Method for determining a driving instruction

Patent metadata

Field	Value
Publication number	US-11282299-B2
Application number	US-201816607308-A
Country	US
Kind code	B2
Filing date	May 15, 2018
Priority date	May 23, 2017
Publication date	Mar 22, 2022
Grant date	Mar 22, 2022

Abstract

The disclosure relates to a method for determining a driving instruction, whereby environmental data relevant to the surroundings of the motor vehicle is acquired by at least one detection device of a motor vehicle, after which, as a function of the environmental data, a driving instruction relevant to the driving operation of the motor vehicle is determined, which is specified by a gesture and/or a pose of a traffic controller mapped by the environmental data, wherein the determination of the driving instruction is carried out as a function of at least one set of training data, which was previously acquired by the detection device or a further detection device and which maps a further traffic controller and at least a traffic participant.

First claim

The invention claimed is:

1. A method for determining a driving instruction for a motor vehicle, comprising:
acquiring, by a sensor, environmental data relevant to surroundings of the motor vehicle; and
determining, by a processor, the driving instruction relevant to a driving operation of the motor vehicle as a function of the environmental data, wherein the driving instruction is specified by a gesture or a pose of a traffic controller mapped by the environmental data;
wherein the determining of the driving instruction is carried out as a function of a set of training data, which was previously acquired by a further sensor, and
wherein the set of training data is acquired by the further sensor by mapping a further traffic controller and a traffic participant.

2. The method according to claim 1 , wherein the determining of the driving instruction further comprises applying a processing algorithm to the environmental data or to a processing data determined from the environmental data, the processing algorithm being parameterized by a plurality of processing parameters, which are determined by training the processing algorithm via the set of training data as part of a machine learning process.

3. The method according to claim 1 , wherein the determining of the driving instruction includes determining as a function of a classification information which is determined by classifying the set of training data which includes a driving maneuver carried out by the traffic participant and the pose or the gesture mapped by the traffic controller.

4. The method according to claim 3 , wherein the driving maneuver of the traffic participant, or the pose or the gesture of the traffic controller are classified by a classification algorithm parameterized by a plurality of classification parameters, the classification algorithm is trained by a plurality of training data sets as part of a machine learning process.

5. The method according to claim 1 , wherein the determining of the driving instruction includes determining as a function of an infrastructure element recognized in the environmental data or in the set of training data.

6. The method according to claim 1 , wherein the determining of the driving instruction includes determining as a function of digital map data relevant to the surroundings of the motor vehicle or the further sensor.

7. The method according to claim 1 , wherein the determining of the driving instruction includes determining as a function of communication data received.

8. The method according to claim 1 , wherein the determining of the driving instruction includes determining the driving instruction relevant to the driving operation of the motor vehicle at a later point in time,
wherein the driving instruction is determined by a further set of training data, which includes the environmental data of current time and further environmental data, and
wherein the further environmental data is acquired by the sensor at the later point in time and is specified by a further gesture or a further pose of the further traffic controller.

9. The method according to claim 1 , further comprising outputting a reference relevant to the driving instruction to a user or to guide the motor vehicle in accordance with the driving instruction by at least one vehicle device a speaker of the motor vehicle controlled as a function of the driving instruction.

10. A motor vehicle comprising:
a sensor configured to acquire environmental data relevant to surroundings of the motor vehicle; and
a processor configured to determine a driving instruction relevant to a driving operation of the motor vehicle as a function of the environmental data, wherein the driving instruction is specified by a gesture or a pose of a traffic controller mapped by the environmental data,
wherein the processing device is further configured to determine the driving instruction as a function of a set of training data, which was previously acquired by a further sensor, and
wherein the set of training data is acquired by the further sensor by mapping a further traffic controller and a traffic participant.

Assignees

• Audi Ag

Inventors

• Sippl Christoph
• Profendiner Daniel

Classifications

• B60W40/04 Primary

  Traffic conditions · CPC title

• G06V40/28 Primary

  Recognition of hand or arm movements, e.g. recognition of deaf sign language (static hand signs G06V40/113) · CPC title

• G06F18/214

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• B60W2555/60

  Traffic rules, e.g. speed limits or right of way · CPC title

• B60W50/14

  Means for informing the driver, warning the driver or prompting a driver intervention · CPC title