Method and device for operating an automated vehicle

Abstract

Method (300) and device for operating (350) an automated vehicle, comprising a step of detecting (310) objects in an environment of the automated vehicle, a step of determining (320) a predicted behavior for these objects, a step of creating (330) a comparison of the predicted behavior with an actual behavior of these objects, a step of determining (340) a driving strategy for the automated vehicle depending on the comparison, and a step of operating (350) the automated vehicle depending on the driving strategy.

Description

[0001] The present invention relates, inter alia, to a method for operating an automated vehicle depending on a predetermined driving strategy. Disclosure of the invention

[0002] The method for operating an automated vehicle comprises a step of detecting objects in an environment of the automated vehicle, a step of determining a predicted behavior for these objects, and a step of comparing the predicted behavior with an actual behavior of these objects. The method further comprises a step of determining a driving strategy for the automated vehicle based on the comparison and a step of operating the automated vehicle based on the driving strategy.

[0003] An automated vehicle is a partially, highly or fully automated vehicle according to one of the SAE levels 1 to 5 (see standard SAE J3016).

[0004] Operating an automated vehicle, particularly depending on the driving strategy, is understood to mean, for example, executing lateral and / or longitudinal control of the automated vehicle, with the lateral and / or longitudinal control being performed such that the automated vehicle moves along a trajectory. In one possible embodiment, operation also includes, for example, executing safety-relevant functions ("arming" an airbag, fastening the seat belts, etc.) and / or other (driver assistance) functions.

[0005] Objects in the environment of the automated vehicle are detected using a specially designed environmental sensor system. An environmental sensor system is understood to mean at least one video and / or at least one radar and / or at least one lidar and / or at least one ultrasound and / or at least one other sensor, which is designed to detect the environment of a vehicle in the form of environmental data values. In one possible embodiment, the environmental sensor system comprises, for example, a computing unit (processor, RAM, hard disk) with suitable software and / or is connected to such a computing unit. In one possible embodiment, this software comprises, for example, object recognition algorithms based on a neural network or artificial intelligence.

[0006] Objects can be static and / or dynamic. A static object is defined as an object that is, at least not currently, moving. This could be, for example, traffic signs (street signs, traffic lights, etc.), infrastructure features (guardrails, bridge piers, lane markings, etc.), parked vehicles, garbage cans on the side of the road, buildings, etc. A dynamic object is defined as an object that is currently moving. This could be, for example, other vehicles, pedestrians, cyclists, etc.

[0007] An environment is defined here as at least one area—particularly along the traffic route—that can be accessed by vehicles. The environment includes not only the traffic route itself, but also areas along the traffic route that can also be detected by environmental sensors when driving along the route.

[0008] A traffic route, for example, is a single-lane or multi-lane road. An area along a traffic route is understood to include the traffic route itself and a strip to the left and / or right of the traffic route. The width of the strip depends, for example, on the specific design of the surroundings and / or the sensor range of the individual vehicles. Typically, this strip includes environmental features such as traffic signs, etc.

[0009] Predicted behavior for these objects is understood to mean a prediction of the movement behavior of these objects. This can involve a single object or multiple objects, depending on the number of objects or the design of the environment, etc. Movement behavior of the objects relative to the automated vehicle is understood to mean, for example, whether this object is moving away from the automated vehicle or towards the automated vehicle and / or whether the distance between this object and the automated vehicle is increasing or decreasing, etc. In one embodiment, the movement behavior particularly includes whether the movement of this object poses a risk to the automated vehicle (for example, if this object is approaching in such a way that a collision is imminent, etc.).

[0010] A comparison of the predicted behavior with the actual behavior of these objects is created by comparing the actual behavior—as detected by the environmental sensors—with the predicted behavior. The comparison can relate, for example, to speeds, acceleration behavior, turning behavior, distances from the automated vehicle, etc.

[0011] The method according to the invention advantageously solves the problem of providing a method for safely operating an automated vehicle. Unlike a human driver, an automated vehicle cannot rely on its intuition and the resulting assessment of a current (traffic) situation. Therefore, it is of great importance for the safety of the automated vehicle, its occupants, and all other road users to compensate for this intuition as best as possible using suitable methods. The problem of technically implementing this intuition is solved by the method according to the invention, among other things, by detecting objects in the environment, determining a predicted behavior for these objects, and comparing the predicted behavior with the actual behavior of these objects.If the predictions correspond to the actual behavior, this means that the automated vehicle's systems are functioning reliably or can reliably handle the current situation. However, if significant deviations occur—according to predefined criteria—the automated vehicle's driving strategy must be adjusted accordingly (e.g., reducing a certain speed, etc.).

[0012] Preferably, an object density in the environment of the automated vehicle is also determined. The driving strategy is then determined based on the object density.

[0013] Object density refers to the number of objects in relation to the surrounding area and / or to a part of the surrounding area—for example, relative to a traffic route segment. A traffic route segment is understood, for example, to be a section of a traffic route of a certain length and / or between two intersections and / or between two entrances or exits, etc., of the corresponding traffic route.

[0014] The driving strategy is determined, for example, by comparing the previously determined object density with the object densities stored in the automated vehicle.

[0015] Preferably, the predicted behavior of the objects comprises a trajectory and / or a speed behavior and / or an acceleration behavior of the respective objects.

[0016] A trajectory is understood, for example, in relation to a map, as a line that the object follows. In one embodiment, this line refers, for example, to a fixed point on the object. In another possible embodiment, a trajectory is understood, for example, as a path through which the object travels.

[0017] Preferably, a configuration of the environment is also recorded. The driving strategy is then determined based on this configuration.

[0018] A design of the environment can be understood as, for example, a classification of the current traffic route (motorway, country road, inner-city road, etc.) and / or the presence of zebra crossings, traffic lights, intersections, entrances and exits, pedestrians, cyclists, etc. and / or infrastructure features (bridges, tunnels, parking lots, etc.) and / or other features.

[0019] The device according to the invention, in particular a control unit, is designed to carry out all steps of the method according to one of the method claims for operating an automated vehicle.

[0020] For this purpose, the device comprises, in particular, a computing unit (processor, RAM, storage medium) and suitable software for executing the method according to one of the method claims. Furthermore, the device comprises an interface for transmitting and receiving data values ​​via a wired and / or wireless connection, for example, with other vehicle devices (control units, communication devices, environmental sensors, navigation system, etc.) and / or external devices (server, cloud, etc.).

[0021] Furthermore, a computer program is claimed, comprising instructions that, when executed by a computer, cause the computer to execute a method according to one of the method claims for operating an automated vehicle. In one embodiment, the computer program corresponds to the software included in the device.

[0022] Furthermore, a machine-readable storage medium on which the computer program is stored is required.

[0023] Advantageous further developments of the invention are specified in the subclaims and listed in the description. Drawings

[0024] Embodiments of the invention are illustrated in the drawing and explained in more detail in the following description. It shows: Fig. 1 an embodiment of the method according to the invention for operating an automated vehicle in the form of a flow chart. Embodiments of the invention

[0025] Fig. 1 shows an embodiment of a method 300 for operating 350 an automated vehicle.

[0026] In step 301, the method 300 starts.

[0027] In step 310, objects in an environment of the automated vehicle are detected.

[0028] In step 320, a predicted behavior for these objects is determined.

[0029] In step 330, a comparison of the predicted behavior with an actual behavior of these objects is created.

[0030] In step 340, a driving strategy for the automated vehicle is determined depending on the comparison.

[0031] In step 350, the automated vehicle is operated depending on the driving strategy.

[0032] In step 360, the method 300 ends.

Claims

[1] A method (300) for operating (350) an automated vehicle, comprising: - detecting (310) objects in an environment of the automated vehicle; - determining (320) a predicted behavior for these objects; - creating (330) a comparison of the predicted behavior with an actual behavior of these objects; - determining (340) a driving strategy for the automated vehicle depending on the comparison; and - Operating (350) the automated vehicle depending on the driving strategy. [2] Method (300) according to claim 1, characterized by that an object density in the environment of the automated vehicle is additionally determined and the driving strategy is additionally determined depending on the object density. [3] Method (300) according to claim 1, characterized bythat the predicted behavior of the objects includes a trajectory and / or a speed behavior and / or an acceleration behavior of the respective objects. [4] Method (300) according to claim 1, characterized by that the design of the environment is also recorded and the driving strategy is also determined depending on the design. [5] Device, in particular a control device, which is designed to carry out all steps of the method (300) according to one of claims 1 to 4. [6] A computer program comprising instructions which, when the computer program is executed by a computer, cause the computer to carry out a method (300) according to any one of claims 1 to 4. [7] A machine-readable storage medium on which the computer program according to claim 6 is stored.

Images