Method of availability prediction for feature-based positioning of vehicle and method for controlling vehicle

By calculating the characteristic availability value on the vehicle's driving route, the problem of unavailable positioning of autonomously controlled vehicles during driving is solved, and accurate prediction and route planning of vehicle positioning are achieved, and the reliability of autonomous control is improved.

CN118974519APending Publication Date: 2024-11-15ROBERT BOSCH GMBH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202380032358.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-04-01
Filing Date
2023-03-06
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

Autonomous control The vehicle can not detect objects in the feature map during driving, resulting in unavailability of positioning, affecting the vehicle's autonomous control ability.

Method used

By receiving characteristic map data of the road traffic network, the characteristic availability value on the vehicle's driving route is calculated, and factors such as environmental sensor type, directional characterization and traffic flow are taken into account, and relevant availability information is output to assist route planning and vehicle control.

Benefits of technology

Accurate prediction and route planning of vehicle positioning availability are achieved, ensuring that the vehicle can detect necessary features with the highest probability on the selected route, and improving the reliability of autonomous control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118974519A_ABST
    Figure CN118974519A_ABST
Patent Text Reader

Abstract

The invention relates to a method (100) for availability prediction of feature-based localization of a vehicle (401), the method comprising: receiving (101) map data (412) of a feature map (411) of a road traffic network; ascertaining (103) a feature (413) for at least one roadway (403) to be driven by the vehicle (401) on the basis of feature information of the feature map (411); calculating (105) an availability value of a feature (413) of at least one roadway (403) to be driven by the vehicle (401) in relation to an availability criterion; and outputting (107) availability information relating to a feature (413) of the roadway (403) to be driven, said availability information comprising the availability value.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to a method for availability prediction of feature-based positioning of a vehicle. The invention also relates to a method for route planning for an autonomously controllable vehicle. The invention also relates to a method for controlling a vehicle. Background Art

[0002] Automated and highly automated driving is considered a future trend. For the orientation of autonomously controllable vehicles, the vehicle's environmental map representation is crucial. The positioning of the vehicle is achieved in particular by matching the features of the corresponding feature map with the objects arranged in the vehicle's environment detected by the environmental sensors. If such positioning is not possible because the corresponding objects are not detected by the environmental sensors during driving, autonomous control is not possible. Therefore, for the autonomous control of the vehicle, the following routes should be decisively selected: in these routes, it can be expected that a sufficient number of objects can be reliably detected to match the corresponding features of the feature map. Summary of the invention

[0003] It is therefore an object of the present invention to provide an improved method for predicting the availability of feature-based localization of a vehicle, an improved method for route planning for an autonomously controllable vehicle and an improved method for controlling a vehicle.

[0004] This object is achieved by a method for predicting the availability of a feature-based localization of a vehicle, a method for route planning for an autonomously controllable vehicle, and a method for controlling a vehicle according to the independent claims. Advantageous embodiments are the subject matter of the dependent claims.

[0005] According to one aspect of the present invention, a method for predicting availability of feature-based positioning of a vehicle is provided, the method comprising:

[0006] Receiving map data of a feature map of a road traffic network, wherein the feature map includes feature information of a plurality of roadways on which vehicles can travel, and wherein the features are arranged to be detected by a vehicle traveling on the roadways through sensor data of an environmental sensor of the vehicle and used for positioning the vehicle;

[0007] Determining characteristics of at least one roadway on which the vehicle is to travel based on the characteristic information of the characteristic map;

[0008] calculating, as a function of an availability criterion, an availability value for a feature of at least one roadway on which the vehicle is to travel, wherein the availability value indicates a quantitative measure of the availability of the feature for positioning the vehicle when the vehicle travels on the roadway; and

[0009] Availability information related to the characteristics of the roadway to be traveled on is output, the availability information including the availability value.

[0010] The following technical advantage can be achieved by this: an improved method for predicting the availability of feature-based positioning of a vehicle can be provided. The method according to the present invention is particularly used for route planning for a vehicle, such as an autonomously controllable vehicle. Therefore, for a route to be traveled by a vehicle, the features of a feature map are obtained for the corresponding roadway of the route, and an availability value is calculated for the corresponding feature. The availability value describes a quantitative measure of the availability of the feature for the positioning of the vehicle when the roadway of the selected route is traveled. If the corresponding feature can be detected by the environmental sensor of the vehicle when the vehicle travels the corresponding roadway of the selected route, the feature of the feature map can be used for the positioning of the vehicle. The feature of the feature map corresponds to the corresponding object in the environment. These objects can be arranged along the corresponding roadway to be traveled by the vehicle. For example, these objects can be arranged at the roadway edge of the roadway to be traveled. However, depending on the position of the vehicle on the roadway, the type of environmental sensor or the conditions of the environment, such as weather conditions or traffic flow, all objects may not be seen by the environmental sensor of the vehicle at every time point or every time the vehicle travels the roadway, and therefore are not available for the position determination of the vehicle. After calculating the availability values ​​of a plurality of features of different roadways, the corresponding availability information related to the features of the roadway to be traveled is output. With the output availability information, the corresponding route selection can be carried out based on the availability of the features or objects arranged along the selected route. Therefore, based on the availability information in the route planning, for example, in addition to providing the route with the shortest driving time, the driver can be provided with a route with the highest availability of the features. In this case, the availability describes a value, such as a percentage or a probability value, which indicates how many of the objects can be seen or with what probability the object is expected to be detected.

[0011] According to one specific embodiment, the availability criterion comprises detectability by surroundings sensors of the vehicle based on sensor type and / or direction-specific features of the surroundings sensors of the vehicle, wherein calculation of the availability value comprises:

[0012] ascertaining a sensor type and / or a direction indicator of at least one surroundings sensor of the vehicle; and

[0013] The detectability of features of the roadway on which the vehicle is to travel is determined for the sensor type and / or the direction characterization of the at least one surroundings sensor.

[0014] The following technical advantages can be achieved by this: the availability of the features stored in the feature map for positioning the vehicle can be accurately calculated. For this purpose, the availability criteria considered for calculating the availability value are defined as the detectability of the vehicle's environmental sensors through the roadway to be traveled based on the sensor type and / or direction characterization features of the vehicle's environmental sensors. The sensor type of the environmental sensor can include the configuration of the environmental sensor as a camera sensor, a radar sensor or a lidar sensor. According to the present invention, the direction characterization is understood as the sensitivity of the corresponding direction association of the corresponding environmental sensor. Therefore, based on the sensor type and the direction characterization, the detectability of the features arranged along the roadway to be traveled by the vehicle can be calculated for each environmental sensor of the vehicle. Therefore, the detectability of the features through the corresponding environmental sensors is related to the position of the features relative to the vehicle, wherein the corresponding features are completely mapped, partially mapped or not mapped at all due to the direction characterization of the corresponding environmental sensors. Similarly, the detectability of the features can be given by the corresponding properties of the features, wherein, depending on the reflectivity of the features, the features can be well detected, poorly detected or not detected at all by different types of environmental sensors. Thus, for example, objects which can be detected without problems by a radar sensor, for example at night and in insufficient lighting conditions, can hardly be detected by a camera sensor and are therefore not available for localizing the vehicle.

[0015] According to one specific embodiment, the availability criterion comprises the detectability of the vehicle's surroundings by sensors taking into account the traffic flow on the roadway to be traveled, wherein the calculation of the availability value comprises:

[0016] Calculating the traffic flow on the roadway through which the vehicle is to pass; and

[0017] By calculating the coverage of the feature of the roadway by the traffic flow on the roadway, the detectability of the feature of the roadway on which the vehicle is to travel is determined.

[0018] The following technical advantage can be achieved by this: the calculation of the availability information of the individual features of the feature map can be further improved. For this purpose, the detectability of the features by the environmental sensors of the vehicle is also calculated for the availability criterion under consideration of the traffic flow on the roadway on which the vehicle is to pass. Since the individual features are usually arranged along the roadway on which the vehicle is to pass, the detectability of these features by the environmental sensors of the vehicle may be greatly affected by other vehicles of the road traffic arranged in the environment of the vehicle in addition to the characteristics of the corresponding environmental sensors. In the case of high traffic flow, in which a large number of other vehicles are arranged in the environment of the vehicle, which respectively hinder the detection of the features arranged at the edge of the roadway by the environmental sensors of the vehicle, a correspondingly lower availability of the features of the corresponding roadway is obtained, because the features cannot be detected or detected by the environmental sensors due to the blocking other vehicles.

[0019] According to one implementation, obtaining the traffic flow includes:

[0020] determining an average number and / or an average speed of vehicles per time unit on a roadway through which the vehicle travels; and wherein the determination of detectability comprises:

[0021] An average coverage of the features of the roadway is calculated based on an average number and / or an average speed of vehicles per time unit.

[0022] The following technical advantage can thereby be achieved: an accurate prediction of the traffic flow for the corresponding roadway on which the vehicle is to pass can be implemented. This in turn contributes to an improved determination of availability information related to the corresponding roadway. Since the method according to the present invention is primarily configured for route planning, in order to determine the availability of features of the roadway on which the corresponding vehicle is to pass in the future, it is necessary to predict the traffic flow that may occur on the corresponding roadway at the time point when the vehicle passes through the roadway. Therefore, by calculating the average traffic flow and the average coverage of vehicles passing the traffic flow based on this feature, an accurate and possible prediction of the traffic flow to be encountered at any time point in the future can be achieved. The average traffic flow can be calculated here based on the average number or average speed of vehicles on the corresponding roadway.

[0023] According to one embodiment, the calculation of the availability value includes: determining at least one characterization (Charakteristikum) of a feature, wherein the at least one characterization includes: the type of feature, the number of features, the number of features of a specific type or category, the extension and / or size of the feature, the reflectivity of the feature; a re-recognition value (Wiedererkennungswert) of the feature, and wherein the detectability is determined in relation to at least one specific characterization of the feature and a detectability-corrected characterization is calculated.

[0024] The following technical advantages can be achieved in this way: the calculation of the availability value or the availability information can be further refined. The detectability of a plurality of features of the corresponding roadway can be further quantified by different characterizations of the features, such as the type of feature, the number of features or the spatial extension of the characteristic. In this case, the characterization can be extracted from the detected features, in particular, by implementing a correspondingly trained artificial intelligence. According to the invention, the characterization is in particular a statistical variable which describes the feature set in its entirety.

[0025] According to one embodiment, the calculation of the availability value includes:

[0026] At least one representation of a feature of the map representation is compared to a corresponding detectability-corrected representation.

[0027] The following technical advantage can thereby be achieved: the calculation of the availability value can be further refined. For this purpose, a comparison is performed of the characterization of the features of the feature map with the corresponding detectability-corrected characterization of the features. For this purpose, for example, the number of features in the feature map can be compared or correlated with the number of features predicted for a specific traffic flow and reduced accordingly. Due to the corresponding traffic flow and the other vehicles respectively arranged in the environment of the vehicle, not all features of the roadway can be detected by the vehicle. Therefore, a quantitative value for the availability of the corresponding feature of the feature map can be calculated by comparing the features of the feature map with the number of features calculated for the corresponding traffic flow and detectable by the vehicle's environmental sensors.

[0028] According to one specific embodiment, the determination of detectability is carried out for at least one previously known position of the vehicle on the roadway or for different previously known positions of the vehicle on different lanes of the roadway.

[0029] This allows the following technical advantages to be achieved: The position-dependent detectability of features of the roadway to be traveled on can be determined. Taking the position into account allows a further refinement of the determination of the availability of features of the feature map. Taking into account the different lanes of the roadway to be traveled on further results in an additional refinement of the availability determination.

[0030] According to one embodiment, the determination of detectability is carried out by means of a correspondingly trained artificial intelligence, wherein the artificial intelligence is trained based on environmental sensor data of an environmental sensor of at least one vehicle, and wherein the environmental sensor data have been recorded during a plurality of trips of the vehicle along at least one roadway during a plurality of different traffic flows.

[0031] This makes it possible to achieve the technical advantage that a precise, rapid and reliable determination of detectability is possible.

[0032] According to one specific embodiment, the features are characterizing objects arranged at the edge of the road and include: buildings, traffic signs, road markings.

[0033] This can achieve the following technical advantages: It enables comprehensive consideration of different features. In particular, the characterizing object is given by all objects that are suitable for positioning and can be detected by radar, lidar, ultrasound and video, and can include direction arrows, lane markings, in particular broken lines, trees, other vegetation, bridges, distributed structures, such as posts and columns; elements for lane delimitation: paving stones, crash barriers and bollards. This list should not be understood as exhaustive.

[0034] Furthermore, features that cannot be semantically labeled but can be extracted from the raw data of the environmental sensors by a correspondingly trained artificial intelligence can be detected and used. The artificial intelligence usually recognizes or detects key points in the environmental sensor data and sets a vector describing the type of the point for these key points. These key points that are not known to the operator of the artificial intelligence and cannot be semantically identified but are nevertheless reliably detected by the corresponding artificial intelligence can also serve as characterization objects in the sense of the present invention.

[0035] According to another aspect, there is provided a method for route planning for an autonomously controllable vehicle, the method comprising:

[0036] Implementing the method for feature-based positioning availability prediction of a vehicle according to one of the preceding embodiments on a plurality of possible routes of the vehicle between a predetermined starting point and a predetermined end point; and

[0037] Based on the carried out availability prediction, a route of the vehicle is ascertained which has the highest predicted availability of the vehicle based on the feature-based positioning.

[0038] This makes it possible to achieve the technical advantage of improved route planning for autonomously controllable vehicles, wherein, in addition to the fastest route, a route can be provided on which the highest availability of features required for positioning is expected and on which fully autonomous control of the vehicle is therefore possible with the highest probability.

[0039] According to another aspect, there is provided a method for controlling a vehicle, the method comprising:

[0040] Implementing a method for route planning for an autonomously controllable vehicle; and

[0041] The vehicle is steered based on the selected route.

[0042] This makes it possible to achieve the technical advantage of an improved control of an autonomously controllable vehicle, wherein the control leads back to an improved route planning and an improved availability prediction with the above-mentioned technical advantages.

[0043] According to one specific embodiment, the steering of the vehicle includes the execution of a maneuver planning, wherein the maneuver planning includes a driving maneuver of the vehicle that enables an optimal availability of features of the features of the feature map.

[0044] This allows the technical advantage of improved control of the vehicle to be achieved. In particular, the vehicle can perform a driving maneuver based on the result of the availability determination, thereby optimizing the availability. For example, if a difference in the availability of characteristics of different lanes on a roadway is determined, the driving maneuver can provide for a lane change of the roadway to be driven.

[0045] According to a further aspect, a computing unit is provided which is configured to implement a method for predicting availability of feature-based positioning of a vehicle and / or a method for route planning for an autonomously controllable vehicle and / or a method for controlling a vehicle according to one of the aforementioned embodiments.

[0046] According to another aspect, a computer program product is provided, which includes instructions that, when the program is executed by a data processing unit, cause the data processing unit to implement a method for feature-based positioning availability prediction of a vehicle and / or a method for route planning for an autonomously controllable vehicle and / or a method for controlling a vehicle according to one of the aforementioned embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Embodiments of the present invention are described below with reference to the accompanying drawings. In the accompanying drawings:

[0048] Figure 1 : A schematic diagram of a system for controlling a vehicle;

[0049] Figure 2 : A flow chart of a method for feature-based positioning availability prediction of a vehicle according to one embodiment;

[0050] Figure 3: A flow chart of a method for route planning for an autonomously controllable vehicle according to one embodiment;

[0051] Figure 4 : A flow chart of a method for controlling a vehicle according to one embodiment; and

[0052] Figure 5 : Schematic diagram of a computer program product for implementing a method for feature-based positioning availability prediction of a vehicle and / or a method for route planning for an autonomously controllable vehicle and / or a method for controlling a vehicle. DETAILED DESCRIPTION

[0053] Figure 1 A schematic diagram of a system 400 for controlling a vehicle 401 is shown.

[0054] Figure 1 4 shows a vehicle 401 traveling on a roadway 403. Various features 413 are arranged along the roadway 403. Features 413 are designed as different objects, such as buildings, vegetation, traffic signs, etc., by means of which orientation of the vehicle 401 is possible. FIG. A also shows a feature map 413, in which the illustrated roadway 403 is represented with correspondingly arranged features 413. FIG. A also shows a computing unit 415 with an installed artificial intelligence 419.

[0055] In this case, computing unit 415 is designed to carry out the method according to the present invention for predicting availability for feature-based localization of vehicle 401 .

[0056] Vehicle 401 also has at least one environment sensor 405, by means of which an environment recognition of the environment of vehicle 401 is possible. Vehicle 401 also has a computing unit 417. For example, computing unit 417 may be designed for autonomous or partially automated control of the vehicle.

[0057] For example, computing unit 415 may be designed as an external server unit or an external cloud server.

[0058] To implement the method for feature-based location availability prediction of vehicle 401 according to the present invention, computing unit 415 first receives feature map 411 in the form of corresponding map data 412. In addition, sensor information data 407 of environmental sensor 405 of vehicle 401 are provided to computing unit 415. For example, sensor information data 407 may include information related to the sensor type of the environmental sensor or the direction characterization of the corresponding environmental sensor 405 of vehicle 401. In addition, data 409 of traffic flow related to roadway 403 may be provided to computing unit 415. The data 409 of traffic flow may be current data of traffic flow in a specific roadway or multiple different roadways at a predetermined time point. Alternatively, the data may be related to a past time point. Alternatively, the data may describe an average traffic flow. For example, data 409 may be transmitted by another vehicle that has traveled the corresponding roadway at a predetermined time point. Alternatively, data 409 may be archived data. Data 409 may also include the number and / or speed of vehicles.

[0059] To calculate an availability prediction for feature-based positioning of vehicle 401 , an availability value is calculated by a calculation unit 415 for roadway 403 to be traveled by vehicle 401 based on map data 412 of a feature map 411 for features 413 arranged along roadway 403 , taking into account availability criteria.

[0060] According to one specific embodiment, the detectability of the feature 413 by the corresponding environmental sensor 405 of the vehicle 401 may be considered for the availability criterion of the individual features 413. For this purpose, information of the sensor information data 407 relating to the sensor type and / or the direction representation 410 of the individual environmental sensors 405 may be considered. Thus, based on the feature information of the feature map 411, for each feature 413 of the feature map 411 arranged along the roadway 403 to be traveled by the vehicle 401, the corresponding detectability of the corresponding feature 413 by the environmental sensor 405 may be calculated according to the corresponding sensor type or the direction representation 410 of the corresponding environmental sensor 405 of the vehicle 401. The detectability describes a quantifiable variable according to which the corresponding feature 413 can be detected by the environmental sensor 405 of the vehicle 401. This detectability may, for example, be related to the properties of the corresponding feature 413 and / or the properties of the environmental sensor. The feature 413 may therefore have a favorable reflectivity for a lidar sensor or a radar sensor, but may be poorly detectable for a camera sensor, for example due to low ambient light.

[0061] Alternatively or additionally, the detectability of feature 413 can be calculated taking into account the expected traffic flow on the corresponding roadway 403. Based on the corresponding data 409 of the expected, current or average traffic flow on the corresponding roadway 403, the traffic flow for the time point when vehicle 401 travels the corresponding roadway 403 can be calculated. For this calculation, for example, the average speed or the average number of vehicles expected on roadway 403 at a future time point can be used for the calculation of the average coverage. In this case, the average coverage describes the coverage of feature 413 arranged at the edge of roadway 403 by other vehicles arranged on average in the environment of vehicle 401 due to the traffic flow when traveling on roadway 403.

[0062] In the diagram B, such calculation of the detectability of individual features 413 for the environmental sensor 405 of the vehicle 401 traveling on the roadway 403 is graphically represented. In the illustrated diagram, the vehicle 401 is arranged on the left lane 404 of the roadway 403. In addition, three other vehicles of the expected traffic flow 409 are shown on the right lane 404 of the roadway 403. In addition, the diagram B shows three direction representations 410 of three different environmental sensors 405 of the vehicle 401. Here, the direction representation 410 points to the front area of ​​the vehicle 401, while the other two direction representations 410 point to the rear area of ​​the vehicle 401. In the illustrated diagram, for the environmental sensor 405 of the vehicle 401, the feature 413 arranged at the right lane edge of the roadway 403 is covered by other vehicles of the traffic flow 409. This is represented in the diagram B by an average coverage 414. The average coverage 414 can be indicated as a percentage, for example. In the illustrated diagram, only five of the six features 413 arranged at the left-hand side edge of roadway 403 are located within the region of direction representation 410. Therefore, features 413 that are not covered by direction representation 410 cannot be detected by vehicle 401 in the illustrated position P. According to the invention, the availability of features 413 of feature map 411 can be calculated in a position-dependent manner for different positions P of vehicle 401 on roadway 403. Thus, in diagram B, for position P of vehicle 401, only five of the six features 413 at the left-hand side edge of roadway 403 can be detected by environmental sensor 405 of vehicle 401.

[0063] According to one embodiment, for calculating the availability values ​​of different features 413, features of the features can be determined. For example, these features can include the type of feature 413, the number of features 413 in the area of ​​the roadway 403 to be traveled, the spatial extension or size of the features 413, or the reflectivity of the features 413. For determining the detectability, these features of the features 413 can be taken into account by calculating the corresponding detectability-corrected features. In the example of the number of features 413 as a feature, the detectability-corrected number of features 413 can be calculated as the number of features 413 that can be detected by the environment sensor 405 for the corresponding sensor type or direction representation 410 of the environment sensor 405 or for the calculated predicted traffic flow 409.

[0064] Thus, the availability value of each feature 413 of the selected roadway 403 calculated in this way can be indicated, for example, as a percentage of the number of features 413 of roadway 403. Thus, the corresponding availability information can indicate that a certain percentage of features 413 of feature map 411 is available for the positioning of vehicle 401 for the corresponding roadway 403.

[0065] Therefore, for corresponding route planning of vehicle 401, in addition to the calculated route with the shortest driving duration, a route with the highest availability of features 413 of the calculated route based on the calculated availability information of different roadways 403 of the corresponding route can also be provided to vehicle 401 or the driver.

[0066] The corresponding route data 421 may be provided in the corresponding vehicle 401 by a computer unit 415 designed as an external server unit.

[0067] Thus, external server unit 415 may be configured to calculate the availability of features 413 or objects arranged on the corresponding roadway for vehicle 401 and the corresponding route or roadway 403 to be traveled, and to determine the corresponding route with the maximum availability of features 413. This information may be provided to vehicle 401 communicating with external server unit 415.

[0068] According to the invention, a data connection, for example in the form of a wireless data connection, can be established between the vehicle 401 and a computing unit 415 designed as an external server unit for calculating a route. In this case, sensor information data 407 of the environmental sensors 405 of the vehicle 401 can be transmitted to the computing unit 415. In addition to the data 409 relating to the average traffic flow, the computing unit 415 or the external server unit can calculate the corresponding route with the greatest availability according to the method according to the invention for availability prediction and the method for route planning and provide this route to the vehicle 401 via wireless communication.

[0069] Figure 2 A flow chart of a method 100 for feature-based localization availability prediction of a vehicle 401 according to one embodiment is shown.

[0070] According to the present invention, in a first method step 101, map data 412 of a feature map 411 of a road traffic network is received, wherein the feature map 411 includes feature information of multiple features 413 of multiple lanes 403 on which a vehicle 401 can travel, and wherein the features 413 are configured to be detected by a vehicle 401 traveling on the lanes 403 through sensor data 406 of an environmental sensor 405 of the vehicle 401 and are used for positioning the vehicle 401.

[0071] In a further method step 103 , characteristics 413 for at least one roadway 403 on which vehicle 401 is to travel are ascertained based on characteristic information of characteristic map 411 .

[0072] In a further method step 105 , an availability value for feature 413 of at least one roadway 403 to be traveled by vehicle 401 is calculated as a function of an availability criterion, wherein the availability value indicates a quantitative measure of the availability of feature 413 for locating vehicle 401 when vehicle 401 travels on roadway 403 .

[0073] For this purpose, in the specific embodiment shown, in a further method step 109 , a sensor type and / or a direction indicator 410 of surroundings sensor 405 of vehicle 401 is ascertained.

[0074] Furthermore, in a further method step 113 , the traffic flow is ascertained.

[0075] For this purpose, in method step 115 , the average number and / or the average speed of vehicles on roadway 403 on which the vehicle is to be driven is determined.

[0076] In a further method step 117 , an average coverage 414 of feature 413 by vehicles passing through the traffic flow is calculated based on the average number or average speed.

[0077] Furthermore, in method step 119, a characterization of feature 413 is determined. The characterization may include, for example, the number, the quality or the spatial extension of the feature.

[0078] In method step 111 , the detectability of individual features by surroundings sensor 405 of vehicle 401 is calculated based on the sensor type or the direction characterization and / or based on the calculated traffic flow or average coverage.

[0079] In a further method step, at least one representation of feature 413 is compared with the detectability-corrected representation calculated in method step 119. This comparison can provide usability values ​​in the form of quantitative values ​​for the different representations. The usability value can be specified, for example, as a percentage.

[0080] In a further method step 107 , availability information relating to features 413 of feature map 411 for roadway 403 to be traveled by vehicle 401 is output, said availability information being based on the availability value calculated in method step 105 .

[0081] Figure 3 A flow chart of method 200 for route planning for autonomously controllable vehicle 401 according to one specific embodiment is shown.

[0082] According to the present invention, firstly in method step 201 , method 100 for feature-based localization availability prediction of vehicle 401 is carried out on a plurality of possible routes of vehicle 401 between a predetermined starting point and a predetermined end point.

[0083] In a further method step 203 , route 421 of vehicle 401 having the highest predicted availability with the feature-based position determination of vehicle 401 is determined based on the availability prediction performed.

[0084] According to one specific embodiment, the control of vehicle 301 may include the execution of a maneuver planning. In particular, a driving maneuver may be planned and executed by vehicle 301, which increases the availability of features of a feature map for a roadway to be traveled by vehicle 301. Such a driving maneuver may include, for example, a change to a specific lane of the roadway to be traveled, wherein an increased availability of features is expected for the specific lane. Alternatively, the control may include other driving maneuvers that may increase the availability of features, such as reducing the planned speed or activating the vehicle headlights, so that objects arranged along the roadway to be traveled can be better seen by the vehicle's environmental sensors.

[0085] Figure 4 A flow chart of method 300 for controlling vehicle 401 according to one specific embodiment is shown.

[0086] According to the present invention, method 200 for route planning for an autonomously controllable vehicle is first carried out in method step 301 .

[0087] In a further method step 303 , vehicle 401 is controlled based on the selected route.

[0088] Figure 3A schematic diagram of a computer program product 500 is shown, which includes instructions that, when the program is executed by a computing unit, cause the computing unit to implement method 100 for availability prediction of feature-based positioning of vehicle 401 and / or a method for route planning for an autonomously controllable vehicle 401 and / or a method for controlling vehicle 401.

[0089] In the illustrated embodiment, the computer program product 500 is stored on a storage medium 501. The storage medium 501 may be any storage medium known in the art.

Claims

1. A method (100) for feature-based positioning availability prediction of a vehicle (401), the method comprising: Receiving (101) map data (412) of a feature map (411) of a road traffic network, wherein the feature map (411) includes feature information of a plurality of features (413) of a plurality of roadways (403) on which a vehicle (401) can travel, and wherein the features (413) are arranged to be detected by a vehicle (401) traveling on the roadways (403) through sensor data (406) of an environmental sensor (405) of the vehicle (401) and used for positioning the vehicle; Determining (103) characteristics (413) of at least one roadway (403) on which the vehicle (401) is to travel based on the characteristic information of the characteristic map (411); calculating (105) an availability value for a feature (413) of at least one roadway (403) on which the vehicle (401) is to travel, in relation to an availability criterion, wherein the availability value indicates a quantitative measure of the availability of the feature (413) for positioning the vehicle (401) when the vehicle (401) travels along the roadway (403); and Availability information related to the characteristics (413) of the roadway (403) to be traveled is output (107), wherein the availability information includes the availability value.

2. The method (100) according to claim 1, wherein: The availability criterion comprises detectability of the feature (413) by an environmental sensor (405) of the vehicle (401) based on a sensor type and / or orientation characterization (410) of the vehicle (401), and wherein the calculation (105) of the availability value comprises: Ascertaining (109) a sensor type and / or a direction indicator (410) of at least one surroundings sensor (405) of the vehicle (401); and For a sensor type and / or orientation characterization (410) of the at least one environmental sensor (405), a detectability of a feature (413) of a roadway (403) on which the vehicle (401) is to travel is determined (111).

3. The method (100) according to claim 1 or 2, wherein: The availability criterion comprises the detectability of the feature by the vehicle's surrounding sensors taking into account the traffic flow on the roadway to be traveled, and wherein the calculation (105) of the availability value comprises: Determining (113) the traffic flow on the roadway through which the vehicle is to pass; and The detectability of a feature of the roadway on which the vehicle is to travel is determined (111) by calculating a coverage of the feature of the roadway by the traffic flow on the roadway.

4. The method (100) according to claim 3, wherein: The obtaining (113) of the traffic flow (409) includes: determining (115) an average number and / or an average speed of vehicles per time unit on a roadway to be travelled by the vehicle; and wherein the determination (111) of detectability comprises: An average coverage (414) of the feature (413) of the roadway is calculated (117) based on an average number and / or an average speed of vehicles per time unit.

5. The method (100) according to any one of the preceding claims 2 to 4, wherein: The calculation of the availability value (105) includes: Determine (119) at least one characterization of the feature (413), wherein the at least one characterization includes: the type of the feature, the number of the features, the number of the features of a specific type or category; the re-recognition value of the feature, the extension and / or size of the feature, the reflectivity of the feature (413); and wherein the detectability determination (111) is performed in relation to at least one specific characterization of the feature, and a detectability-corrected characterization is calculated.

6. The method (100) according to claim 5, wherein: The calculation of the availability value (105) includes: The at least one representation of the feature (413) of the feature map (411) is compared (121) with a corresponding detectability-corrected representation.

7. The method (100) according to any one of the preceding claims 2 to 6, wherein: The determination (111) of detectability is performed for at least one previously known position (P) of the vehicle (401) on the roadway (403) or for different previously known positions of the vehicle (401) on different lanes (404) of the roadway (403).

8. The method (100) according to any one of the preceding claims 2 to 7, wherein: The determination (111) of the detectability is carried out by means of a correspondingly trained artificial intelligence (419), wherein the artificial intelligence (419) is trained based on environmental sensor data (406) of an environmental sensor (403) of at least one vehicle (401), and wherein the environmental sensor data (406) have been recorded during a plurality of trips of the vehicle (401) along the at least one roadway (403) during a plurality of different traffic flows (409).

9. The method (100) according to any one of the preceding claims, wherein: The features (413) are characterizing objects arranged at the edge of the roadway (403) and include: buildings, traffic signs, and roadway markings.

10. A method (200) for route planning for an autonomously controllable vehicle (401), the method comprising: implementing (201) the method (100) for feature-based positioning availability prediction of a vehicle (401) according to any one of the preceding claims 1 to 9 on a plurality of possible routes of the vehicle (401) between a predetermined starting point and a predetermined end point; and Based on the performed availability prediction, a route (421) of the vehicle (401) is ascertained (203) which has the highest predicted availability for the feature-based positioning of the vehicle (401).

11. A method (300) for controlling a vehicle, the method comprising: implementing (301) the method (200) for route planning for an autonomously controllable vehicle according to claim 10; and The vehicle (401) is controlled (303) based on the selected route.

12. The method (300) of claim 11, wherein: The steering of the vehicle comprises implementing a maneuver planning, wherein the maneuver planning comprises a driving maneuver of the vehicle that enables an optimal availability of features of the features of the feature map.

13. A computing unit (415, 417) configured to implement the method (100) for availability prediction for feature-based positioning of a vehicle according to any of the preceding claims 1 to 9 and / or the method (200) for route planning for an autonomously controllable vehicle according to claim 10 and / or the method (300) for controlling a vehicle according to claim 11 or 12.

14. A computer program product (500), comprising instructions which, when the program is executed by a data processing unit, cause the data processing unit to implement the method (100) for availability prediction of feature-based positioning of a vehicle according to any one of claims 1 to 9 and / or the method (200) for route planning for an autonomously controllable vehicle according to claim 10 and / or the method (300) for controlling a vehicle according to claim 11 or 12.