Map data processing method, navigation path planning method and device, and vehicle

Abstract

This application provides a map data processing method, a navigation route planning method, a device, and a vehicle. The method includes: acquiring a set of map units, which is obtained by decomposing original map data, and each map unit has an initial credibility; acquiring vehicle-mounted perception data and updating the initial credibility of each map unit in the map unit set based on the vehicle-mounted perception data to obtain a local evaluation result; the vehicle-mounted perception data includes environmental perception data and / or cabin behavior perception data; and determining the global credibility of each map unit based on the local evaluation result. This allows the vehicle to perceive the differences between the map and the actual road environment, as well as the driver's cognitive burden level, improving the real-time performance and accuracy of map credibility assessment. Determining the global credibility of each map unit based on the local evaluation result allows route planning to be based on the global credibility, avoiding untrusted map units and improving the safety and accuracy of route planning.

Description

Technical Field

[0001] This application relates to the field of automotive technology, and in particular to a map data processing method, a navigation route planning method, a device, and a vehicle. Background Technology

[0002] With the development of autonomous driving and intelligent navigation technologies, high-precision maps have become the core basis for route planning and driving decisions. However, map data often contains local errors, information lags, or is not compatible with the actual road environment.

[0003] In related technologies, map reliability updates typically rely on specialized data collection vehicles or centralized map version updates, resulting in low map update reliability and difficulty in meeting actual usage needs. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention are proposed to provide a map data processing method, navigation route planning method, apparatus and vehicle that overcome the above problems or at least partially solve the above problems.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: In a first aspect, embodiments of this application disclose a map data processing method, the method comprising: Obtain a set of map units, which is obtained by decomposing the original map data, and each map unit has an initial confidence level; Acquire vehicle-mounted perception data, and update the initial confidence level of each map unit in the map unit set based on the vehicle-mounted perception data to obtain a local evaluation result; the vehicle-mounted perception data includes environmental perception data and / or cabin behavior perception data; Based on the local evaluation results, the global credibility of each map unit is determined; The process of updating the initial confidence level of each map unit in the map unit set based on the vehicle-mounted perception data to obtain a local evaluation result includes: The consistency deviation is determined based on the environmental perception data, and / or the cabin behavior load index is determined based on the cabin behavior perception data; The initial confidence level of the map unit is updated based on the consistency deviation and / or the cabin behavior load index to obtain a local evaluation result.

[0006] Secondly, embodiments of this application disclose a navigation path planning method, the method comprising: Obtain a set of map cells; each map cell in the set of map cells has a global credibility determined using the method described in the first aspect; Path planning is performed based on the global credibility.

[0007] Thirdly, embodiments of this application disclose a map data processing apparatus, the apparatus comprising: The first acquisition module is used to acquire a set of map units, which is obtained by decomposing the original map data, and each map unit has an initial confidence level. An evaluation module is used to acquire vehicle-mounted perception data and update the initial confidence of each map unit in the map unit set based on the vehicle-mounted perception data to obtain a local evaluation result; the vehicle-mounted perception data includes environmental perception data and / or cabin behavior perception data. The determination module is used to determine the global credibility of each map unit based on the local evaluation results; The evaluation module includes: The first determining submodule is used to determine the consistency deviation based on the environmental perception data, and / or determine the cabin behavior load index based on the cabin behavior perception data; The update submodule is used to update the initial credibility of the map unit based on the consistency deviation and / or the cockpit behavior load index to obtain the local evaluation result.

[0008] Fourthly, embodiments of this application disclose a navigation path planning device, the device comprising: The second acquisition module is used to acquire a set of map units; each map unit in the set of map units has a global credibility determined by the method described in the first aspect; The planning module is used to plan paths based on the global credibility.

[0009] Fifthly, embodiments of this application disclose an electronic device, including: a processor connected to a memory; the memory being used to store a computer program; and the processor being used to execute the computer program stored in the memory to implement the steps in the methods described in the first and second aspects.

[0010] In a sixth aspect, embodiments of this application disclose a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps in the methods described in the first and second aspects.

[0011] This application discloses a map data processing method that decomposes the original map data into multiple independent map units, independently evaluates local areas, and dynamically updates the initial credibility of each map unit using real-time vehicle perception data to generate local evaluation results. This allows vehicles to perceive the differences between the map and the actual road environment, as well as the driver's cognitive load level, improving the real-time performance and accuracy of map credibility evaluation. Furthermore, the global credibility of each map unit is determined based on the local evaluation results, enabling route planning to be based on global credibility, avoiding untrusted map units, and improving the safety and accuracy of route planning. Attached Figure Description

[0012] Figure 1 This is a flowchart of the steps of a map data processing method provided in an embodiment of this application; Figure 2 This is a flowchart illustrating the steps of a navigation path planning method provided in an embodiment of this application; Figure 3 This is yet another path planning method provided in the embodiments of this application; Figure 4 This is a block diagram of a map data processing device provided in an embodiment of this application; Figure 5 This is a block diagram of a navigation path planning device provided in an embodiment of this application; Figure 6 This is a block diagram of an electronic device provided in an embodiment of this application; Figure 7 This is a schematic diagram of another electronic device provided in the embodiments of this application. Detailed Implementation

[0013] Exemplary embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the scope of the present application to those skilled in the art.

[0014] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and are not limited in number; for example, a first object can be one or more. Furthermore, the term "and / or" in the specification and claims is used to describe the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. In the embodiments of this application, the term "multiple" refers to two or more, and other quantifiers are similar.

[0015] refer to Figure 1 , Figure 1 This application discloses a flowchart of a map data processing method according to an embodiment, including: Step 101: Obtain a set of map units, which is obtained by decomposing the original map data. Each map unit has an initial confidence level.

[0016] In this embodiment, the original map data can be a navigation electronic map or high-precision map data. The original map data can be broken down into multiple independent map units according to link segments defined by the map provider or preset splitting rules. These independent map units serve as the smallest atomic units that can be independently evaluated and replaced in route planning, forming a map unit set. Each map unit corresponds to a continuous, independently evaluable road or lane segment; for example, a map unit can be a road segment, an intersection, or a lane segment. Each map unit has an initial confidence level, which can be determined based on preset rules such as the type of original map data, data version release time, and update frequency, and is used to characterize the initial reliability of the map unit.

[0017] Furthermore, after obtaining the set of map units, for each map unit... Assign an initial credibility Its value can be limited to the interval [0,1], and is used to quantify the basic reliability of the map unit before real-time evaluation. The initial reliability value can be determined based on the source type and update quality of the map data. Used to characterize the Each map unit corresponds to a continuous road or lane segment; The initial confidence level of the map unit is used to characterize the initial confidence level. One method for determining the initial confidence level is shown in Table 1. Table 1 is a table of methods for determining the initial confidence level, as follows.

[0018] Table 1

[0019] As shown in Table 1, one method for assigning initial confidence levels is as follows: For high-definition maps (HD Maps), which possess centimeter-level accuracy and high-frequency update capabilities, resulting in high data quality, an initial confidence level of 0.9 can be assigned, with a reasonable range of 0.85 to 0.95; for online navigation maps, which are periodically updated and have moderate accuracy, an initial confidence level of 0.7 can be assigned, with a reasonable range of 0.6 to 0.8; for low-frequency updates or historical data, which are lagging in updates and have lower data reliability, an initial confidence level of 0.5 can be assigned, with a reasonable range of 0.4 to 0.6. Through these differentiated assignments, the basic reliability levels of map units from different sources can be distinguished in the initial stage of the system, providing a unified numerical benchmark for subsequent dynamic adjustment of confidence levels.

[0020] For example, suppose a certain map unit If the data is derived from an online navigation map, then: By determining the initial confidence level of each map cell, a set containing the map cells and their initial confidence levels is output. express:

[0021] The above set It can be used as a basic input for subsequent processing procedures, and is used in step 102 to update and evaluate the map's credibility.

[0022] Step 102: Obtain vehicle perception data, and update the initial confidence of each map unit in the map unit set based on the vehicle perception data to obtain a local evaluation result; the vehicle perception data includes environmental perception data and / or cabin behavior perception data.

[0023] In this embodiment, the vehicle can collect onboard perception data in real time through onboard sensors during operation. This perception data can include environmental perception data, such as lane lines, lane width, and obstacle locations, as well as cabin behavior perception data, such as the number of navigation touch operations, the number of times voice commands are repeated or corrected, and the frequency of driver gaze deviation. The vehicle can update the initial credibility of map units based on the onboard perception data. For example, it can compare the road structure in the environmental perception data with the structural features of the map units, or analyze the driver's cognitive load level based on the cabin behavior perception data. Based on the comparison results, the initial credibility of the map units is dynamically updated, and the updated credibility is the local evaluation result.

[0024] Step 103: Determine the global credibility of each map unit based on the local evaluation results.

[0025] In this embodiment, the vehicle can determine global credibility based on local evaluation results. For example, if the vehicle passes through the same map unit multiple times, a local evaluation result is generated each time it passes through. The current local evaluation result is then statistically fused with historically stored evaluation results to obtain the global credibility of the corresponding map unit. Alternatively, the vehicle can directly use the current local evaluation result as the global credibility of the corresponding map unit. The vehicle updates the credibility based on its own perception data and locally stored historical data, which can be applied to scenarios with poor network conditions or high privacy requirements.

[0026] In one embodiment, the vehicle can collaborate with the cloud to determine global credibility. For example, the vehicle can report the generated local evaluation results to the cloud platform via the network. The local evaluation results may include information such as map unit identifier, local evaluation result, and evaluation time. The cloud can aggregate local evaluation results from multiple different vehicles. For any map unit, the cloud can fuse the local evaluation results from multiple vehicles and generate the global credibility of that map unit by combining the local evaluation results from all vehicles. Through cloud aggregation, the credibility evaluation of map units becomes more reliable. The vehicle can obtain the global credibility determined by the cloud for each map unit in real time as a reference for route planning, improving the reliability of route planning. In this application, the vehicle uses real-time onboard perception data to dynamically update the initial credibility of each map unit and generate local evaluation results, enabling a single vehicle to independently discover the differences between the map and the actual environment, improving the real-time performance and accuracy of local evaluation. Simultaneously, the local evaluation results are reported to the cloud, where the cloud aggregates the local evaluation results of multiple vehicles to generate the global credibility of each map unit and updates the map unit status in real time. This solves the problems of limited coverage of a single vehicle and high data noise, while improving the accuracy of the global credibility evaluation results. This allows the vehicle to prioritize map units with high global credibility when planning routes based on the real-time updated global credibility, thereby improving the safety and accuracy of route planning.

[0027] Optionally, step 102 includes: Sub-step 1021: Determine the consistency deviation based on the environmental perception data, and / or determine the cabin behavior load index based on the cabin behavior perception data; Sub-step 1022: Update the initial credibility of the map unit based on the consistency deviation and / or the cockpit behavior load index to obtain the local evaluation result.

[0028] In this embodiment, for sub-steps 1021 and 1022, the vehicle-mounted perception data includes environmental perception data and / or cabin behavior perception data. For environmental perception data, the vehicle can extract pre-labeled structural features from map units, such as the number of lanes, lane width, road boundaries, and obstacle locations, and extract corresponding real-time perception features from the environmental perception data. The two are then compared dimension by dimension to obtain the consistency deviation, which reflects the degree of difference between map labels and the actual road environment. For cabin behavior perception data, the vehicle can collect the number of navigation-related touch operations, the number of times voice commands are repeated or corrected, and the frequency of the driver's gaze deviating from the navigation display area per unit time. Each variable is multiplied by its corresponding preset weight and then summed to obtain the cabin behavior load index, which reflects the driver's cognitive burden level in the current navigation scenario. Based on the consistency deviation and / or cabin behavior load index, the initial credibility of the map unit is updated to obtain the local evaluation result.

[0029] Furthermore, the vehicle-side can update the initial confidence level based on one of the available vehicle perception data types, or update the initial confidence level based on both indicators simultaneously, without limiting the scope of this application embodiment.

[0030] Optionally, sub-step 1021 includes: Sub-step 10211: For any of the map units, obtain the pre-labeled structural features in the map unit and the real-time perception features extracted from the environmental perception data; the structural features correspond to the real-time perception features; the structural features include at least one of the following: number of lanes, lane width, and obstacle location; Sub-step 10212: Compare the structural features with the real-time sensing features, and determine the consistency deviation based on the comparison results.

[0031] In this embodiment, for sub-steps 10211 and 10212, when updating the credibility of map units based on environmental perception data, for each map unit to be evaluated, pre-annotated structural features in the map unit and real-time perception features extracted from the environmental perception data are obtained. The structural features are information pre-annotated in the map, which may include information such as the number of lanes, lane width, and obstacle positions of the map unit. The real-time perception features may be information such as the current number of lanes, measured lane width, and relative obstacle positions detected in real time by cameras or radar. The structural features and real-time perception features correspond one-to-one in feature dimensions, so that each feature dimension can be compared item by item to determine consistency deviations.

[0032] Optionally, sub-step 10212 includes: Sub-step A1: For each feature dimension, calculate the absolute difference between the real-time perceived feature and the structural feature; Sub-step A2 involves summing the absolute differences of all feature dimensions and dividing by the total number of feature dimensions to obtain the consistency deviation.

[0033] In this embodiment, for sub-steps A1 and A2, after acquiring the structural features and corresponding real-time perception features of the map unit, the vehicle-side performs calculations for each feature dimension. For each type of feature, such as the number of lanes, lane width, and obstacle location, it compares it with the real-time perception features on the corresponding feature dimension to obtain the absolute difference for that feature dimension. The absolute difference reflects the degree of deviation between the real-time perception result and the pre-labeled information on the map on the corresponding feature dimension; the smaller the difference, the more consistent they are, and the larger the difference, the greater the discrepancy. After calculating the absolute differences for all feature dimensions, the absolute differences for each feature dimension are summed, and the sum is divided by the total number of feature dimensions to obtain the consistency deviation of the corresponding map unit. The consistency deviation can range from 0 to 1. The closer the consistency deviation is to 0, the more closely the map label matches the actual environment; the closer the consistency deviation is to 1, the greater the difference between the map label and the actual environment.

[0034] In one embodiment, for any map unit First, extract the set of pre-labeled structural features of the map unit in the map data, represented as... :

[0035] Different structural features.

[0036] Simultaneously, a set of real-time sensing features corresponding one-to-one with the above structural features is extracted from the environmental sensing data, represented as follows: :

[0037] These are real-time sensing features that correspond one-to-one with the above structural features.

[0038] By comparing each feature in the two sets, a perceptual consistency bias is constructed to quantify the degree of difference between actual road conditions and map annotations. The bias is defined as follows:

[0039] Indicates consistency deviation, The number of feature dimensions, This indicates real-time perceived features. Indicates structural features, The larger the value, the more significant the difference between the map description and the real environment.

[0040] in, The value range can be [3, 10], including at least the number of lanes, lane width, and obstacle location. It can be the eigenvalues ​​that have been normalized to the interval [0,1].

[0041] Received The range of values ​​for can be: .

[0042] For structural features and real-time perceived features, normalization can be performed first, followed by consistency deviation calculation. For example, for the original physical quantities (such as lane width and obstacle distance), linear normalization can be performed first, as follows:

[0043] in, This represents the normalized value. The original value representing the structural features or actual perceived features. For the minimum value of the feature, The maximum value of the feature is given. Normalization is performed based on the above formula; an example is shown in Table 2, which contains examples of feature values.

[0044] Table 2

[0045] For example, for lane number characteristics Common lane number ranges for urban roads and expressways: The number of lanes marked on the map in the structural features: ;but

[0046] Example of real-time perception feature normalization calculation: Camera and perception algorithm to identify the number of lanes: ;but:

[0047] The same method was used to calculate lane width and obstacle distribution, and the resulting consistency deviation for this map unit was:

[0048] By calculating the consistency deviation, the difference between actual road data and map data is determined, thereby updating the initial credibility of map units so that the credibility of map units can reflect the actual situation.

[0049] Optionally, sub-step 1021 includes: Sub-step 10213: Collect cabin behavior perception data during vehicle driving. The cabin behavior perception data includes at least one of the following: the number of navigation-related touch operations per unit time, the number of repetitions or corrections in voice navigation commands per unit time, and the frequency of the driver's gaze deviating from the navigation display area. Sub-step 10214: The cockpit behavior perception data is weighted and summed to obtain the cockpit behavior load index.

[0050] In this embodiment, for sub-steps 10213 and 10214, the vehicle-mounted device continuously collects behavioral data related to navigation interaction within the cabin during vehicle operation. For example, the device collects the number of touch operations performed by the driver on the navigation interface on the in-vehicle central control screen per unit time, such as zooming in / out of the map, changing the destination, and viewing route details; it also collects the number of repetitions or corrections in the navigation voice commands issued by the driver per unit time, such as the driver repeating the same destination name or explicitly correcting errors in the navigation broadcast; and it collects the frequency of the driver's gaze deviating from the navigation display area via the driver monitoring camera, i.e., the number of times or the percentage of time the driver's gaze leaves the navigation screen. This behavioral data can reflect the driver's cognitive burden level and dependence on navigation information in the current navigation scenario from different dimensions.

[0051] After collecting cabin behavior perception data, each type of data is multiplied by its corresponding preset weight, and the weighted results are summed to obtain the cabin behavior load index. Each preset weight can be a value pre-set by the system, and the sum of all weights is 1. The specific values ​​of the weights can be adjusted according to the driving scenario. For example, in scenarios with frequent touch operations, the weight corresponding to the number of touch operations is set higher; in scenarios where voice interaction is dominant, the weight corresponding to the number of voice repetitions or corrections is set higher. A higher cabin behavior load index indicates a heavier cognitive burden on the driver in the current navigation scenario, which can indirectly reflect potential problems such as inaccurate map information or unclear navigation guidance on the current driving segment.

[0052] For example, in complex road conditions or scenarios with uncertain maps, even if the perceived data does not show obvious anomalies, drivers may express their distrust of the navigation results through frequent operations or repeated confirmations. Therefore, this application introduces quantitative modeling of driver behavior in the cockpit as an implicit risk signal into the further correction process of map credibility.

[0053] During vehicle operation, the system continuously collects cockpit behavior data related to navigation, including but not limited to: the number of navigation-related touch operations per unit time. Number of repetitions or corrections in voice navigation commands Frequency of driver's gaze deviating from the navigation display area The behavioral data mentioned above all reflect the level of cognitive burden on drivers in the current navigation scenario.

[0054] Based on the collected behavioral data, a cockpit behavior load index is constructed. The calculation method is as follows: in, , , Weights are preset for the system to adjust the influence of different behavioral factors on the overall load. Table 3 shows the range of values ​​for the behavioral variables.

[0055] Table 3

[0056] The weight values ​​satisfy: .

[0057] The specific values ​​of the weights can be adjusted according to the driving scenario. For example, in a touch-dominated scenario... Larger Voice-dominated scenarios Relatively large.

[0058] An example of a weight value is as follows: .like , , The calculated cabin behavior load index is:

[0059] Optionally, sub-step 1022 includes: Sub-step 10221: Multiply the initial confidence level by an exponential function with the natural constant as the base and the product of the negative perceptual sensitivity coefficient and the consistency deviation as the exponent to obtain the first updated confidence level; Sub-step 10222: Subtract the product of the behavior influence coefficient and the cockpit behavior load index from the first update confidence level to obtain the second update confidence level, which is used as the local evaluation result; the perception sensitivity coefficient and the behavior influence coefficient are preset values.

[0060] In this embodiment, after the vehicle-side calculates the consistency deviation based on environmental perception data, it can use an exponential decay model to update the initial confidence of the map unit for the first time. The exponential decay model is expressed as:

[0061] in, The preset perception sensitivity coefficient is used to adjust the strength of the impact of perception differences on credibility. Its value range is [0.5, 3.0], with higher values ​​indicating greater sensitivity to perception differences. Different perception sensitivity coefficients can be set for different road types, such as urban roads. Choose [1.5, 2.5] for high-speed or structurally stable roads: Take [0.5, 1.5].

[0062] If the initial credibility Consistency deviation , Then the reliability of the first update can be:

[0063] Through the above calculations, the set of map units updated and verified by environmental perception data is obtained: This set can serve as a direct input for introducing cockpit behavior load corrections in subsequent steps.

[0064] The first update confidence of the above output Combined with the cockpit behavior load index, the reliability of map units is corrected a second time, and its expression is as follows:

[0065] in, This is the behavioral influence coefficient, used to adjust the magnitude of the driver's behavior's impact on credibility correction. Its value ranges from [0.05, 2], and different values ​​can be used for different driving scenarios, such as under normal driving conditions. Using [0.05, 0.1], in high-risk or complex scenarios Take [0.1, 0.2].

[0066] For example, , , The calculated second update confidence level is: .

[0067] After correction based on environmental perception data and cockpit behavior load data, local evaluation results are obtained for map units, generating a set of map units with final credibility status. , by map unit And its second update credibility Formation, represented as:

[0068] Through the two updates described above, the vehicle-side integrated environmental perception data and driver behavior information, resulting in a more comprehensive local evaluation result. In practical applications, the initial confidence level can be updated solely based on the consistency deviation, in which case the calculated first updated confidence level is used as the local evaluation result. Alternatively, the initial confidence level can be updated solely based on the cabin behavior load index, in which case the initial confidence level minus the product of the behavior influence coefficient and the cabin behavior load index is used as the local evaluation result. Furthermore, the initial confidence level can be updated simultaneously based on both the consistency deviation and the cabin behavior load index. This embodiment of the application does not impose any limitations on these methods.

[0069] refer to Figure 2 , Figure 2 This application discloses a flowchart of the steps of a navigation path planning method provided in an embodiment, including: Step 201: Obtain a set of map cells; each map cell has a global credibility. Step 202: Perform path planning based on the global credibility.

[0070] In this embodiment of the application, for steps 201 and 202, before starting route planning, the vehicle can obtain a set of map units, where each map unit corresponds to a global confidence level. The global confidence level is used to reflect the reliability of each map unit. The higher the value, the more reliable the map unit is and the more suitable it is as a navigation basis. The lower the value, the more likely the map unit is to have errors or be incompatible with the actual environment and is not suitable as a navigation basis.

[0071] Global credibility can be derived from various sources, such as statistical fusion results based on historical observation data from the vehicle-side, local evaluation results from the vehicle-side at the current moment, or requests sent by the vehicle-side to the cloud via a communication network, or global credibility of each map unit actively distributed by the cloud. After obtaining the global credibility, the vehicle-side can store it in a local cache for subsequent route planning.

[0072] Furthermore, the vehicle-side performs route search and planning based on the global credibility of each map unit. When planning a route, map units with higher global credibility are prioritized for recommended routes, while the weight of map units with lower global credibility is avoided or reduced. For example, the vehicle-side can calculate the cost value of each map unit in the candidate path; this cost value is negatively correlated with the global credibility of the map unit. The total cost of each candidate path is determined, and the total cost of all candidate paths is compared. The path with the lowest total cost is selected as the final navigation recommendation. Through this method, the route planning result is determined based on the real-time global credibility of map units, improving the safety and reliability of navigation.

[0073] Optionally, step 202 includes: Sub-step 2021: Obtain the credibility threshold; the credibility threshold is determined based on the current road type; Sub-step 2022: Determine the planning priority of the map unit based on the comparison result between the global confidence level of the map unit and the confidence threshold. Optionally, sub-step 2022 includes: Sub-step 20221: If the global confidence level of the map unit is less than the confidence level threshold, then the planning priority of the map unit is low priority. Sub-step 20222: If the global confidence level of the map unit is equal to the confidence level threshold, then the planning priority of the map unit is medium priority. Sub-step 20223: If the global credibility of the map unit is greater than the credibility threshold, then the planning priority of the map unit is high priority.

[0074] Sub-step 2023: Determine the recommended path based on the planning priority of the map unit.

[0075] In this embodiment, for sub-steps 2021 to 2023, the credibility threshold is used to classify the credibility level of map units. The credibility threshold can be determined based on the road type where the vehicle is currently located. Different road types have different requirements for map accuracy, so the corresponding credibility thresholds can also be different. For example, in complex urban road scenarios, due to the complex road structure, frequent lane changes, and significant interference from pedestrians and non-motorized vehicles, the requirement for map credibility is high, so the credibility threshold can be set higher. In highway or ordinary road scenarios, the road structure is relatively simple, and the requirement for map credibility is relatively low, so the credibility threshold can be set lower accordingly. An example of a credibility threshold value could be: a range of [0.35, 0.4] for complex urban roads and a range of [0.3, 0.35] for ordinary roads. The credibility threshold is adaptively adjusted according to the actual driving scenario to make the path planning strategy more reasonable.

[0076] Furthermore, the global credibility of each map unit is compared with a credibility threshold, and a corresponding planning priority is determined for each map unit based on the comparison result. The planning priority characterizes the degree to which a map unit is selected in path planning. For example, when the global credibility is higher than the credibility threshold, the map unit has a high planning priority and can be preferentially selected in path planning; when the global credibility equals the credibility threshold, the map unit has a medium planning priority and can be considered as an alternative; when the global credibility is lower than the credibility threshold, the map unit has a low planning priority and should be avoided as much as possible in path planning. Through this hierarchical mechanism, path planning can prioritize high-priority map units, improving the reliability of path planning.

[0077] Optionally, sub-step 2023 includes: Sub-step 20231: Determine candidate paths based on the planning priority of the map unit; Sub-step 20232: Obtain the length of each map cell in the candidate path; Sub-step 20233: Calculate a confidence penalty term based on the global confidence of each map unit; the confidence penalty term is negatively correlated with the global confidence. Sub-step 20234: Add the length of each map unit to the confidence penalty term to obtain the cost of each map unit; Sub-step 20235: Sum the cost values ​​of all map units in the candidate path to obtain the total cost of the candidate path; Sub-step 20236: Select the candidate path with the minimum total cost as the recommended path for path planning.

[0078] In this embodiment, for sub-steps 20231 to 20236, during route planning, several candidate routes from the starting point to the destination are first generated. Each candidate route is composed of several consecutive map units connected in series. The length of each map unit in each candidate route is obtained; the length can be the actual physical length of the map unit on the road centerline. Based on the global credibility of each map unit obtained from the cloud or vehicle, a credibility penalty term corresponding to each map unit is calculated. The credibility penalty term is used to quantify the impact of map unit credibility. The size of the credibility penalty term is negatively correlated with the global credibility; that is, the higher the global credibility, the smaller the credibility penalty term, and the lower the global credibility, the larger the credibility penalty term. The map unit length and the credibility penalty term are summed to obtain the passage cost of the map unit. Here, the length of the map unit represents the basic cost required for normal passage, and the credibility penalty term represents the additional cost affected by the map unit credibility. For each candidate route, all map units contained in the route are traversed, and the calculated costs of each map unit are summed to obtain the total cost of the candidate route. The candidate path with the minimum total cost is selected as the final navigation recommendation path. Minimizing the total cost represents the optimal result that balances path length and map cell reliability.

[0079] During the path search process, a credibility-aware path cost function is introduced, which is defined as follows:

[0080] in, This represents the length of a map cell, in meters, with a value range of [5, 50]. It is abstracted as a distance fraction and used as a dimensionless distance fraction in the path cost function described above. This indicates the final credibility of the map unit. This is the credibility penalty coefficient, with a value range of [5, 50]. The lengths of map units for different road types exhibit different statistical distribution characteristics. For example, urban complex roads, due to their dense structure, typically have shorter map unit lengths. The length range can be [10, 30], and correspondingly, Take [20,40]; highways or roads with clear structures are usually longer in map unit length because they are straight and have simple connections. The length range that can be presented is [30, 50], correspondingly Take [5,20]. As a credibility penalty item.

[0081] The Cost function for credibility-aware paths is used as follows: Calculate the total cost of each candidate path by iterating through each map cell in the candidate path and accumulating the Cost according to the formula. The smaller the Cost value, the shorter and more reliable the path. Sort all candidate paths by Cost; the path with the lowest Cost is selected as the final navigation path.

[0082] For example, if a path contains a map cell: (In path cost calculation, a map cell length of 30 meters is abstracted as a distance fraction of 30). , ,but:

[0083] If a candidate path consists of three map units, as shown in Table 4, Table 4 is an example table for cost calculation: Table 4

[0084] m1 has low credibility (T2=0.32), so its unit cost of 43.6 is relatively high, and the algorithm tends to avoid or compromise on it. m2 and m3 have higher credibility and lower cost, so the algorithm tends to use these units. Finally, the algorithm will select the path with the minimum total cost from all candidate paths as the recommended path, achieving a balance between short path and high credibility.

[0085] Optionally, it also includes: Step 203: If the global credibility of the map unit is updated during the vehicle's journey, the total cost of the current path or candidate path is recalculated. Step 204: Automatically adjust the recommended path based on the recalculated total cost.

[0086] In this embodiment, regarding steps 106 and 107, if the global credibility of a map unit is updated during vehicle travel, the total cost of the current path or candidate path is recalculated, and the recommended path is automatically adjusted based on the recalculated total cost. That is, when real-time updates are detected... Then, the path cost is recalculated; the system automatically adjusts the recommended path to ensure safety and reliability.

[0087] Additionally, when determining the route, you can refer to which area the map cell belongs to, for example, As a confidence threshold, when any map unit satisfies If the map cell's reliability in the current driving scenario collapses, it is deemed unsuitable as a reliable basis for navigation calculations, and its planning priority is low. If the map cell is considered to be within a critical confidence interval, it will not collapse immediately in the current driving scenario, but needs to enter an observation state, and its planning priority is medium priority. This map unit falls within a trusted range and is considered a trusted map unit in the current driving scenario. It participates normally in path planning, and its planning priority is high. In actual operation, a specific threshold can be selected from the interval based on the road type as the current judgment criterion. Furthermore, for complex urban roads, a threshold of [0.35, 0.4] can be used, while for ordinary roads, it can be [0.3, 0.35]. For example, if: ,but: If a map unit meets the collapse criteria, it is classified as a low-confidence map unit and should be avoided as much as possible during subsequent path planning. For map units identified as having collapsed confidence, if the scenario involves temporary road control, temporary cognitive map units can be constructed based on vehicle-mounted perception data. Temporary cognitive map units are marked as valid only within the current trip, eliminating the need for cloud reporting or local updates. Through this process, high-priority map units can generate trusted map subsets. ,Depend on Map units and temporary cognitive map units Composition, represented as:

[0088] When determining candidate paths, priority can be given to searching based on a subset of trusted maps to improve path accuracy.

[0089] refer to Figure 3 , Figure 3 This application illustrates a path planning method provided by an embodiment, comprising: S1, multi-source data input; S2, map unit division; S3, calculate the reliability of map units; S4, determine if the credibility is less than the credibility threshold. If yes, proceed to step S5; otherwise, proceed to step S6. S5, credibility collapse handling; S6, retain the original map units; S7, generate a subset of the trusted map; S8, calculates the cost of the unit; S9, total standby accumulation for the path; S10, Path sorting and selection.

[0090] In this embodiment, the multi-source data may include environmental perception data and cockpit behavior load data. The original map data is divided into map units. The initial confidence of the map units is updated based on the environmental perception data and cockpit behavior load data. It is determined whether the updated confidence is less than a confidence threshold. If it is less than the confidence threshold, it means that the confidence of the map unit is low and it is the lowest priority for path selection. If it is not less than the confidence threshold, the original map unit is kept and used normally for path planning. Based on the comparison with the confidence threshold, a confidence map subset is generated. During path planning, planning is preferentially based on the map units in the confidence map subset. For each map unit in the candidate path, the unit cost is calculated, and the total cost of the candidate path is obtained by accumulation. The path with the minimum total cost is selected from the candidate paths as the navigation recommendation route.

[0091] In summary, this embodiment decomposes the original map data into multiple independent map units, independently evaluates local areas, and dynamically updates the initial credibility of each map unit using real-time vehicle perception data to generate local evaluation results. This allows vehicles to perceive the differences between the map and the actual road environment, as well as the driver's cognitive load level, improving the real-time performance and accuracy of map credibility evaluation. Furthermore, the global credibility of each map unit is determined based on the local evaluation results, enabling route planning to be based on global credibility, avoiding untrusted map units, and improving the safety and accuracy of route planning.

[0092] refer to Figure 4 This illustrates a map local evaluation device 30 provided in an embodiment of this application, the device comprising: The first acquisition module 301 is used to acquire a set of map units, which is obtained by decomposing the original map data, and each map unit has an initial confidence level. Evaluation module 302 is used to acquire vehicle perception data and update the initial confidence of each map unit in the map unit set based on the vehicle perception data to obtain a local evaluation result; the vehicle perception data includes environmental perception data and / or cabin behavior perception data; The determination module 303 is used to determine the global credibility of each map unit based on the local evaluation results.

[0093] Optionally, the evaluation module includes: The first determining submodule is used to determine the consistency deviation based on the environmental perception data, and / or determine the cabin behavior load index based on the cabin behavior perception data; The update submodule is used to update the initial credibility of the map unit based on the consistency deviation and / or the cockpit behavior load index to obtain the local evaluation result.

[0094] Optionally, the first determined submodule includes: The first acquisition unit is configured to acquire, for any one of the map units, pre-labeled structural features in the map unit and real-time perception features extracted from the environmental perception data; the structural features correspond to the real-time perception features; the structural features include at least one of the following: number of lanes, lane width, and obstacle location; The first determining unit is used to compare the structural features with the real-time perceived features and determine the consistency deviation based on the comparison results.

[0095] Optionally, the first determining unit includes: The first calculation subunit is used to calculate the absolute difference between the real-time perceived feature and the structural feature for each feature dimension; The second calculation subunit is used to sum the absolute differences of all feature dimensions and divide by the total number of feature dimensions to obtain the consistency deviation.

[0096] Optionally, the first determined submodule includes: The second acquisition unit is used to collect cabin behavior perception data during vehicle driving. The cabin behavior perception data includes at least one of the following: the number of navigation-related touch operations per unit time, the number of repetitions or corrections in voice navigation commands per unit time, and the frequency of the driver's gaze deviating from the navigation display area. The second determining unit is used to perform a weighted summation of the cockpit behavior perception data to obtain the cockpit behavior load index.

[0097] Optionally, update the submodules, including: The first update unit is used to multiply the initial confidence level by an exponential function with the natural constant as the base and the product of the negative perception sensitivity coefficient and the consistency deviation as the exponent, to obtain the first updated confidence level. The second update unit is used to subtract the product of the behavior influence coefficient and the cabin behavior load index from the first update confidence level to obtain the second update confidence level, which is used as the local evaluation result; the perception sensitivity coefficient and the behavior influence coefficient are preset values.

[0098] refer to Figure 5 This application illustrates a navigation path planning device 40 provided in an embodiment of the present application, the device comprising: The second acquisition module 401 is used to acquire a set of map units; each map unit has a global credibility. Planning module 402 is used to perform path planning based on the global credibility.

[0099] Optionally, the planning module includes: The first acquisition submodule is used to acquire a credibility threshold; the credibility threshold is determined based on the current road type. The second determining submodule is used to determine the planning priority of the map unit based on the comparison result between the global credibility of the map unit and the credibility threshold. The third determination submodule is used to determine the recommended path based on the planning priority of the map unit.

[0100] Optionally, the second determining submodule includes: The third determining unit is configured to set the planning priority of the map unit to low priority if the global confidence level of the map unit is less than the confidence level threshold. The fourth determining unit is configured to determine the planning priority of the map unit as medium priority if the global confidence level of the map unit is equal to the confidence level threshold. The fifth determining unit is configured to set the planning priority of the map unit to high priority if the global credibility of the map unit is greater than the credibility threshold.

[0101] Optionally, the third determining submodule includes: The sixth determining unit is used to determine candidate paths based on the planning priority of the map unit; The length acquisition unit is used to obtain the length of each map unit in the candidate path; The first calculation unit is used to calculate a confidence penalty term based on the global confidence of each map unit; the confidence penalty term is negatively correlated with the global confidence. The second calculation unit is used to add the length of each map unit to the confidence penalty term to obtain the cost of each map unit; The third calculation unit is used to sum the cost values ​​of all map units in the candidate path to obtain the total cost of the candidate path. The second determining unit is used to select the candidate path with the minimum total cost as the recommended path for path planning.

[0102] Optionally, the device further includes: The dynamic calculation module is used to recalculate the total cost of the current path or candidate path if the global credibility of the map unit is updated during vehicle operation. The dynamic update module is used to automatically adjust the recommended path based on the recalculated total cost.

[0103] In summary, this application's embodiments decompose the original map data into multiple independent map units, independently evaluate local areas, and dynamically update the initial credibility of each map unit using real-time vehicle perception data to generate local evaluation results. This allows vehicles to perceive the differences between the map and the actual road environment, as well as the driver's cognitive load level, improving the real-time performance and accuracy of map credibility evaluation. Furthermore, the global credibility of each map unit is determined based on the local evaluation results, enabling route planning to be based on global credibility, avoiding untrusted map units, and improving the safety and accuracy of route planning.

[0104] Reference Figure 6 The electronic device 600 may include one or more of the following components: a processing component 602, a memory 604, a power supply component 606, a multimedia component 608, an audio component 610, an input / output (I / O) interface 612, a sensor component 614, and a communication component 616.

[0105] Processing component 602 typically controls the overall operation of electronic device 600, such as operations associated with display, telephone calls, data communication, camera operation, and recording operations. Processing component 602 may include one or more processors 620 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 602 may include one or more modules to facilitate interaction between processing component 602 and other components. For example, processing component 602 may include a multimedia module to facilitate interaction between multimedia component 608 and processing component 602.

[0106] Memory 604 is used to store various types of data to support the operation of electronic device 600. Examples of this data include instructions for any application or method operating on electronic device 600, contact data, phonebook data, messages, pictures, multimedia, etc. Memory 604 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0107] Power supply component 606 provides power to various components of electronic device 600. Power supply component 606 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 600.

[0108] Multimedia component 608 includes a screen that provides an output interface between the electronic device 600 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may not only sense the boundaries of touch or swipe actions but also detect the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 608 includes a front-facing camera and / or a rear-facing camera. When the electronic device 600 is in an operating mode, such as a shooting mode or a multimedia mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0109] Audio component 610 is used to output and / or input audio signals. For example, audio component 610 includes a microphone (MIC) used to receive external audio signals when electronic device 600 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 604 or transmitted via communication component 616. In some embodiments, audio component 610 also includes a speaker for outputting audio signals.

[0110] I / O interface 612 provides an interface between processing component 602 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0111] Sensor assembly 614 includes one or more sensors for providing state assessments of various aspects of electronic device 600. For example, sensor assembly 614 can detect the on / off state of electronic device 600, the relative positioning of components such as the display and keypad of electronic device 600, changes in position of electronic device 600 or a component of electronic device 600, the presence or absence of user contact with electronic device 600, orientation or acceleration / deceleration of electronic device 600, and temperature changes of electronic device 600. Sensor assembly 614 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 614 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 614 may also include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor.

[0112] Communication component 616 facilitates wired or wireless communication between electronic device 600 and other devices. Electronic device 600 can access wireless networks based on communication standards, such as WiFi, carrier networks (such as 2G, 3G, 4G, or 5G), or combinations thereof. In one exemplary embodiment, communication component 616 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 616 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0113] In an exemplary embodiment, the electronic device 600 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to implement a method provided in the embodiments of this application.

[0114] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 604 including instructions, which can be executed by a processor 620 of an electronic device 600 to perform the above-described method. For example, the non-transitory storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0115] Figure 7A block diagram of an electronic device 700 is shown according to an exemplary embodiment. For example, the electronic device 700 may be provided as a server. (Refer to...) Figure 7 Electronic device 700 includes a processing component 722, which further includes one or more processors, and memory resources represented by memory 732 for storing instructions, such as application programs, that can be executed by the processing component 722. The application programs stored in memory 732 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 722 is configured to execute instructions to perform a method provided in embodiments of this application.

[0116] Electronic device 700 may also include a power supply component 726 configured to perform power management of electronic device 700, a wired or wireless network interface 750 configured to connect electronic device 700 to a network, and an input / output (I / O) interface 758. Electronic device 700 may operate on an operating system stored in memory 732, such as Windows Server™, MacOSX™, Unix™, Linux™, FreeBSD™, or similar.

[0117] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the method described above.

[0118] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0119] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A map data processing method, characterized in that, The method includes: Obtain a set of map units, which is obtained by decomposing the original map data, and each map unit has an initial confidence level; Acquire vehicle-mounted perception data, and update the initial confidence level of each map unit in the map unit set based on the vehicle-mounted perception data to obtain a local evaluation result; the vehicle-mounted perception data includes environmental perception data and / or cabin behavior perception data; Based on the local evaluation results, the global credibility of each map unit is determined; The process of updating the initial confidence level of each map unit in the map unit set based on the vehicle-mounted perception data to obtain a local evaluation result includes: The consistency deviation is determined based on the environmental perception data, and / or the cabin behavior load index is determined based on the cabin behavior perception data; The initial confidence level of the map unit is updated based on the consistency deviation and / or the cabin behavior load index to obtain a local evaluation result.

2. The method according to claim 1, characterized in that, Based on the environmental perception data, consistency deviations are determined, including: For any of the map units, pre-labeled structural features in the map unit and real-time perception features extracted from the environmental perception data are obtained; the structural features correspond to the real-time perception features; the structural features include at least one of the following: number of lanes, lane width, and obstacle location; The structural features are compared with the real-time sensing features, and the consistency deviation is determined based on the comparison results.

3. The method according to claim 2, characterized in that, The step of comparing the structural features with the real-time perceived features and determining the consistency deviation based on the comparison results includes: For each feature dimension, calculate the absolute difference between the real-time perceived feature and the structural feature; The consistency deviation is obtained by summing the absolute differences of all feature dimensions and dividing by the total number of feature dimensions.

4. The method according to claim 1, characterized in that, The step of determining the cabin behavior load index based on the cabin behavior perception data includes: The system collects cabin behavior perception data during vehicle operation. The cabin behavior perception data includes at least one of the following: the number of navigation-related touch operations per unit time, the number of repetitions or corrections in voice navigation commands per unit time, and the frequency of the driver's gaze deviating from the navigation display area. The cockpit behavior perception data is weighted and summed to obtain the cockpit behavior load index.

5. The method according to claim 1, characterized in that, The initial confidence level of the map unit is updated based on the consistency deviation and / or the cabin behavior load index to obtain a local evaluation result, including: The initial confidence level is multiplied by an exponential function with the natural constant as the base and the product of the negative perceptual sensitivity coefficient and the consistency deviation as the exponent, to obtain the first updated confidence level. The first update confidence level is obtained by subtracting the product of the behavior influence coefficient and the cockpit behavior load index, which is used as the local evaluation result; the perception sensitivity coefficient and the behavior influence coefficient are preset values.

6. A navigation path planning method, characterized in that, The method includes: Obtain a set of map cells; each map cell in the set of map cells has a global confidence level determined by the method described in any one of claims 1-5; Path planning is performed based on the global credibility.

7. The method according to claim 6, characterized in that, The path planning based on the global credibility includes: Obtain a credibility threshold; the credibility threshold is determined based on the current road type; The planning priority of the map unit is determined based on the comparison between the global credibility of the map unit and the credibility threshold. The recommended path is determined based on the planning priority of the map unit.

8. The method according to claim 7, characterized in that, The step of determining the planning priority of a map unit based on a comparison between the global confidence level of the map unit and the confidence threshold includes: If the global confidence level of the map unit is less than the confidence level threshold, then the planning priority of the map unit is low priority. If the global confidence level of the map unit is equal to the confidence level threshold, then the planning priority of the map unit is medium priority. If the global credibility of the map unit is greater than the credibility threshold, then the planning priority of the map unit is high priority.

9. The method according to claim 7, characterized in that, The step of determining the recommended path based on the planning priority of the map unit includes: Candidate paths are determined based on the planning priority of the map units; Obtain the length of each map unit in the candidate path; A credibility penalty term is calculated based on the global credibility of each map unit; the credibility penalty term is negatively correlated with the global credibility. The length of each map unit is added to the confidence penalty term to obtain the cost of each map unit; The total cost of the candidate path is obtained by summing the cost values ​​of all map units in the candidate path. The candidate path with the lowest total cost is selected as the recommended path for path planning.

10. The method according to claim 7, characterized in that, The method further includes: If the global confidence of a map cell is updated during vehicle travel, the total cost of the current path or candidate path is recalculated. The recommended path is automatically adjusted based on the recalculated total cost.

11. A map data processing device, characterized in that, The device includes: The first acquisition module is used to acquire a set of map units, which is obtained by decomposing the original map data, and each map unit has an initial confidence level. An evaluation module is used to acquire vehicle-mounted perception data and update the initial confidence of each map unit in the map unit set based on the vehicle-mounted perception data to obtain a local evaluation result; the vehicle-mounted perception data includes environmental perception data and / or cabin behavior perception data. The determination module is used to determine the global credibility of each map unit based on the local evaluation results; The evaluation module includes: The first determining submodule is used to determine the consistency deviation based on the environmental perception data, and / or determine the cabin behavior load index based on the cabin behavior perception data; The update submodule is used to update the initial credibility of the map unit based on the consistency deviation and / or the cockpit behavior load index to obtain the local evaluation result.

12. A navigation path planning device, characterized in that, The device includes: The second acquisition module is used to acquire a set of map units; each map unit in the set of map units has a global confidence level determined by the method described in any one of claims 1-5; The planning module is used to plan paths based on the global credibility.

13. A vehicle, characterized in that, The vehicle includes the map data processing device as described in claim 11, and / or the navigation route planning device as described in claim 12.

14. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the method as described in any one of claims 1-5 or 6-10.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method as described in any one of claims 1-5 or 6-10.

Images