Method, Device, Computer Program, and Computer Program Product for Checking an at Least Semi-Autonomous Driving Mode of a Vehicle

Abstract

In a method for checking an at least semi-autonomous driving mode of a vehicle, intervention data are provided by a plurality of vehicles. The intervention data each represent a human intervention in an at least semi-autonomous driving mode of a vehicle. The intervention data includes sensor data at the time of the intervention and position data for a position at the time of the intervention. In accordance with the intervention data from the plurality of vehicles, a position is determined at which an increased number of vehicles registered a human intervention.

Claims

1-10. (canceled)

11. A method for checking an at least semiautonomous driving mode of a vehicle, the method comprising: providing, by a plurality of vehicles, intervention data, wherein the intervention data are each representative of a human intervention in an at least semiautonomous driving mode of a vehicle, and wherein the intervention data comprise sensor data at the time of the intervention and position data for a position at the time of the intervention; and ascertaining a position at which an elevated number of vehicles has registered a human intervention in dependence on the intervention data of the plurality of vehicles.

12. The method according to claim 11, wherein depending on the intervention data of an individual vehicle of the plurality of vehicles, ascertaining which type of the human intervention occurred.

13. The method according to claim 12, wherein depending on the intervention data of the individual vehicle and the ascertained type of the human intervention, ascertaining whether the intervention took place due to an error of the at least semiautonomous driving mode.

14. The method according to claim 11, wherein correction parameters are ascertained in dependence on the intervention data of the plurality of vehicles and transmitted to the plurality of vehicles, and the correction parameters are representative for corrected sensor data, by which an at least semiautonomous driving mode without human intervention is enabled at the ascertained position.

15. The method according to claim 11, wherein the semiautonomous driving mode comprises an autonomous lateral control and/or an autonomous longitudinal control of the vehicle.

16. The method according to claim 11, wherein a data collection message is transmitted to the plurality of vehicles in dependence on the ascertained position, which data collection message is representative of the fact that the plurality of vehicles is to acquire and transmit specified sensor data when driving on the ascertained position.

17. The method according to claim 11, wherein a stop message is transmitted to at least a subset of the plurality of vehicles in dependence on the ascertained position, which stop message is representative of the fact that the subset of the plurality of vehicles is no longer to transmit intervention data when driving on the ascertained position.

18. A device for checking an at least semiautonomous driving mode of a vehicle, comprising: one or more processors and associated memory operatively configured to: provide, by a plurality of vehicles, intervention data, wherein the intervention data are each representative of a human intervention in an at least semiautonomous driving mode of a vehicle, and wherein the intervention data comprise sensor data at the time of the intervention and position data for a position at the time of the intervention; and ascertain a position at which an elevated number of vehicles has registered a human intervention in dependence on the intervention data of the plurality of vehicles.

19. A computer program product for checking an at least semiautonomous driving mode of a vehicle, comprising a non-transitory computer readable medium having stored thereon executable program code, wherein the program code upon execution by a data processing device, carries out the acts of: providing, by a plurality of vehicles, intervention data, wherein the intervention data are each representative of a human intervention in an at least semiautonomous driving mode of a vehicle, and wherein the intervention data comprise sensor data at the time of the intervention and position data for a position at the time of the intervention; and ascertaining a position at which an elevated number of vehicles has registered a human intervention in dependence on the intervention data of the plurality of vehicles.

Description

BRIEF DESCRIPTION OF THE DRAWING

[0028] FIG. 1 is a flow chart for checking an at least semiautonomous driving mode.

DETAILED DESCRIPTION OF THE DRAWING

[0029] FIG. 1 shows a flow chart for checking an at least semiautonomous driving mode of a vehicle.

[0030] The program can be run by a device. The device is formed, for example, in a server and/or a backend. The device can also be formed distributed in a cloud.

[0031] The device can also be referred to as a device for checking an at least semiautonomous driving mode.

[0032] The device includes, for this purpose, in particular a processing unit, a program and data memory, and also, for example, one or more communication interfaces. The program and data memory and/or the processing unit and/or the communication interfaces can be formed in one structural unit and/or distributed onto multiple structural units.

[0033] For this purpose, in particular a program for checking an at least semiautonomous driving mode is stored on the program and data memory of the device.

[0034] The program is started in a step S1, in which variables can be initialized if necessary.

[0035] In a step S3, intervention data are provided by a plurality of vehicles, wherein the intervention data are each representative for a human intervention in an at least semiautonomous driving mode of a vehicle and wherein the intervention data comprise sensor data at the time of the intervention and position data for a position at the time of the intervention.

[0036] The plurality of vehicles is, for example, a vehicle fleet of a vehicle producer or at least a part of a vehicle fleet of a vehicle producer.

[0037] To reduce the amount of transmitted data, the sensor data do not comprise, for example, raw data, but only detected objects of the sensors, such as traffic signals, road markings, and/or other objects such as obstacles, other vehicles, and the like.

[0038] The position data can be ascertained, for example, by means of a global navigation satellite system such as GPS in the respective vehicle.

[0039] The intervention data are transmitted, for example, after each intervention, via a wireless communication interface of the respective vehicle to a database and subsequently provided by the database.

[0040] In a step S5, a position, at which an increased number of vehicles has registered a human intervention, is ascertained in dependence on the intervention data of the plurality of vehicles.

[0041] The position at which an elevated number of vehicles has registered a human intervention can be ascertained, for example, in that local maxima of positions are ascertained from the set of all interventions, in particular local maxima which deviate in a statistically significant manner.

[0042] Subsequently, the program is ended in a step S7 and can be started again if necessary in step S1.

[0043] For classification of the interventions, it can additionally be ascertained in dependence on the intervention data of an individual vehicle of the plurality of vehicles which type the human intervention was. The type can comprise, for example: braking to a standstill, counter steering to the right/left, tracking to the right/left, no relevant intervention, since the driver wishes to drive further himself.

[0044] Furthermore, the intervention data can be used to ascertain whether the intervention took place due to an error of the autonomous driving mode.

[0045] The above-provided intervention data and the ascertained position at which an elevated number of vehicles has registered a human intervention can subsequently be used to determine further measures.

[0046] For example, correction parameters can be ascertained in dependence on the intervention data of the plurality of vehicles and transmitted to the plurality of vehicles, wherein the correction parameters are representative for corrected sensor data, by means of which an at least semiautonomous driving mode without human intervention is enabled at the ascertained position.

[0047] If it is not (yet) possible to ascertain correction parameters on the basis of the existing data, alternatively or additionally, a data collection message can be transmitted to the plurality of vehicles in dependence on the ascertained position, which is representative of the fact that the plurality of vehicles is to acquire and transmit specified sensor data when driving on the ascertained position. The ascertained position can be studied more accurately in this way and correction parameters can subsequently be ascertained if necessary in dependence on the new sensor data. In addition, the position can also deliberately be approached using development vehicles in order to acquire more detailed sensor data and if necessary correction parameters are subsequently ascertained in dependence on the more detailed sensor data.

[0048] Furthermore, in dependence on the ascertained position, a map can be prepared which is representative of positions at which an approval for highly/fully automated systems is possible, since an intervention probability is very low and for positions at which an approval for highly/fully automated systems is not reasonable, since an intervention probability is very low.

[0049] In summary, a very large number of vehicles can thus contribute by way of the above method to each individual vehicle being able to operate more reliably in an at least semiautonomous driving mode.