Method and system for routing an autonomous driving vehicle

Abstract

The present disclosure relates to a method for routing an autonomous driving vehicle, in particular a motor vehicle. The method includes determining a lane-precise route from a starting point to a destination by using lane-precise map data, where determining the lane-precise route includes: for a plurality of travel sections between the starting point and the destination, ascertaining a lane suitable for automatic driving among the plurality of travel sections; and determining a lane-precise route, taking into account the lanes suitable for automatic driving of the plurality of travel sections, such that the time and / or travel on the lane-precise route is maximum for automatic driving.

Description

Technical Field

[0001] The present disclosure relates to a method for planning a route for an autonomous vehicle, a storage medium for executing the method, a system for route planning for an autonomous vehicle, and a vehicle having such a system. In particular, the present disclosure relates to lane-accurate route calculation for an autonomous vehicle. Background Art

[0002] Driving assistance systems for automated driving are becoming increasingly important. Automated driving can be performed at different levels of automation. Exemplary levels of automation are assisted automated driving, partially automated driving, conditionally automated driving, highly automated driving or fully automated driving. The five levels of automation mentioned above correspond to SAE Levels 1 to 5 according to the SAE J3016 standard (SAE - Society of Automotive Engineering) as of April 30, 2021. In fully automated driving (SAE Level 5), the system can perform all aspects of the dynamic driving task under any road and environmental conditions, which are also mastered by the human driver.

[0003] Today's route planning systems are able to quickly and efficiently calculate an optimized route from a starting point to a destination and predict arrival times and / or travel times. For route planning, only the topological properties (e.g., fork junctions) and dynamic properties (e.g., current speed, road construction) of the travel segment are generally taken into account. For example, no further consideration of structural conditions is made, which, in particular in conjunction with driver assistance systems for automated driving, can lead to inefficient route planning and / or dissatisfaction of the users of the driver assistance systems, depending on their functionality. Summary of the invention

[0004] The object of the present disclosure is to describe a method for planning a route for an autonomous vehicle, a storage medium for executing the method, a system for route planning for an autonomous vehicle, and a vehicle having the system, which enable efficient route planning for the autonomous vehicle. In particular, the object of the present disclosure is to achieve maximum availability of the autonomous driving mode.

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

[0006] According to an independent aspect of the present disclosure, a method for planning a route for an autonomous vehicle, in particular a motor vehicle, is disclosed. The method comprises determining a lane-accurate route from a starting point to a destination by using lane-accurate map data, wherein determining the lane-accurate route comprises: for a plurality of travel segments between the starting point and the destination, finding lanes suitable for autonomous driving in the plurality of travel segments; and determining the lane-accurate route in consideration of the lanes suitable for autonomous driving, so that the time and / or travel on the lane-accurate route is maximized for autonomous driving.

[0007] According to the invention, lane-accurate map data, for example map data with lane widths, lane markings, road surface and / or curve radii, are taken into account during route planning. Based on the lane-accurate map data, it is determined for each lane of a travel section whether automated driving is possible in the respective lane. This information is used to plan routes accurately, wherein travel sections with lanes suitable for automated driving are selected in a targeted manner for these routes. The vehicle can then drive along the route through lanes suitable for automated driving, for example by performing automatic and / or manual lane changes in the case of a multi-lane travel section. In this way, maximum availability of the automated driving mode can be achieved.

[0008] In this text, "autonomous driving" is to be understood in the context of this text as driving with automatic longitudinal and / or lateral guidance. For example, autonomous driving can be driving for a longer period of time on the highway or driving for a limited time in the area of ​​parking. The term "autonomous driving" includes autonomous driving with any degree of automation. Exemplary degrees of autonomous driving are assisted autonomous driving, partial autonomous driving, conditional autonomous driving, highly automated driving and fully automated driving (with a respectively increasing degree of autonomous driving). According to April 30, 2021, the above five degrees of automation correspond to SAE levels 1 to 5 in the SAE J3016 standard (SAE - Society of Automotive Engineers).

[0009] In assisted driving (SAE Level 1), the system performs longitudinal or lateral guidance in certain driving situations. In partially automated driving (SAE Level 2), the system takes over longitudinal and lateral guidance in certain driving situations, where the driver must constantly monitor the system as in assisted driving. In conditionally automated driving (SAE Level 3), the system takes over longitudinal and lateral control in certain driving situations, where the driver does not have to constantly monitor the system; however, the driver must be able to take over vehicle guidance at a request made by the system within a certain time. In highly automated driving (SAE Level 4), the system takes over vehicle guidance in certain driving situations, even if the driver does not respond to a request for intervention. In fully automated driving (SAE Level 5), the system can perform all aspects of the dynamic driving task that are also mastered by the human driver under every road and environmental condition.

[0010] Furthermore, the term "at least partially automated driving or maneuvering" is to be understood in the context of this document as partially automated driving, conditionally automated driving, highly automated driving, and fully automated driving. In other words, the term "at least partially automated driving" is to be understood as the degree of automated driving from and including SAE Level 2.

[0011] Preferably, the lane-accurate route is determined by using a routing algorithm.

[0012] Preferably, a lane suitable for automated driving is determined based on the functional properties of the driver assistance system. In other words, the answer to the question "Is the lane suitable for automated driving?" can depend on the functional properties of the driver assistance system (e.g. SAE Level 2, 3 or 4). For example, some driver assistance systems or corresponding functional properties enable driving through lanes with a smaller lane width than other driver assistance systems or corresponding functional properties.

[0013] Preferably, the plurality of travel sections comprises at least one multi-lane travel section. The at least one multi-lane travel section comprises two or more lanes for the direction of travel of the vehicle. For each lane of the multi-lane travel section, it is determined whether automated driving is possible. For example, not every lane of the multi-lane travel section is suitable for automated driving. According to the route planning of the invention, lanes in the multi-lane travel section are selected for driving through which the time and / or distance of automated driving are optimized.

[0014] A unique route can be realized between the starting point and the destination point, which has a plurality of travel sections, which have at least one multi-lane travel section. According to the route planning of the present invention, such lanes in at least one multi-lane travel section that optimize the time and / or distance of the automated driving are selected for driving.

[0015] In some embodiments, multiple routes may be implemented between the starting point and the destination, wherein each of the multiple routes has multiple travel sections. The multiple routes may at least partially have different travel sections. According to the route planning of the present invention, such a route is selected from the multiple routes that optimizes the time and / or travel of the automated driving.

[0016] Preferably, the lane accurate map data comprises one or more lane accurate attributes. The one or more lane accurate attributes may be selected from the group consisting of: lane type, lane width, lane marking, road surface, turning radius, and construction site.

[0017] Preferably, the method further comprises determining a lane suitable for automated driving based on one or more lane-precise properties. The functional characteristics of the driver assistance system (e.g. SAE Level 2, 3 or 4) may be taken into account here. In other words, the answer to the question "is a lane suitable for automated driving" may depend on the functional characteristics of the driver assistance system. For example, some driver assistance systems or corresponding functional characteristics enable driving through a lane with a smaller lane width than other driver assistance systems or corresponding functional characteristics.

[0018] Preferably, the determined lane-accurate route includes a geographic location, in particular a high-precision geographic location and / or a GPS location. The geographic location indicates a lane on the lane-accurate route that is suitable for automated driving. The vehicle uses the geographic location to navigate the lane. In other words, the geographic location can be used for lane-accurate driving of the route.

[0019] Preferably, the geographical location indicates the center of at least one lane suitable for automated driving. Thus, the vehicle can be driven through the lane centered or along a (virtual) center line.

[0020] Alternatively, the geographical position may deviate to the left or right from the lane center relative to the vehicle's direction of travel. In particular, the vehicle may travel along the left lane boundary or the right lane boundary (or closer to the left lane boundary than the right lane boundary or closer to the right lane boundary than the left lane boundary), for example, to form an emergency lane.

[0021] In addition to geographic location, in some embodiments, a tolerance range for a lane-accurate route may be determined or specified that describes possible driving corridors in which the vehicle may travel.

[0022] Preferably, the method includes determining at least one lane change that is necessary for the vehicle to travel along the lane-accurate route suitable for automated driving. In particular, the at least one lane change can be performed on a multi-lane travel section with two or more lanes for the vehicle's direction of travel. This ensures that an optimized lane is always used on the multi-lane travel section, so that the time and / or distance for automated driving can be optimized.

[0023] In some embodiments, the method includes automatically performing at least one lane change by the autonomous vehicle. In particular, the vehicle may take over lateral guidance of the vehicle to automatically change lanes.

[0024] In another embodiment, the method comprises issuing a driver instruction to a driver of the vehicle for the driver to manually perform at least one lane change. In particular, the vehicle may request the driver to manually change lanes. To this end, in some embodiments, a temporary change from an automated driving mode to a manual driving mode may be made in order to enable the driver to perform a manual lane change. This may be done, for example, in situations where the functional characteristics of the driver assistance system do not allow automated lane changes (e.g., SAE Level 2).

[0025] Preferably, the vehicle comprises at least one output device for outputting driver information. 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 screen, in particular a liquid crystal display screen, a plasma display screen or an OLED display screen. In addition or alternatively, the at least one display device may comprise a projection device, which is arranged to fade the information directly into the driver's field of vision, in particular onto the windshield. In some embodiments, the at least one output device may be a central information output device of the infotainment system, such as a head unit or a column display. Preferably, the at least one output device is fixedly mounted in the vehicle.

[0026] Preferably, the method further comprises detecting environmental data by means of an environmental sensor device of the vehicle; and performing lane-accurate automated driving along a lane-accurate route based on the environmental data. Thus, the environmental data or a corresponding vehicle environment model based on the sensors can form an influencing factor, for example, to prevent a collision of the vehicle with an object or other traffic participants.

[0027] Preferably, the vehicle comprises an environment sensing device, which is arranged to detect environment data. Preferably, the environment sensing device comprises at least one lidar system and / or at least one radar system and / or at least one camera and / or at least one ultrasonic system and / or at least one laser scanner. The environment sensing device can provide environment data (also referred to as "surrounding environment data"), which describe the surrounding area of ​​the vehicle.

[0028] Preferably, the method further comprises controlling the autonomous driving vehicle so that the vehicle follows a lane-accurate route. In particular, the vehicle can follow a lane-accurate route by comparing its current position with a planned position and adapting the steering and / or speed.

[0029] Preferably, the method also includes providing lane-accurate routes for simulation in order to ensure the driver assistance system for automated driving. In order to ensure the driving function for automated driving, it is necessary to drive through these routes by means of simulation and endurance driving. The lane-accurate routes determined by the method according to the invention can be used for lane-accurate assurance of the driving function and thus allow, for example, autonomous lane changes to be performed on the lane-accurate routes, thereby improving the user-friendliness of the driving function.

[0030] According to another independent aspect of the present disclosure, a software (SW) program is provided. The software (SW) program can be configured to be executed on one or more processors, and thereby perform the method for route planning for an autonomous vehicle described herein.

[0031] According to another independent aspect of the present disclosure, a storage medium is disclosed. The storage medium may include a SW program, which is configured to be executed on one or more processors, and thereby execute the method for route planning for an autonomous driving vehicle described herein.

[0032] According to another independent aspect of the present disclosure, there is provided software having a program code, which is configured to perform a method for route planning for an autonomous vehicle when the software is run on one or more software-controlled devices.

[0033] According to another independent aspect of the present disclosure, a system for planning a route for an autonomous vehicle is disclosed. The system includes one or more processors; and at least one memory connected to the one or more processors, the memory containing instructions that can be executed by the one or more processors to perform the method for route planning for an autonomous vehicle described herein.

[0034] The system is particularly configured to execute the method for planning a route for an autonomously driven vehicle described herein. The method can implement aspects of the system described herein.

[0035] A processor or a processor module is a programmable computing unit, ie a machine or an electronic circuit which controls other elements according to transmitted instructions and thereby drives an algorithm (process).

[0036] Preferably, the system is a driver assistance system for automated driving, or is at least partially included in such a driver assistance system, or is communicatively connected to a driver assistance system.

[0037] Preferably, the entire system is integrated in the vehicle. However, the present disclosure is not limited thereto and parts of the system or the entire system, such as a routing module for route planning according to the present invention, may be implemented outside the vehicle, such as in a central unit or 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 driver assistance system functions described herein to be implemented. For example, the communication connection may be implemented by means of a mobile network, such as an LTE network or a 5G network.

[0038] According to another independent aspect of the present disclosure, a vehicle, in particular a motor vehicle, is provided, which includes a system for planning a route for an autonomous vehicle and / or a driving assistance system for autonomous driving according to an embodiment of the present disclosure.

[0039] The term vehicle includes passenger cars, trucks, buses, motor homes, motorcycles, etc., used for transporting people, goods, etc. The term especially includes motor vehicles used for the transport of people. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Embodiments of the present disclosure are shown in the accompanying drawings and described in more detail below. The accompanying drawings show:

[0041] Figure 1 schematically illustrates a vehicle having a driving assistance system for autonomous driving according to an embodiment of the present disclosure, and

[0042] Figure 2 is a flowchart of a method for route planning for an autonomous vehicle according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0043] In the following, identical and similarly acting elements are provided with the same reference numerals unless otherwise indicated.

[0044] 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.

[0045] During automated driving, the longitudinal and / or lateral guidance of the vehicle 10 is automatically performed. Therefore, the driver assistance system 100 takes over the vehicle guidance. To this end, the driver assistance system 100 controls the drive device 20, the transmission 22, the hydraulic brake device 24 and the steering device 26 via an intermediate unit (not shown).

[0046] In order to plan and execute the automated driving, environmental information of an environmental sensor device observing the vehicle environment is received by the driver assistance system 100. In particular, the vehicle may include at least one environmental sensor 12, which is configured to receive surrounding environmental data indicative of the vehicle environment. For example, the at least one environmental sensor 12 may include one or more LiDAR systems, one or more radar systems, one or more laser scanners, one or more ultrasonic sensors and / or one or more cameras.

[0047] Figure 2 The flowchart of a method 200 for planning a route for an autonomous driving vehicle according to an embodiment of the present disclosure is schematically shown. The method 200 may be implemented by corresponding software executable by one or more processors (eg, CPU).

[0048] Method 200 determines a lane-accurate route from a starting point to a destination by using lane-accurate map data. Determining the lane-accurate route includes: in block 210, for a plurality of travel segments between the starting point and the destination, finding lanes suitable for autonomous driving in the plurality of travel segments; and in block 220, considering the lanes suitable for autonomous driving in the plurality of travel segments, determining the lane-accurate route so that the time and / or distance used for autonomous driving on the lane-accurate route is maximized.

[0049] Method 200 can be implemented by a routing algorithm that calculates a route so that the vehicle can remain in the automated driving mode for as long as possible and without interruption. To this end, method 200 combines the properties of the digital map with the technical characteristics of the available driving functions and optionally uses a list of actions that the vehicle and / or the driver must perform.

[0050] These actions may include necessary manual and / or autonomous lane changes to the optimized lane, preconditioning of the vehicle for automated driving operation, etc. The attributes used for the route calculation of the digital map include lane-accurate attributes for constructing a lane-accurate route, such as lane width, lane markings, vehicle surface (potholes, friction values, etc.), turning radius and / or construction sites.

[0051] The result of the routing algorithm is a list of high-precision geographic positions on the lane of suitable travel sections. The position on the lane can be located centrally in the middle of the lane or can also deviate to the right or left edge. Variations in the lane can help avoid objects and / or form emergency lanes. In addition to the high-precision position, a tolerance range for the route can also be specified, which describes the possible driving range of the vehicle.

[0052] The lane-accurate route can be transmitted to the real autonomous vehicle and / or to a simulation (virtual vehicle). The real / virtual vehicle follows the predefined route by comparing its current position with the planned position and adapting the steering and / or speed. Influencing factors can also be a sensor-based vehicle environment model that prevents collisions with objects and other traffic participants.

[0053] According to the invention, lane-accurate map data, for example map data with lane widths, lane markings, road surface and / or turning radii, are taken into account during route planning. Based on the lane-accurate map data, it is determined for each lane of the travel section whether automated driving is possible in the respective lane. This information is used to plan a route accurately, wherein travel sections with lanes suitable for automated driving are selected in a targeted manner for the route. The vehicle can then travel along the route through lanes suitable for automated driving, for example by performing automatic and / or manual lane changes in a multi-lane travel section. In this way, maximum availability of the automated driving mode can be achieved.

[0054] Although the present invention has been described and explained in detail by preferred embodiments, the present invention is not limited to the disclosed embodiments, and the skilled person may deduce other changes without departing from the scope of protection of the present invention. Therefore, it is clear that there are a large number of possible variations. It is also clear that the exemplary embodiments mentioned are actually only examples and shall not be understood in any way as limitations on the scope of protection, application possibilities or configuration of the present invention. The foregoing description and the accompanying drawings describe to enable those skilled in the art to specifically implement the exemplary embodiments, wherein the skilled person, with an understanding of the disclosed inventive concept, can make various changes to the functions or arrangements of the various elements mentioned in the exemplary embodiments without departing from the scope of protection defined by the claims and their legal equivalents, as further explained in the specification.

Claims

1. A method (200) for planning a route for an autonomous vehicle, comprising: Determining a lane accurate route from a starting point to a destination by using lane accurate map data, wherein determining the lane accurate route comprises: For a plurality of travel segments between the starting point and the destination, obtaining (210) lanes suitable for autonomous driving in the plurality of travel segments; and The lane-accurate route is determined (220) by considering the lanes applicable to the automated driving of the plurality of travel segments such that time and / or travel on the lane-accurate route is maximized for the automated driving.

2. The method (200) of claim 1, wherein performing said determining of a lane suitable for autonomous driving based on functional properties of an autonomous driving assistance system for said autonomous driving; and / or The plurality of travel sections include at least one multi-lane travel section, and it is determined for each lane of the multi-lane travel section whether automated driving is possible.

3. The method (200) according to claim 1 or 2, wherein the lane accurate map data comprises one or more lane accurate attributes, wherein the one or more lane accurate attributes are selected from the group consisting of: lane type, lane width, lane marking, road surface, turning radius and construction site, in particular wherein the method further comprises: The lane suitable for the autonomous driving is determined based on the one or more lane precise attributes.

4. The method (200) according to any one of claims 1 to 3, wherein the determined lane-precise route includes a geographic location, wherein the geographic location indicates at least one lane suitable for the autonomous driving on the lane-precise route, in particular wherein the geographic location indicates the center of the at least one lane suitable for the autonomous driving or a deviation to the left or to the right from the center.

5. The method (200) according to any one of claims 1 to 4, further comprising: determining at least one lane change necessary for the vehicle to navigate the lane along the lane-precise route suitable for the automated driving; as well as automatically performing the at least one lane change by the vehicle being autonomously driven; or A driver instruction is issued to a driver of the vehicle to manually perform the at least one lane change by the driver.

6. The method (200) according to any one of claims 1 to 5, further comprising detecting environmental data by an environmental sensor device of the vehicle; and Lane accurate autonomous driving is performed along the lane accurate route based on the environment data.

7. The method (200) according to any one of claims 1 to 6, further comprising: Controlling the autonomously driven vehicle so that the vehicle follows a precise route in the lane; and / or The lane-accurate route is provided for a simulation of a driver assistance system for ensuring the automated driving.

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

9. A system for planning a route for an autonomous vehicle, comprising: one or more processors; as well as At least one memory, the at least one memory being 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 autonomous 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