DE102020208541A1 - Method and device for creating and providing a high-precision map and method for operating an automated vehicle - Google Patents

Abstract

Method (300) and device for creating (320) and providing (330) a high-precision map, comprising a step of receiving (310) accident data representing at least one traffic accident in connection with an accident location, a step of creating (320) the high-accuracy map based on map data values depending on the accident data, and a step of providing (330) the high-accuracy map for operating an automated vehicle. Furthermore, a method for operating (430) an automated vehicle, comprising a step of detecting (410) a predetermined route of the automated vehicle, a step of performing (420) a comparison of the predetermined route with a highly accurate map, and a step of operating ( 430) of the automated vehicle, depending on the comparison carried out.

Description

The present invention relates, inter alia, to a method for creating and providing a highly accurate map, comprising a step of receiving accident data, a step of creating the highly accurate map based on map data values depending on the accident data, and a step of providing the highly accurate map.

Disclosure of Invention

The method according to the invention for creating and providing a high-precision map comprises a step of receiving accident data, which represents at least one traffic accident in connection with an accident location, a step of creating the high-precision map based on map data values, depending on the accident data, and a step of providing the highly accurate map for operating an automated vehicle.

An automated vehicle is a vehicle which, according to one of the SAE levels 1 to 5 (see Standard SAE J3016 ) is trained to understand.

Operating the automated vehicle includes, for example, the execution of safety-related functions (“arming” or triggering an airbag, tightening a seat belt, executing an emergency stopping process, etc.) and/or executing what are known as driver assistance functions (here, for example: executing a lane departure warning system, etc .) And/or automated transverse and/or longitudinal control and/or determining and/or following a trajectory for the automated vehicle, etc.

Map data values mean, for example, a digital map that is present on a storage medium. The map is designed, for example, in such a way that one or more map layers are included, one map layer showing, for example, a map from a bird's eye view (course and position of roads, buildings, landscape features, etc.). This corresponds, for example, to a map of a navigation system. A further map layer includes a radar map, for example, with the environmental features that are mapped by the radar map being stored with a radar signature. A further map layer comprises a lidar map, for example, with the environmental features which are mapped by the lidar map being stored with a lidar signature.

In particular, the map is designed in such a way that it is suitable for navigating a vehicle, in particular an automated vehicle. For this purpose, the individual map layers include, for example, environmental features with a GPS position, this position being known with great accuracy. A high-precision position is to be understood as meaning a position which is so precise within a predetermined coordinate system, for example GNSS coordinates, that this position does not exceed a maximum permissible degree of uncertainty. In this case, the maximum blurriness can depend, for example, on the environment—or the number and/or design of the environmental features. Furthermore, the maximum blurring can depend, for example, on the SAE level of the automated vehicle. In principle, the maximum blur is so low that, in particular, safe operation of the automated vehicle is ensured. For fully automated operation of the automated vehicle (SAE Level 5), the maximum blur is, for example, of the order of around 10 centimeters.

An environmental feature is to be understood, for example, as an object (traffic sign, infrastructure feature [guardrail, curve, tunnel, bridge, etc.], building, etc.) that can be detected and/or classified or assigned using an environmental sensor system of a vehicle. In one embodiment, the environment sensor system includes, for example, a computing unit (processor, main memory, hard disk) with suitable software and/or is connected to such a computing unit. In one embodiment, an environmental feature is additionally or alternatively to be understood, for example, as the course of a road (number of lanes, curve radius, etc.) and/or a pattern of several - for example repetitive - objects (for example a characteristic sequence of traffic signs, etc.).

Surroundings sensors are at least one video sensor and/or at least one radar sensor and/or at least one lidar sensor and/or at least one ultrasonic sensor and/or at least one additional sensor, which is designed to detect the surroundings of an (automated) To detect vehicle in the form of environmental data values.

The method according to the invention advantageously solves the problem of optimizing the operation of an automated vehicle and making it safer and more reliable. This object is achieved using the method according to the invention by providing a highly accurate map which takes into account accident data from traffic accidents. As a result, the accident position at be taken into account, for example, when planning a driving strategy and/or a trajectory. Furthermore, for example, a reduced number of environmental features, which are usually used to localize the automated vehicle, can be taken into account (since, for example, the corresponding environmental feature is at least temporarily destroyed and/or covered due to the accident).

The high-precision map is preferably also created as a function of a time specification, the time specification representing the duration of the impact of the traffic accident on the accident site.

A time specification is to be understood, for example, as the duration of a possible impairment of the accident site. This has the advantage that the corresponding accident data can be automatically removed from the map again, for example. In an alternative embodiment, the accident data can no longer be actively used after the duration—for example when planning a trajectory—but can still continue to be collected in the map data in the sense of an “accident counter”. This makes it possible, for example, to create an accident history and can be used to avoid or at least reduce certain road sections that frequently have traffic accidents when determining a trajectory and/or a driving strategy for the automated vehicle.

The accident site preferably includes an environmental feature for locating a vehicle, the accident data including an effect of the traffic accident on the environmental feature. It often happens that in an accident, for example, traffic signs such as traffic lights and/or street signs are affected or destroyed as a result of the accident. However, since traffic signs are suitable as environmental features for locating a vehicle due to their fixed position, it is advantageous if it is known in advance - for example when planning a trajectory - whether and how many environmental features are present along the trajectory and can be detected accordingly.

The accident data preferably include an accident severity of the traffic accident. For example, the accident is divided into attributes such as “minor”, “medium” and “severe” depending on specified criteria (number of vehicles involved, number of emergency vehicles, duration of a possible road block, etc.). This shows the advantage that a driving strategy or a trajectory can be adapted in even more detail. For example, it can be determined whether the automated vehicle can safely pass the scene of the accident (e.g. a vehicle has left the road, which means that the actual lane can still be driven on; this would correspond to the attribute "easily") or whether it is a Complete closure of the roadway at the scene of the accident (e.g. because a vehicle is on fire as a result of the accident and several emergency vehicles and/or heavy smoke is to be expected, which can also impair the automated vehicle’s surroundings sensors; this would correspond to the attribute “severe”).

The device according to the invention, in particular a computing unit, is set up to carry out all the steps of the method according to one of the method claims for creating and providing a high-precision map.

The device is designed, for example, as an externally arranged computing unit (server, cloud, control center, etc.) relative to the automated vehicle. The device includes, for example, a transmitting and/or receiving unit, which is designed to transmit and/or receive signals or data values (highly automated map, accident data, etc.). In an alternative embodiment, the device does not directly include the transmitting and/or receiving unit, but is connected to it. Furthermore, the computing unit includes means (processor, main memory, storage medium, software) for creating a highly automated map.

Furthermore, a computer program is claimed, comprising instructions which, when the computer program is executed by a computer, cause the computer to carry out a method according to one of the method claims for creating and providing a highly precise map. In one embodiment, the computer program corresponds to the software comprised by the device.

Furthermore, a machine-readable storage medium on which the computer program is stored is claimed.

The method according to the invention for operating an automated vehicle comprises a step of recording a predefined route of the automated vehicle, a step of carrying out a comparison of the predefined route with a high-precision map which includes current accident data, the high-precision map in particular using the method described here for creating and providing a high-precision map, and a step of operating the automated vehicle, depending on the comparison performed.

The operation preferably includes a localization of the automated vehicle and/or an adjustment of a driving strategy. Specific design options for this are advantageously described above.

Advantageous developments of the invention are specified in the dependent claims and listed in the description.

character list

• 1 ein Ausführungsbeispiel des erfindungsgemäßen Verfahrens zum Erstellen und Bereitstellen einer hochgenauen Karte in Form eines Ablaufdiagramms; und
• 2 ein Ausführungsbeispiel des erfindungsgemäßen Verfahrens zum Betreiben eines automatisierten Fahrzeugs in Form eines Ablaufdiagramms.

Embodiments of the invention are shown in the drawings and are explained in more detail in the following description. Show it:

• 1 an embodiment of the inventive method for creating and providing a highly accurate map in the form of a flow chart; and
• 2 an exemplary embodiment of the method according to the invention for operating an automated vehicle in the form of a flowchart.

Embodiments of the invention

1 shows an embodiment of a method 300 for creating 320 and providing 330 a high-precision map.

In step 301, the method 300 starts.

In step 310, accident data representing at least one traffic accident associated with an accident location is received.

Receiving the accident data means, for example, that the accident data is received by means of a transmitting and/or receiving device, in particular by means of a radio link. In this case, this accident data is transmitted for reception, for example, by a police station and/or another facility that created the accident data from the traffic accident.

In step 320, a highly accurate map is created based on map data values depending on the accident data.

Creating the high-precision map means, for example, that the accident data, which represent at least one traffic accident in connection with an accident location, is inserted into the map data values. In this context, an accident location is to be understood, for example, as a GPS position of the traffic accident.

In step 330, the highly accurate map for operating an automated vehicle is provided.

Providing the high-precision map is to be understood, for example, as meaning that the high-precision map can be called up and received by an automated vehicle using a transmitting and/or receiving device, in particular using a radio link.

In step 340, the method 300 ends.

2 shows an embodiment of a method 400 for operating 430 an automated vehicle.

In step 401, the method 400 starts.

In step 410, a predetermined route of the automated vehicle is recorded.

In step 420, the specified route is compared with a high-precision map, which includes current accident data, this high-precision map having been created using a method 300 for creating 320 and providing 330.

In step 430, the automated vehicle is operated depending on the comparison performed.

In step 440, the method 400 ends.

QUOTES INCLUDED IN DESCRIPTION

This list of documents cited by the applicant was generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.

Non-patent Literature Cited

• Standard SAE J3016 [0003]

Claims (10)

A method (300) for creating (320) and providing (330) a highly accurate map, comprising: - receiving (310) accident data representing at least one traffic accident associated with an accident location; - creating (320) the highly accurate map based on map data values depending on the accident data; and - providing (330) the highly accurate map for operating an automated vehicle. Method (300) according to claim 1 , characterized in that the creation (320) of the high-precision map is additionally dependent on a time specification, the time specification representing the duration of the impact of the traffic accident on the accident site. Method (300) according to claim 1 , characterized in that the accident site includes an environmental feature for locating a vehicle, wherein the accident data include an impact of the traffic accident on the environmental feature. Method (300) according to claim 1 , characterized in that the accident data include an accident severity of the traffic accident. Device, in particular a computing unit, which is set up to carry out all the steps of the method (300) according to one of Claims 1 until 4 to execute. Computer program, comprising instructions which, when the computer program is executed by a computer, cause the latter to carry out a method (300) according to one of Claims 1 until 4 to execute. Machine-readable storage medium on which the computer program claim 6 is saved. A method (400) for operating (430) an automated vehicle, comprising: - detecting (410) a predetermined route of the automated vehicle; - Carrying out (420) a comparison of the specified route with a high-precision map, which includes current accident data, wherein the high-precision map in particular by means of a method (300) according to at least one of Claims 1 until 4 was created; and - operating (430) the automated vehicle depending on the performed comparison. Method (400) according to claim 8 , characterized in that operating (430) comprises locating the automated vehicle. Method (400) according to claim 8 , characterized in that the operation (430) includes an adjustment of a driving strategy.

Images