision map coordinate system, including: matching and mapping the electronic navigation path to the high-precision map coordinate system to obtain a high-precision navigation path corresponding to the vehicle's real-time positioning information.

[0071] This mapping process involves semantically enhanced path resampling and topology alignment. The low density of electronic navigation path points fails to meet lane-level control requirements. By initiating the process before the vehicle enters a high-precision coverage area, the electronic navigation path is matched and mapped to the high-precision map coordinate system, resulting in high-density path points. This facilitates the switch from the electronic navigation path to the high-precision navigation path, ensuring that the path remapping is completed before entering complex nodes and avoiding decision-making delays.

[0072] In some optional implementations, the electronic navigation path matching is mapped to a high-precision map coordinate system to obtain a high-precision navigation path corresponding to the vehicle's real-time positioning information, including:

[0073] The electronic navigation path is mapped to the high-precision map coordinate system to obtain multiple high-precision simulated road segments;

[0074] The high-precision simulation segment that best matches the optimization objective is selected from multiple high-precision simulation segments to obtain the high-precision navigation path.

[0075] The electronic navigation path is mapped to a high-precision map coordinate system to obtain multiple high-precision simulated road segments. Then, a probabilistic statistical model is used to match the high-precision simulated road segments with the optimization target to obtain the matching probability of multiple high-precision simulated road segments. Finally, a path planning algorithm is used to select the optimal road segment and use the optimal road segment as the high-precision navigation path, thereby improving the accuracy of navigation.

[0076] For example, when the navigation path indicates "turn left in 300 meters", the system searches for all possible left-turn lane combinations within a 50-meter range before and after the location in the discrete local high-precision map, maps them to the high-precision map coordinate system to form a set of candidate paths, matches the high-precision map paths of the candidate paths with the optimization target through a probabilistic statistical model, obtains the matching probability of multiple high-precision inferred road segments, and then selects the road segment with the best matching probability as the high-precision navigation path through the path planning algorithm.

[0077] In some alternative implementations, the probabilistic statistical model includes: a Hidden Markov Model; and / or, the path planning algorithm includes: the A* algorithm, the DijkstrA* algorithm.

[0078] A Hidden Markov Model (HMM) is a statistical model used to analyze time series data. It describes a doubly stochastic process: the system contains a sequence of unobservable "hidden" states that follow Markov properties, and each hidden state generates an observable output. The core value of this model lies in its ability to infer the unobservable hidden state sequence from the visible observation sequence, or to assess the probability that the observed sequence was generated by a specific model.

[0079] The HMM is implemented using a forward-backward algorithm to calculate the probability of the state sequence, and its state transition matrix is ​​obtained by training with historical traffic flow data.

[0080] The A* algorithm is a heuristic search algorithm primarily used to find the shortest path from a starting point to an ending point in a graph. It is widely used in path planning, game AI, and navigation systems. Dijkstra's algorithm solves the single-source shortest path problem in a graph with non-negative weights, employing a greedy strategy to progressively determine the shortest paths from the starting point to all other vertices.

[0081] The path planning algorithm preferably adopts the A* algorithm, which can converge quickly under the guidance of a heuristic function and is suitable for vehicle real-time requirements (<200ms). During the system resource redundancy or offline training phase, the DijkstrA* algorithm can be switched to verify the optimality of the entire path.

[0082] The probabilistic statistical model is implemented using Hidden Markov Models (HMMs). Its state space consists of all possible lane segments in a discrete local high-precision map, with the observed values ​​being the two-dimensional coordinates and heading angles of the vehicle's real-time positioning information. Specifically, the HMM's transmission probability can be jointly modeled by the positioning error distribution (e.g., Gaussian distribution, with the mean being the current positioning point and the covariance dynamically calculated by the IMU drift model) and the lane geometric matching degree of the high-precision map (e.g., lane centerline distance, curvature difference). The HMM's state transition probability is driven by the semantic instructions of the electronic navigation path, such as "going straight" corresponding to continuation in the same lane, and "turning left" corresponding to transition to the adjacent left-hand lane. Within each sampling period, the system calculates the posterior probability of all possible lane sequences based on the current observations and historical state sequences, outputting the high-precision inferred road segment. For example, at a four-lane intersection, multiple candidate paths such as "going straight, second lane from the left," "turning left, first lane from the left," and "turning left, first lane from the right" can be inferred.

[0083] Subsequently, the A* algorithm uses highly precise projected road segments as nodes and spatial distance, topological continuity, and consistency of driving direction as cost functions to search for the optimal path. The heuristic function of the A* algorithm can be a weighted sum of Euclidean distance and the expected heading of the navigation path to ensure search efficiency and semantic rationality.

[0084] A combination of Hidden Markov Models (HMMs) and the A* algorithm is used to match and associate electronic navigation paths with discrete local high-precision maps. Since the data sources, road segmentation granularity, and road numbering systems of the electronic navigation map and the discrete local high-precision map are independent, they cannot be directly mapped one-to-one using road numbers or simple coordinates. Therefore, cross-map matching is achieved by fusing positioning information and path topology information.

[0085] like Figure 3 As shown, taking an electronic navigation route as an example, the high-precision map route mapping and switching method is as follows: This route includes four roads that the vehicle passes through in sequence according to the driving order, denoted as Electronic Navigation Route 1 L1, Electronic Navigation Route 2 L2, Electronic Navigation Route 3 L3, and Electronic Navigation Route 4 L4. These four roads pass through a complex intersection J1 covered by a discrete local high-precision map in the driving direction. It is understandable that because the electronic navigation map divides road segments according to the overall road, it does not finely divide the driving sections inside the complex intersection, while the high-precision map divides road segments according to lane-level fine segment division, dividing the complex intersection entry section, the driving section inside the intersection, the intersection exit section, and the turning transition section into independent road segments. Therefore, the electronic navigation route and the high-precision map route are not completely consistent in terms of the number of road segments and the length of road segments.

[0086] During the matching process, a Hidden Markov Model (HMM) is first used, with vehicle positioning information as observations. The spatial positional relationship, topological connectivity, and consistency of driving direction between the electronic navigation path and the high-precision navigation path are used as the basis for state transitions. The correspondence between the electronic navigation path and the high-precision navigation path is probabilistically deduced to obtain the matching probability of different road segment combinations, thus completing a coarse matching. Based on this, the A* algorithm is combined, with the optimization objectives of minimizing spatial distance, optimizing topological continuity, and maximizing driving direction consistency, to solve for the optimal path sequence that best fits the overall electronic navigation path among all traversable road segments on the high-precision map, eliminating redundant road segments with low matching probability, topological discontinuities, and inconsistent directions.

[0087] Through the above joint matching method, the refined high-precision navigation routes that overlap geographically, have the same driving direction, and correspond to each other in road topology with electronic navigation routes 1 L1, 2 L2, 3 L3, and 4 L4 are finally determined in the high-precision map. These routes are high-precision navigation routes 1 H1, 2 H2, 3 H3, 4 H4, and 5 H5. This sequence of road segments constitutes the high-precision navigation route corresponding to the vehicle within the complex intersection J1 range.

[0088] In some alternative implementations, the electronic navigation path is mapped to a high-precision map coordinate system to obtain multiple high-precision projected road segments, including:

[0089] Using real-time vehicle location information as the observation value and electronic navigation path and high-precision map path as the basis for state transition, the correspondence between electronic navigation path and high-precision map path is probabilistically deduced to obtain the matching probability of multiple high-precision deduced road segments.

[0090] The high-precision map path is a topological graph in a discrete local high-precision map, using real-time vehicle positioning information as observations. Each path includes attributes such as lane ID, curvature, gradient, speed limit, and traffic sign ID. The state transition of the probabilistic statistical model relies not only on the semantic instructions of the electronic navigation path (such as "turn right in 200 meters"), but also on the physical accessibility of the high-precision map path, improving the map's accuracy and effectively suppressing "wrong lane" misjudgments caused by positioning drift.

[0091] For example, when the navigation command is "turn right", but the current lane is the leftmost straight lane and there is no dedicated right-turn lane on the right, the HMM sets the transition probability of the transition path to an extremely low value (e.g., <0.01) to avoid mismatches.

[0092] In some alternative implementations, a high-precision navigation path is obtained by selecting the optimal route from multiple high-precision simulated route segments using a route planning algorithm, including:

[0093] By using a path planning algorithm, the optimal route segment among multiple high-precision simulated route segments is selected based on the optimization objective, thus obtaining a high-precision navigation route.

[0094] The path planning algorithm in the system can be run in a graph search manner. Nodes are the endpoints of the high-precision road segments, and edges are the lanes that can be crossed (such as going straight, changing lanes, and turning left). This allows the algorithm to adjust and optimize the target in different scenarios, and then select the optimal road segment according to the needs, thereby further improving the accuracy of navigation.

[0095] In some alternative implementations, the optimization objective includes at least one of the following: minimum spatial distance, optimal topological continuity, and most consistent driving direction.

[0096] Spatial distance refers to the path of the high-precision simulation segment. The minimum spatial distance is the high-precision simulation segment with the smallest path among multiple high-precision simulation segments as the basic target. When there is no topological conflict, the minimum spatial distance is given priority, but it can be sacrificed under safety constraints.

[0097] Optimal topological continuity means that the lane line type, number of lanes (number of lane changes), and traffic signs remain unchanged in the high-precision navigation path. For example, if the electronic navigation path indicates "enter the main road", but the high-precision map shows that the road segment is "three lanes turning into two lanes", then the path that retains continuous lane lines without breaks will be selected instead of the "virtual lane" where the lane lines suddenly disappear.

[0098] The most consistent driving direction means that the deviation between the path heading and the navigation command heading is minimal. In the scenario of highway ramp exit, if the electronic navigation prompts "right turn exit", but there are two right turn exits in the high-precision map (one is a 90° sharp bend and the other is a 30° gentle bend), the system will prioritize the gentle bend exit with less heading change, reduce the vehicle's yaw rate, and improve ride comfort and safety.

[0099] The cost function constructed based on the optimization objective can be: fn = gn + hn, where gn is the cumulative cost from the starting point to the current node, which is a weighted sum of spatial distance (meters), the number of topological breaks (such as lane line disappearances), and directional deviation (degrees); hn is the heuristic function, which uses the Euclidean distance to the straight-line distance to the end point of the navigation path. The system dynamically adjusts the weights during the search process: when a vehicle enters a complex intersection (such as a roundabout or an intersection without traffic lights), the topological continuity weight is increased to 0.5, and the spatial distance weight is reduced to 0.3, ensuring that semantic integrity of the path takes precedence over the shortest path.

[0100] In some optional implementations, the high-precision map data for determining the target road segment on the current navigation path is determined based on electronic navigation maps, real-time vehicle positioning information, and discrete local high-precision maps, and further includes:

[0101] If a discrete local high-precision map exists on the current navigation path, then based on the electronic navigation map, real-time vehicle positioning information, and the discrete local high-precision map, the high-precision map data of the target road segment is obtained, and the high-precision map data is used as the map data of the target road segment.

[0102] This ensures that a discrete local high-precision map exists for the current navigation path before performing matching and switching operations, avoiding system lag, further improving traffic efficiency and driving safety, and saving map data transmission traffic.

[0103] In some optional implementations, the high-precision map data for determining the target road segment on the current navigation path is determined based on electronic navigation maps, real-time vehicle positioning information, and discrete local high-precision maps, and further includes:

[0104] If no discrete local high-precision map exists on the current navigation path, the electronic navigation map will be used as the map data for the target road segment.

[0105] Even when there is no discrete local high-precision map for the current navigation route, the electronic navigation map will still be used as the map data for the target road segment to ensure that the basic map data can maintain the navigation function.

[0106] In some alternative implementations, the electronic navigation map includes an electronic navigation route, and the current navigation route is obtained by using the electronic navigation route and the vehicle's real-time positioning information.

[0107] By integrating satellite positioning (such as GPS) to obtain real-time vehicle location information, electronic map data, and real-time traffic information, electronic navigation routes can be obtained, enabling dynamic route calculation and guidance, accurate positioning and real-time route updates, intelligent route planning and dynamic recalculation, which can significantly improve driving safety and experience.

[0108] The current navigation path is not a statically planned result, but a dynamically corrected real-time path. The system uses the electronic navigation path as an initial reference, combining real-time vehicle positioning information (longitude, latitude, heading, and speed) with short-term predictions from inertial navigation to calculate the vehicle's current projection point on the navigation path (i.e., the "nearest path point") and a local path segment consisting of several points ahead of it. When the vehicle deviates laterally due to crosswinds, road slope, or tire slippage, the positioning module detects that the vehicle's actual position has deviated from the navigation path. The system feeds this deviation back to the path generation module, fusing the positioning error with the path curvature change rate to perform local smoothing corrections to the electronic navigation path, generating a "current navigation path" that more closely resembles the vehicle's actual driving trajectory. This path retains the semantic attributes of the original navigation path (e.g., "roundabout ahead"), but its geometry more closely matches real tire tracks, improving the accuracy of HMM observations during subsequent high-precision map matching. This correction process operates independently of the navigation system, only reading its output path point sequence, achieving architectural decoupling. In high-speed cruising scenarios, this mechanism ensures that the vehicle always travels along the "optimal rut," reducing unnecessary lane changes and steering maneuvers, and improving ride comfort and energy efficiency.

[0109] In some alternative implementations, the processing method further includes:

[0110] Based on high-precision map data and electronic navigation maps, a high-precision map of the target is obtained; the high-precision map of the target is then sent to the autonomous driving system.

[0111] The target high-definition map is a fused hybrid map, and its data format may include lane-level semantics, dynamic obstacle prediction, and traffic rule constraints. High-definition map data and electronic navigation data... Figure 2 After fusion, the system uses the vehicle's real-time location as a reference, extracts a certain range along the current navigation path, and generates a high-precision map of the target area in a unified coordinate system. This high-precision map data within that range is then broadcast to the autonomous driving perception, planning, and control modules. This enables on-demand, localized, and dynamic broadcasting of high-precision map data, achieving real-time stitching and transmission of electronic navigation maps and discrete local high-precision maps. The system is logically simple, robust, timely, and has low maintenance costs. For example, during high-speed driving, the system uses the electronic navigation path in areas without high-precision data, automatically switching to high-precision map data 100 meters before entering a complex overpass, achieving a seamless transition.

[0112] In practice, as mentioned earlier, the target high-precision map sent to the autonomous driving system can vary depending on the type of high-precision map. For example, the geometric absolute accuracy of the high-precision map may be reduced from 20cm to 100cm. As the perception and model capabilities of autonomous driving improve, certain elements of the high-precision map can be removed accordingly, such as stop lines at intersections and ground directional arrows.

[0113] As the vehicle enters the coverage area of ​​the high-precision map, following the steps described above, local high-precision map data of the navigation path ahead of the vehicle is sent. The high-precision map does not need to be continuous; it only needs to cover the area where autonomous driving fails.

[0114] In some optional implementations, the high-precision map data includes high-precision road segments, and the electronic navigation map includes electronic road segments; based on the high-precision map data and the electronic navigation map, a target high-precision map is obtained, including:

[0115] By stitching together the high-precision road segments that overlap in geographic space with the electronic road segments, a high-precision map of the target is obtained.

[0116] The stitching operation is performed in a spatial coordinate system, and absolute coordinate alignment based on RTK-GNSS can be used. Areas where the high-precision road segment and the electronic road segment overlap geographically (e.g., error <1 meter) are identified as "overlapping areas". Lane lines, traffic signs, and speed limit information of the high-precision road segment are overlaid onto the corresponding locations of the electronic road segment to form an enhanced road model. For example, a road segment in the electronic navigation map is only labeled "urban road", while the high-precision map shows that the road segment includes "two-way four lanes, bus lane on the left, non-motorized vehicle lane on the right, speed limit 50km / h, and pedestrian crossing signal lights". After stitching, the target high-precision map completely retains these semantics, enabling the autonomous driving system to perform refined decisions such as "avoiding buses" and "yielding to pedestrians".

[0117] In some alternative implementations, high-precision road segments that overlap geographically are stitched together with electronic road segments to obtain a target high-precision map, including:

[0118] When the electronic navigation map is switched to high-precision map data, the subsequent roads of the geographically overlapping high-precision road segments are stitched together with the preceding roads of the electronic road segments to obtain the target high-precision map.

[0119] This scenario applies to the "entry" of high-precision map data. When a vehicle approaches an area where high-precision data has been deployed (e.g., a complex intersection 300 meters ahead), the system triggers the loading of high-precision map data 10 seconds in advance. At this time, the preceding road segment of the electronic road segment (the road segment the vehicle is currently on) and the entrance road segment of the high-precision road segment spatially overlap. Specifically, the stitching operation connects the subsequent roads of the high-precision road segment (i.e., the branch lanes within the intersection) with the preceding road segment of the electronic road segment (the current straight lane) to form a continuous path. This ensures that the path planning module has pre-loaded the complete path before entering the complex scene area, avoiding decision interruption due to data switching delays and improving the user experience.

[0120] In some alternative implementations, high-precision road segments that overlap geographically are stitched together with electronic road segments to obtain a target high-precision map, including:

[0121] When high-precision map data is switched to electronic navigation map, the preceding road of the geographically overlapping high-precision road segment is stitched together with the subsequent road of the electronic road segment to obtain the target high-precision map.

[0122] This scenario applies to the "exit" of high-precision map data. When a vehicle leaves a complex intersection and enters a regular road section without high-precision data, the system triggers a switch at the exit of the high-precision road section (e.g., 200 meters after an intersection). At this point, the "preceding road" (i.e., the exit lane at the intersection) of the high-precision map and the "following road" (the straight section of the main road) of the electronic navigation spatially overlap. The stitching operation extends the topology of the exit lane of the high-precision road section to the subsequent path of the electronic navigation, ensuring path continuity and avoiding the system's misjudgment of "path termination" due to high-precision data disconnection. This ensures a smooth transition in the high-precision data boundary area, prevents the autonomous driving system from experiencing path jitter or emergency braking due to map switching, improves the safety of autonomous driving, and enhances the user experience.

[0123] During vehicle operation, the system employs an adaptive switching strategy for positioning results: When the vehicle is within the coverage area of ​​a discrete local high-precision map, such as a complex intersection (J1), and a stable and reliable high-precision positioning result can be obtained based on the high-precision navigation path, the system prioritizes using this high-precision positioning result. This provides accurate location support for the autonomous driving decision-making, planning, and control modules, ensuring the safety and maneuverability of autonomous driving in complex scenarios. When the vehicle leaves the high-precision map coverage area and the corresponding high-precision positioning matching result cannot be obtained, the system automatically switches the positioning mode to use the conventional positioning result obtained based on the electronic navigation map. This ensures continuous and uninterrupted vehicle positioning service, reducing the system's computational resource consumption on ordinary road sections while maintaining positioning accuracy.

[0124] The specific splicing logic is as follows:

[0125] When a vehicle travels along a navigation path from a segment on the electronic navigation map into a complex segment covered by a discrete local high-precision map, the electronic navigation path L1 in the electronic navigation map, which is adjacent to the complex path area, and the high-precision navigation path H1 in the high-precision map data overlap and cover each other geographically. At this time, the electronic navigation path L1 in the electronic navigation map is truncated, and / or the high-precision navigation path H1 in the high-precision map data is truncated, so that the end point of the electronic navigation path L1 is completely aligned with the starting point of the high-precision navigation path H1 in the high-precision map in space. The subsequent road of the electronic navigation path L1 in the electronic navigation map is modified to the high-precision navigation path H1, and the preceding road of the high-precision navigation path H1 is modified to the electronic navigation path L1 in the electronic navigation map, so as to achieve a smooth connection between the electronic navigation map and the high-precision map.

[0126] When a vehicle leaves a complex road segment covered by a discrete local high-precision map along the navigation path and returns to a road segment on the electronic navigation map, the high-precision navigation path five (the last road segment) H5 on the high-precision map overlaps with the adjacent electronic navigation path four L4 on the electronic navigation map in geographic space. At this time, the electronic navigation path four L4 on the electronic navigation map is truncated to make the starting point of electronic navigation path four L4 and the ending point of high-precision navigation path five H5 completely aligned in space. The preceding road of electronic navigation path four L4 is modified to the high-precision map road segment H2, and the following road of high-precision navigation path five H5 is modified to electronic navigation path four L4, thus achieving a smooth connection from the high-precision map to the electronic navigation map.

[0127] By employing the aforementioned road segmentation, spatial alignment, and correlation replacement of preceding and subsequent roads, the electronic navigation map and discrete local high-precision maps are merged into a complete, continuous, and seamless map, which is then uniformly broadcast to the autonomous driving system. For example, in an autonomous driving path with a total length of 100km, 95km consists of straight sections and simple path scenarios, while 5km involves complex intersections. The 95km straight sections and simple path scenarios can rely solely on the electronic navigation map, while the 5km complex intersections utilize a high-precision map. At this point, when the simple path approaches a complex intersection, or when the complex intersection marks the end of the preceding road of the simple path, the target high-precision map is sent to the autonomous driving system to improve its maneuverability at complex intersections.

[0128] For example, the steps of a map data processing method are as follows:

[0129] Step S201: Receive the electronic navigation path and real-time vehicle positioning information, and perform heterogeneous matching based on these information. Heterogeneous matching refers to spatially aligning, associating roads, and registering coordinates between electronic navigation maps of different sources, with varying accuracy and data formats, and discrete local high-precision maps, under a unified geospatial reference system. This establishes a correspondence between map data from different sources. Specifically, if the electronic navigation path includes a complex path covered by a discrete local high-precision map, the high-precision map path within that map is acquired. If, after heterogeneous matching, it is determined that the electronic navigation path to be traveled by the vehicle does not have a pre-maintained discrete local high-precision map coverage area, then high-precision map path mapping and switching are unnecessary, and the system continues to use the original electronic navigation path to perform subsequent positioning, map broadcasting, and autonomous driving control processes.

[0130] Step S202: Obtain high-precision positioning results based on real-time vehicle positioning information and high-precision map path. This step can be performed by the autonomous driving module.

[0131] Step S203: Based on the high-precision map path and high-precision positioning results, obtain the target high-precision map and broadcast the target high-precision map of the navigation path within a certain range ahead to the autonomous driving module.

[0132] In addition, in step S202, high-precision navigation positioning around the vehicle's real-time positioning information can be used directly to obtain high-precision positioning results in the high-precision map without relying on the navigation path in the high-precision map; however, the disadvantage of this is that the positioning matching result may not be on the navigation path, resulting in incorrect positioning, and at the same time, it will lead to a reduction in positioning matching efficiency.

[0133] Example 2:

[0134] Embodiment 2 of this application provides a computer-readable storage medium including a computer program. When the computer program is run on a computer device, the computer program is used to cause the computer device to perform the map data processing method described above.

[0135] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0136] Since the computer program stored in the storage medium can execute the steps of any of the map data processing methods provided in the embodiments of this application, the beneficial effects that any of the map data processing methods provided in the embodiments of this application can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.

[0137] Example 2:

[0138] Embodiment 2 of this application provides an electronic device, including:

[0139] A memory on which computer programs are stored;

[0140] A processor is used to execute a computer program in memory to implement the map data processing method described above.

[0141] The electronic device may include a processor with one or more processing cores, a memory with one or more storage media, a power supply, and input units, etc. Those skilled in the art will understand that the structure of the electronic device does not constitute a limitation on the electronic device, and it may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. Wherein:

[0142] The processor is the control center of the electronic device. It connects various parts of the device via interfaces and lines, and performs various functions and processes data by running or executing computer programs and / or modules stored in memory, and by calling data stored in memory. Optionally, the processor may include one or more processing cores; alternatively, the processor may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into the processor.

[0143] Memory can be used to store computer programs and modules. The processor executes these programs and modules to perform various functional applications and vehicle control. Memory can primarily include a program storage area and a data storage area. The program storage area may store the operating system, at least one computer program required for a function (such as vehicle accessibility detection), etc.; the data storage area may store data created based on the use of the electronic device. Furthermore, memory may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, memory electronics may also include memory devices to provide the processor with access to the memory.

[0144] Electronic devices also include power supplies for various components. Optionally, the power supply can be connected to the processor logic through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply may also include one or more DC or AC power sources, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0145] The electronic device may also include an input unit that can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0146] Although not shown, the electronic device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor in the electronic device loads the executable files corresponding to the processes of one or more computer programs into the memory according to the following instructions, and the processor runs the computer programs stored in the memory to realize various functions.

[0147] Example 2:

[0148] Embodiment 2 of this application provides a vehicle, the vehicle comprising:

[0149] As described in the electronic device;

[0150] Alternatively, a processor may be used to execute the map data processing method described above.

[0151] The processor is a heterogeneous computing unit integrated into the vehicle body, comprising a quad-core collaborative architecture of CPU, GPU, NPU, and DSP. This processor directly runs all the algorithm modules of this method without relying on external memory, achieving "edge-side intelligence." During vehicle operation, the processor dynamically prunes unnecessary high-precision data, retaining only the lane topology within a preset range before and after the current path, reducing memory usage. At high speeds, the system predicts whether to enter a high-precision area at preset intervals (e.g., preset time intervals or preset distance intervals), loading data in advance to avoid "data cliffs" caused by network latency.

[0152] The crowdsourced high-precision map in this application specifically refers to a discrete, local crowdsourced high-precision map that is pre-collected and maintained, covering major complex intersections and their surrounding preset range (e.g., 50-200m). Its difference from traditional full-domain high-precision maps lies in that it only collects and maintains data for complex scenarios where autonomous driving is prone to failure. The collected data comes from crowdsourced terminals, and data updates are completed through a cloud-based crowdsourcing platform. In the specific implementation process, the vehicle-side performs road-level stitching processing between the real-time acquired electronic navigation map and this local crowdsourced high-precision map, broadcasting the stitched unified map data to the autonomous driving system. This leverages the high-precision characteristics of crowdsourced high-precision maps in complex scenarios while avoiding the drawbacks of large data volume and high maintenance costs associated with full-domain crowdsourced high-precision maps. Simultaneously, the crowdsourcing model enhances the timeliness and coverage of the high-precision map.

[0153] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A map data processing method, characterized in that, The method includes: Based on electronic navigation maps, real-time vehicle positioning information, and discrete local high-precision maps, high-precision map data of the target road segment on the current navigation path is determined.

2. The processing method according to claim 1, characterized in that, The step of determining the high-precision map data of the target road segment on the current navigation path based on the electronic navigation map, the real-time vehicle positioning information, and the discrete local high-precision map includes: Based on the electronic navigation map, the real-time vehicle positioning information, and the discrete local high-precision map, a high-precision navigation path and a high-precision positioning result are obtained; Based on the high-precision navigation path and the high-precision positioning result, the high-precision map data of the target road segment is obtained.

3. The processing method according to claim 2, characterized in that, The electronic navigation map includes: an electronic navigation path; the process of obtaining a high-precision navigation path and a high-precision positioning result based on the electronic navigation map, the vehicle's real-time positioning information, and the discrete local high-precision map includes: Based on the electronic navigation path and the high-precision map coordinate system, the high-precision navigation path is obtained, wherein the high-precision map coordinate system is the coordinate system in which the discrete local high-precision map is located; The high-precision positioning result is obtained based on the real-time vehicle positioning information and the discrete local high-precision map.

4. The processing method according to claim 3, characterized in that, The process of obtaining the high-precision navigation path based on the electronic navigation path and the high-precision map coordinate system includes: The electronic navigation path is matched and mapped to the high-precision map coordinate system to obtain the high-precision navigation path corresponding to the real-time positioning information of the vehicle.

5. The processing method according to claim 4, characterized in that, The step of matching and mapping the electronic navigation path to the high-precision map coordinate system to obtain the high-precision navigation path corresponding to the vehicle's real-time positioning information includes: The electronic navigation path is mapped to the high-precision map coordinate system to obtain multiple high-precision projected road segments; The high-precision simulation segment that best matches the optimization objective is selected from among the multiple high-precision simulation segments to obtain the high-precision navigation path.

6. The processing method according to claim 5, characterized in that, The process of mapping the electronic navigation path to the high-precision map coordinate system yields multiple high-precision projected road segments, including: Using the real-time vehicle positioning information as the observation value, and the electronic navigation path and the high-precision map path as the state transition basis, the correspondence between the electronic navigation path and the high-precision map path is probabilistically deduced to obtain multiple high-precision deduced road segments.

7. The processing method according to claim 5, characterized in that, The optimization objectives include at least one of the following: minimum spatial distance, optimal topological continuity, and most consistent driving direction.

8. The processing method according to any one of claims 1-7, characterized in that, The step of determining the high-precision map data of the target road segment on the current navigation path based on the electronic navigation map, the real-time vehicle positioning information, and the discrete local high-precision map further includes: If the discrete local high-precision map exists on the current navigation path, then based on the electronic navigation map, the real-time vehicle positioning information and the discrete local high-precision map, the high-precision map data of the target road segment is obtained, and the high-precision map data is used as the map data of the target road segment. Alternatively, if the discrete local high-precision map does not exist on the current navigation path, the electronic navigation map will be used as the map data for the target road segment.

9. The processing method according to claim 8, characterized in that, The electronic navigation map includes an electronic navigation route, and the current navigation route is obtained by: obtaining the current navigation route based on the electronic navigation route and the vehicle's real-time positioning information.

10. The processing method according to any one of claims 1-7, characterized in that, The processing method further includes: Based on the high-precision map data and the electronic navigation map, a target high-precision map is obtained; the target high-precision map is then sent to the autonomous driving system.

11. The processing method according to claim 10, characterized in that, The high-precision map data includes high-precision road segments, and the electronic navigation map includes electronic road segments; obtaining the target high-precision map based on the high-precision map data and the electronic navigation map includes: The high-precision road segments that overlap geographically are stitched together with the electronic road segments to obtain the target high-precision map.

12. The processing method according to claim 11, characterized in that, The step of stitching together the geographically overlapping high-precision road segments with the electronic road segments to obtain the target high-precision map includes: When the electronic navigation map is switched to the high-precision map data, the subsequent roads of the geographically overlapping high-precision road segments are stitched together with the preceding roads of the electronic road segments to obtain the target high-precision map. Alternatively, when the high-precision map data is switched to the electronic navigation map, the preceding road of the geographically overlapping high-precision road segment is stitched together with the subsequent road of the electronic road segment to obtain the target high-precision map.

13. A computer-readable storage medium, characterized in that, Includes a computer program, which, when run on a computer device, causes the computer device to perform the map data processing method according to any one of claims 1-12.

14. An electronic device, characterized in that, include: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the map data processing method according to any one of claims 1-12.

15. A vehicle, characterized in that, The vehicles include: The electronic device as claimed in claim 14; Alternatively, a processor, the processor being configured to perform the map data processing method according to any one of claims 1-12.

Images