Method for controlling a driver assistance system

• US 9,650,056 B2
• Filed: 05/01/2015
• Issued: 05/16/2017
• Est. Priority Date: 05/30/2014
• Status: Active Grant

• Current Assignee: Honda Research Institute Europe GmbH (Honda Motor Company)
• Original Assignee: Honda Research Institute Europe GmbH (Honda Motor Company)
• Inventors: Heckmann, Martin, Wersing, Heiko
• Primary Examiner(s): Melton, Todd
• Application Number:
  US14/701,785
• Publication Number:
  US 20150344040A1
• Time in Patent Office: 746 Days
• CPC Class Codes: B60W 2540/21 Voice
• CPC Class Codes: B60W 30/18154 Approaching an intersection
• CPC Class Codes: B60W 50/08 Interaction between the driver and the control system
• CPC Class Codes: B60W 50/10 Interpretation of driver requests or demands
• CPC Class Codes: B60W 50/14 Means for informing the driver, warning the driver or prompting a driver intervention
• CPC Class Codes: G10L 15/1807 using prosody or stress
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

The invention relates to a method for controlling a driver assistance system comprising the steps of providing information on an environment of a host vehicle, receiving a spoken instruction from a host vehicle driver, generating an attention delegation task for evaluation of the provided information from the spoken instruction, performing evaluation of provided information in accordance with said attention delegation task and outputting a result of the evaluation.

Claims

1. A method for controlling a driver assistance system comprising the steps of:

providing information on an environment of a host vehicle;

receiving a spoken instruction from a host vehicle driver;

generating an attention delegation task for evaluation of the provided information from the spoken instruction;

performing evaluation of provided information in accordance with said attention delegation task; and

outputting a result of the evaluation;

wherein

generated attention delegation tasks that are generated from spoken instructions are stored associated with a traffic scene context in which the spoken instruction is received and a likeliness is estimated from the stored attention delegation tasks, the corresponding spoken instructions, and a current traffic scene context; and

in case a likeliness that exceeds a predetermined threshold is estimated, the attention delegation task is automatically processed or is suggested to the host vehicle driver.

2. The method according to claim 1, wherein

the timing or wording of the spoken utterance in relation to the current environment information is used.

3. The method according to claim 1, wherein

a space of the environment for which provided information is used or for which information is provided is limited according to the attention delegation task.

4. The method according to claim 1, wherein

evaluation of provided information includes perception of the environment and further evaluation is limited to perceived elements defined in the attention delegation task.

5. The method according to claim 1, wherein

the attention delegation task is linked to a current situation or to a situation in the future to be recognized based on an analysis of the provided information.

6. The method according to claim 1, wherein

the provided information is analyzed for critical situations and that a warning is output when such critical situation is identified.

7. The method according to claim 1, wherein

a condition for performing the evaluation according to the attention delegation task is generated from the spoken instruction.

8. The method according to claim 1, wherein

the output includes information on a confidence of the evaluation result.

9. The method according to claim 8, wherein

prosodic variations are used as an indication of confidence in a spoken message being the output.

10. The method according to claim 1, wherein

a prosodic analysis of the speech signal of the driver is performed and possibly combined with other information channels to achieve any of the following

an improved end of utterance detection,

a differentiation of utterances directed to the system from those directed to a human, and

an evaluation of the driver'"'"'s state like mood or stress level.

11. The method according to claim 1, wherein

based on the stored spoken instructions associated with a traffic scene the interaction style with the user is adapted.

12. The method according to claim 11, wherein

an abbreviated spoken instruction is sufficient to trigger a particular attention delegation task.

13. The method according to claim 1, wherein

attention delegation task is carried out with reference to a model of the visibility of the current traffic scene for the human driver in order to deliver an appropriate speech output for the attention delegation task.

14. An advanced driver assistance system,

configured to carry out the method according to claim 1.

15. A vehicle, equipped with the advanced driver assistance system according to claim 14.