Method and system for route planning of autonomous driving vehicle

Abstract

The present disclosure relates to a route planning method for an autonomous driving vehicle, including determining a plurality of candidate driving routes from a starting point to a destination; determining availability of a driving assistance function for automatic driving for each of the plurality of candidate driving routes; and selecting, from among the plurality of candidate travel routes, a candidate travel route having the maximum availability of a driving assistance function for automatic driving as a final travel route.

Description

Technical Field

[0001] The present invention relates to a method for route planning of an autonomously driven vehicle, a storage medium for executing the method, a system for route planning of an autonomously driven vehicle, and a vehicle having such a system. The present disclosure relates in particular to a route calculation for the efficient use of one or more driver assistance functions for autonomous driving. Background Art

[0002] Driver assistance systems for automated driving are becoming increasingly important. Automated driving can be achieved using different degrees of automation. Exemplary degrees of automation are assisted driving, semi-automated driving, conditional automated driving, highly automated driving or fully automated driving. The five degrees of automation mentioned above correspond to SAE levels 1 to 5 according to the SAE J3016 (SAE - Society of Automotive Engineers) standard of April 30, 2021. In fully automated driving (SAE level 5), the system can perform all aspects of the dynamic driving task that are also controlled by the human driver in any lane and environmental conditions.

[0003] Today's routing systems are able to quickly and efficiently calculate the best route from the starting point to the route destination as well as a forecast of the arrival time and / or travel time. For route planning, only the topological properties (e.g. curve relationships) and dynamic properties (e.g. current speed, construction sites) of the route segments are usually taken into account. Further route analysis is usually not performed, which can lead, in particular in conjunction with driver assistance systems for automated driving, depending on their functional characteristics, to inefficient route planning and / or dissatisfaction on the part of the users of the driver assistance systems. Summary of the invention

[0004] The object of the present disclosure is to provide a method for route planning of an autonomous vehicle, a storage medium for executing the method, a system for route planning of an autonomous vehicle, and a vehicle having such a system, which enable efficient route planning for an autonomous vehicle. The object of the present disclosure is, in particular, to enable maximum availability of the autonomous driving mode and thus enable robustness of the available system.

[0005] This object is achieved by the subject matter of the independent claims. Advantageous embodiments are described in the dependent claims.

[0006] According to an independent aspect of the present disclosure, a method for route planning of a vehicle, especially a motor vehicle, for autonomous driving is provided. The method comprises determining a plurality of candidate driving routes from a starting point to a destination; determining the availability of a driving assistance function for autonomous driving for each of the plurality of candidate driving routes; and selecting a candidate driving route with the greatest availability of the driving assistance function for autonomous driving from the plurality of candidate driving routes as a final driving route.

[0007] According to the present invention, in route planning, multiple candidate driving routes are evaluated with respect to the availability of driving assistance functions for autonomous driving. Optionally, also in combination with minimal risk (for example, driving routes that pass by schools around 7:45 a.m. can be avoided), a driving route that provides the maximum availability of driving assistance functions is selected from multiple candidate driving routes as the final route. Therefore, efficient route planning for vehicles for autonomous driving can be achieved, thereby improving user satisfaction. In addition, traffic safety can be improved due to the maximum availability of driving assistance functions, because human driving errors can be avoided.

[0008] Optionally, the method according to the invention can involve multiple assistance systems. For example, calculations for route planning can be generated from different signals of the assistance systems. Here, the learned algorithm can optimize, for example also optimize the calculations for route planning in real time.

[0009] Within the scope of this document, the term "autonomous driving" is understood to mean driving with automatic longitudinal and / or lateral guidance. For example, autonomous driving can be longer driving on specific route types such as suburban roads, urban roads, motorways, urban expressways, country roads or city streets, or time-limited driving within a parking range. The term "autonomous driving" includes autonomous driving with any degree of automation. Exemplary degrees of automation are assisted driving, semi-automatic driving, conditional automated driving, highly automated driving and fully automated driving (with a correspondingly increasing degree of automation). The five degrees of automation mentioned above correspond to SAE levels 1 to 5 according to the SAE J3016 (SAE - Society of Automotive Engineers) standard of April 30, 2021.

[0010] In assisted driving (SAE Level 1), the system performs longitudinal or lateral guidance in certain driving situations. In semi-automated driving (SAE Level 2), the system assumes longitudinal and lateral guidance in certain driving situations, wherein the driver must constantly monitor the system as in assisted driving. In conditionally automated driving (SAE Level 3), the system assumes longitudinal and lateral guidance in certain driving situations without the driver having to constantly monitor the system; however, the driver must be able to assume control of the vehicle for a certain period of time and upon request of the system. In highly automated driving (SAE Level 4), the system assumes control of the vehicle in certain driving situations even when the driver does not react to a request for intervention, so that the driver is no longer available as a backup. In fully automated driving (SAE Level 5), the system can perform all aspects of the dynamic driving task that are also controlled by the human driver in any lane conditions and environmental conditions.

[0011] Furthermore, within the scope of this document, the term "at least semi-automated driving or maneuvering" is also understood to mean semi-automated driving, conditionally automated driving, highly automated driving, fully automated driving. In other words, the term "at least semi-automated driving" is understood to mean a degree of automation starting from SAE Level 2 (inclusive).

[0012] Preferably, the driver assistance function taken into account in the route planning according to the invention is designed for automated driving according to SAE Level 2, SAE Level 3, SAE Level 4 or SAE Level 5.

[0013] Preferably, the method for route planning uses a routing algorithm. In such a routing algorithm, for example, a path selection can be made by calculating a decision criterion (metric) with weighting factors for each possible path. This can also change over runtime, since the algorithm learns from the driver's preferences and uses this data knowledge.

[0014] Preferably, the availability of a driver assistance function for automated driving is determined based on the functional characteristics of the driver assistance function or the driver assistance system and / or the operational design domain (ODD) of the driver assistance function. In other words, answering the question of whether a driving route or a route section thereof is suitable for automated driving may be dependent on the functional characteristics and / or the ODD of the driver assistance function or the driver assistance system (e.g. SAE level 2, 3 or 4). Some driver assistance functions or corresponding functional characteristics may, for example, enable assistance when driving on roads with different specific lane widths and / or different speed ranges (e.g. minimum speed or maximum speed) than other driver assistance functions or corresponding functional characteristics.

[0015] Preferably, each candidate driving route comprises a plurality of route segments, which may differ in their route characteristics (e.g., lane width, maximum permissible speed, etc.). In particular, there are a plurality of candidate driving routes between a starting point and a destination, wherein each of the plurality of candidate driving routes may have a plurality of route segments. The plurality of candidate driving routes may have at least partially different route segments.

[0016] For each of the plurality of route segments of the candidate driving route, it can be determined whether autonomous driving can be achieved according to the ODD. Each route segment that is not a plurality of route segments of the candidate driving route may be suitable for autonomous driving, for example, due to route characteristics, speed ranges and / or weather conditions. The route planning according to the present invention evaluates the plurality of route segments of each candidate driving route with respect to their possibility for autonomous driving, thereby ultimately determining as the final driving route the candidate driving route whose route segments as a whole maximize the availability for autonomous driving.

[0017] Preferably, determining a plurality of candidate driving routes from the starting point to the destination includes obtaining possible driving routes from the starting point to the destination; and selecting a plurality of candidate driving routes from the possible driving routes based on at least one selection criterion. Thus, unsuitable driving routes can be immediately classified before the availability check, thereby further improving the efficiency of route planning.

[0018] Preferably, at least one selection criterion is selected from the group consisting of or consisting of a time-dependent selection criterion, a route-specific selection criterion and a driver-individualized selection criterion.

[0019] The selection criteria over time may be, for example, the (e.g. latest) arrival time at the destination and / or the maximum driving duration or travel time. In a further example, the fastest route may be used as a reference in order to select a plurality of candidate driving routes from the possible driving routes. For example, all driving routes may be sorted whose estimated driving duration or travel time is x times the driving duration or travel time of the fastest driving route. x is greater than 1 here and may be an integer (e.g. 2) or a rational number (e.g. 1.5).

[0020] Route-specific selection criteria may be related to the road conditions, for example. For example, all driving routes may be classified whose (at least section-like) road conditions are disadvantageous for the vehicle and / or the driver, for example due to potholes and / or gravel surfaces.

[0021] The driver-individualized selection criteria may include the driver's preferences. For example, it may be known that the driver avoids certain road categories, such as highways. In this case, all driving routes may be classified, which (at least in sections) include such road categories.

[0022] Preferably, the availability of the driver assistance function for automated driving is a time-dependent availability or a distance-dependent availability. The time-dependent availability relates to a time period of the driving duration or the travel time during which automated driving is possible. In contrast, the distance-dependent availability relates to a driving distance or a driving route during which automated driving is possible.

[0023] Preferably, the availability of the driving assistance function for autonomous driving is determined based on internal information stored in the vehicle and / or collected by the vehicle. The information stored in the vehicle may include, for example, but is not limited to, digital map data, historical information about driving routes, information about driver preferences, etc. The information collected by the vehicle may include, but is not limited to, historical information about driving routes, (historical) information about driver preferences, etc.

[0024] Additionally or alternatively, the availability of the driver assistance function for automated driving is determined based on external information provided to the vehicle by at least one external unit. For example, the at least one external unit may include or be a central unit, such as a backend and / or at least one other vehicle. In some embodiments, the term "central unit" also includes signals from infrastructure to X, i.e., for example, from a control unit installed in a city.

[0025] The vehicle can be connected to at least one external unit via a communication connection in order to receive external information. The communication connection can be realized, for example, by means of a mobile network (such as an LTE network or a 5G network). In another example, Car2Car communication can be used to receive external information directly from other vehicles.

[0026] Preferably, the external information is provided by the fleet. In particular, the vehicles of the fleet can transmit data relevant to the availability check according to the invention (e.g., system crashes on a specific route section) to the backend. The backend can collect the data and, if necessary, provide it to other vehicles for the availability check according to the invention.

[0027] Preferably, the availability of the driving assistance function for automated driving is determined based on the road categories along the candidate driving route (eg according to the Functional Road Class FRC, with a priority ranking according to a low FRC1).

[0028] Additionally or alternatively, the availability of a driving assistance function for autonomous driving may be determined based on intersection characteristics on a candidate driving route, such as the presence of traffic lights at the intersection, a left or right turn at the intersection, the presence of a turning lane at the intersection, etc.

[0029] Additionally or alternatively, the availability of a driver assistance function for automated driving may be determined based on turning situations along the candidate driving routes, for example based on left or right turns, the presence of a turning lane, etc. For example, route sections or driving routes without left turns may be prioritized.

[0030] Additionally or alternatively, the availability of driver assistance functions for automated driving can be determined based on the release of driver assistance functions along the candidate driving route. For example, a comparison can be performed with stored information about the road clearing of an ADAS system (Advanced Driver Assistance System), wherein a prioritization of the released route sections can be performed.

[0031] Additionally or alternatively, the availability of driver assistance functions for automated driving may be determined based on traffic flow along the candidate driving route. Preferably, traffic flow is divided into motorized traffic flow (passenger cars, trucks, etc.) and non-motorized traffic flow (pedestrians, cyclists, etc.). In some embodiments, route sections with low non-motorized traffic flow may be prioritized. For example, route sections around schools may be avoided at certain times.

[0032] Additionally or alternatively, the availability of a driver assistance function for automated driving may be determined based on the average speed along the candidate driving routes. For example, route sections or corresponding driving routes with availability for a level 3 speed range may be prioritized.

[0033] Additionally or alternatively, the availability of a driver assistance function for automated driving may be determined based on the turning radius on the candidate driving route. For example, it may be that some driver assistance functions cannot automatically navigate a narrow turning radius with a defined setting or recommended speed, so that route sections with such a narrow turning radius may be avoided.

[0034] Additionally or alternatively, the availability of the driving assistance function for autonomous driving may be determined based on a forced deactivation scenario of the driving assistance function for autonomous driving along the candidate driving route. Forced deactivation here means terminating the autonomous driving due to the current situation and transferring the vehicle guidance to the driver.

[0035] For example, route sections that may lead to a mandatory deactivation of the driver assistance system may be avoided. For example, a mandatory deactivation may be implemented due to weather conditions (e.g., temperature, precipitation, wind, etc.), climate conditions (e.g., wet, slippery, snowy, frost on the ground, etc.) and / or road conditions (e.g., road characteristics, quality of ground markings, lane width, etc.).

[0036] Additionally or alternatively, the availability of the driver assistance function for automated driving may be determined based on historical deactivations of the driver assistance function for automated driving along the candidate driving route. For example, route sections where forced deactivations often occur may be known from fleet data. Such route sections may be avoided.

[0037] Additionally or alternatively, the availability of driver assistance functions for automated driving can be determined based on the sun position along the candidate driving route. For example, it is possible that a camera-based environment sensor system no longer provides robust environment detection in the case of low sun positions and direct light radiation, which can lead to a mandatory deactivation of the driver assistance function. Route sections where the sun position could lead to such a mandatory deactivation can therefore be avoided.

[0038] Preferably, the method also includes outputting driver instructions about the final driving route. In particular, the final driving route can be suggested to the driver. The driver can select or confirm the final driving route, thereby, for example, starting destination guidance. For manual selection of a driving route by the driver, information about the availability of driving assistance for each driving route can be provided to the driver, for example about the duration of availability and / or a prediction of the route.

[0039] Preferably, the vehicle comprises at least one output device for outputting the driver's instructions. The at least one output device may comprise at least one display device and / or at least one loudspeaker. The at least one display device may comprise a display, in particular an LCD display, a plasma display or an OLED display. In addition or as an alternative, the at least one display device may comprise a projection device designed to display the information directly in the driver's field of vision, in particular to project it onto the windshield. In some embodiments, the at least one output device may be a central information output device of an infotainment system, such as a head unit or a column-to-column display. Preferably, the at least one output device is fixedly mounted in the vehicle.

[0040] Preferably, the method further comprises detecting environmental data by means of an environmental sensor system of the vehicle; and performing automated driving along the final driving route (or on a route section of the final driving route suitable for automated driving) based on the environmental data. Thus, the vehicle's environmental data or a corresponding sensor-based environmental model can form an influencing factor, for example, in order to prevent a collision of the vehicle with an object or other road participant.

[0041] Preferably, the environmental sensor system comprises at least one LiDAR system and / or at least one radar system and / or at least one camera and / or at least one ultrasound system and / or at least one laser scanner. The environmental sensor system may provide environmental data (also referred to as "surrounding data") describing the vehicle's surrounding area.

[0042] Preferably, the method further comprises controlling the autonomously driven vehicle so that the vehicle follows the final driving route or a route section of the final driving route suitable for autonomous driving. In particular, the vehicle can follow the final driving route by comparing its current position with the planned position and adapting the steering and / or speed.

[0043] According to a further independent aspect of the present disclosure, a software (SW) program is described. The software program can be designed to be executed on one or more processors and thereby execute the method for route planning for an autonomously driven vehicle described in this document.

[0044] According to another independent aspect of the present disclosure, a storage medium is described. The storage medium may include a software program designed to be executed on one or more processors, and thereby execute the method for route planning for an autonomous vehicle described in this document.

[0045] According to a further independent aspect of the present disclosure, software with a program code is described. When the software is run on one or more software-controlled devices, the software is designed to execute a method for route planning for an autonomously driven vehicle.

[0046] According to another independent aspect of the present disclosure, a system for route planning of an autonomous vehicle is described. The system includes one or more processors; and at least one memory connected to the one or more processors and containing instructions executable by the one or more processors to execute the method for route planning of an autonomous vehicle described in this document.

[0047] In particular, the system is designed to perform the method for route planning for an autonomously driven vehicle described in this document. The method can implement aspects of the system described in this document.

[0048] A processor or processor module is a programmable computing unit, ie a machine or electronic circuit that controls other elements according to given commands and carries out an algorithm (process) therein.

[0049] Preferably, the system is a driving assistance system for automated driving, or is at least partially included in such a driving assistance system, or is communicatively connected to the driving assistance system.

[0050] Preferably, the entire system is integrated in the vehicle. However, the present disclosure is not limited thereto, and a part of the system or the entire system, for example a routing module for route planning according to the present invention, may be implemented outside the vehicle, for example in a central unit or a backend. In this case, there may be a communication connection between the vehicle and the central unit in order to transmit the lane-accurate route to the vehicle and enable the functions of the driver assistance system described in this document to be implemented. The communication connection may be implemented, for example, by means of a mobile network, such as an LTE network or a 5G network.

[0051] According to another independent aspect of the present disclosure, a vehicle, in particular a motor vehicle, is described. The vehicle includes a system for route planning of an autonomously driven vehicle and / or a driver assistance system for autonomously driven vehicle according to an embodiment of the present disclosure.

[0052] The term vehicle includes passenger cars, trucks, buses, RVs, motorcycles, etc., which are used to transport people, goods, etc. In particular, the term includes motor vehicles used to transport people. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Embodiments of the present disclosure are shown in the accompanying drawings and described in detail below.

[0054] Figure 1 A vehicle having a driving assistance system for autonomous driving according to an embodiment of the present disclosure is schematically shown, and

[0055] Figure 2 A flow chart showing a method for route planning for an autonomously driven vehicle according to an embodiment of the present invention is shown.

[0056] Unless otherwise indicated, the same reference numerals are used subsequently for identical and identically acting elements. DETAILED DESCRIPTION

[0057] Figure 1 A vehicle 10 having a driving assistance system 100 for automated driving according to an embodiment of the present disclosure is schematically shown.

[0058] In automated driving, the longitudinal and / or lateral guidance of the vehicle 10 is carried out automatically. Therefore, the driver assistance system 100 assumes the responsibility for vehicle guidance. To this end, the driver assistance system 100 controls the drive 20, the transmission 22, the hydraulic service brake 24 and the steering device 26 via an intermediate unit (not shown).

[0059] In order to plan and execute the automated driving, the driver assistance system 100 receives environmental information from an environmental sensor system that observes the vehicle environment. In particular, the vehicle may include at least one environmental sensor 12, which is designed to record surrounding data describing the vehicle environment. The at least one environmental sensor 12 may include, for example, one or more laser radar (LiDAR) systems, one or more radar systems, one or more laser scanners, one or more ultrasonic sensors and / or one or more cameras.

[0060] Figure 2 The flowchart of a method 200 for route planning of an autonomous driving vehicle according to an embodiment of the present invention is schematically shown. The method 200 can be implemented by corresponding software, which can be executed by one or more processors (eg, CPU).

[0061] Method 200 includes, in box 210, determining a plurality of candidate driving routes from a starting point to a destination; includes, in box 220, determining the availability of a driving assistance function for autonomous driving for each of the plurality of candidate driving routes; and includes, in box 230, selecting a candidate driving route with the greatest availability of a driving assistance function for autonomous driving from the plurality of candidate driving routes as a final driving route.

[0062] In an exemplary embodiment of the method 200 according to the present invention, the driver can first select the "maximum availability of driving assistance" option in the configuration menu. The method 200 can then apply a routing algorithm that calculates a driving route so that the vehicle can remain in the automated driving mode as long as possible and without interruption.

[0063] For this purpose, a selection of possible driving routes to the entered destination can first be determined according to a time criterion. For example, a driving route can first be selected whose estimated time consumption is less than twice the time required for the fastest route. The selected choice can then be evaluated with regard to the maximum usability of the driver assistance function, for example by comparing the selected driving route with information from map material in the vehicle and / or data from the backend.

[0064] A number of different criteria or aspects may be considered when evaluating the selected driving route. For example, these criteria include road category, type and / or complexity of intersections and turning situations, road clearance, traffic flow, average speed, turning radius, turning process, forced deactivation of driver assistance functions, system crashes caused by customer fleet data, etc. However, the present disclosure is not limited to these criteria, and other criteria may be used to evaluate the selected driving route suitable for checking the availability of driver assistance functions for automated driving.

[0065] The route determined with maximum driving assistance can then be incorporated into the route guidance of the vehicle.

[0066] According to the present invention, in route planning, a plurality of candidate driving routes are evaluated with respect to the availability of a driving assistance function for autonomous driving. As a final driving route, a driving route that provides the maximum availability of a driving assistance function is selected from the plurality of candidate driving routes. Therefore, efficient route planning of a vehicle for autonomous driving can be achieved, whereby user satisfaction can be improved. In addition, due to the maximum availability of the driving assistance function, traffic safety can be improved because human driving errors can be avoided.

[0067] Although the present invention has been described and explained in detail by preferred embodiments, the present invention is not limited to the disclosed examples, and those skilled in the art can derive other variations therefrom without departing from the scope of protection of the present invention. It is therefore clear that there are multiple possibilities for variation. It is also clear that the exemplary embodiments mentioned are actually only examples, which should not be understood in any way as limitations on the scope of protection, application possibilities or configuration of the present invention. On the contrary, the above description and the accompanying drawings enable those skilled in the art to specifically implement the exemplary embodiments, wherein those skilled in the art can make various changes, such as various changes in the functions or arrangements of the various elements mentioned in the exemplary embodiments, without departing from the scope of protection, which is defined by the claims and their legal equivalents, such as further explanations in the specification.

Claims

1. A method (200) for route planning of an autonomous vehicle, comprising: Determining (210) a plurality of candidate travel routes from a starting point to a destination; determining ( 220 ) availability of a driving assistance function for automated driving for each candidate driving route of the plurality of candidate driving routes; as well as A candidate driving route having the greatest availability of a driving assistance function for automated driving is selected ( 230 ) from among the plurality of candidate driving routes as a final driving route.

2. The method (200) according to claim 1, wherein: Determining multiple candidate driving routes from an origin to a destination includes: Find possible driving routes from the starting point to the destination; and The plurality of candidate driving routes are selected from the possible driving routes based on at least one selection criterion.

3. The method (200) according to claim 2, wherein: The at least one selection criterion is selected from the group consisting of: a time-dependent selection criterion, a route-specific selection criterion, and a driver-individualized selection criterion.

4. The method (200) according to any one of claims 1 to 3, wherein: The availability of the driver assistance function for automated driving is a time-dependent availability or a distance-dependent availability.

5. The method (200) according to any one of claims 1 to 4, wherein: The availability of a driving assistance function for automated driving is determined based on internal information stored in and / or collected by the vehicle and / or external information provided to the vehicle from at least one external unit.

6. The method (200) according to claim 5, wherein: The external information is provided by the central unit and / or the fleet.

7. The method (200) according to any one of claims 1 to 6, wherein: The availability of a driving assistance function for automated driving is determined based on at least one of the following aspects: - the type of roads along the candidate driving route; and / or - intersection characteristics on the candidate driving route; and / or - Turning conditions along the candidate driving route; and / or - a driving assistance function is released along the candidate driving route; and / or - traffic flow along the candidate driving route, in particular motorized traffic flow and / or non-motorized traffic flow; and / or - average speed along the candidate driving route; and / or - a turning radius on the candidate driving route; and / or - mandatory deactivation scenarios of driving assistance functions for automated driving along the candidate driving route; and / or - historical deactivation of driver assistance functions for automated driving along the candidate driving route; and / or - The position of the sun along the candidate travel route.

8. A storage medium comprising a software program, the software program being designed to be executed on one or more processors and thereby to execute the method (200) for route planning for an autonomously driven vehicle according to any one of claims 1 to 7.

9. A system for route planning of an autonomous vehicle, comprising: one or more processors; and At least one memory connected to the one or more processors and containing instructions executable by the one or more processors to perform the method (200) for route planning for an autonomously driven vehicle according to any one of claims 1 to 7.

10. A vehicle, in particular a motor vehicle, comprising a system according to claim 9.

Images