Driving assistance technique for active vehicle control

Patent metadata

Field	Value
Publication number	US-10625776-B2
Application number	US-201414478423-A
Country	US
Kind code	B2
Filing date	Sep 5, 2014
Priority date	Sep 9, 2013
Publication date	Apr 21, 2020
Grant date	Apr 21, 2020

Abstract

The invention relates to a driving assistant adapted for active control of a vehicle based on predictions of a behavior of a detected object. A method aspect of the invention comprises accepting a first prediction of a behavior associated with the detected object from a first prediction subsystem and a second prediction from a second prediction subsystem; determining a control signal based on a combination of the first prediction and the second prediction; and initiating active control of the vehicle based on the control signal.

First claim

The invention claimed is:

1. A method for actively controlling a vehicle, the method comprising the following steps:
accepting a first prediction of a behavior associated with a detected object from a first prediction subsystem of a driver assistance system of the vehicle to obtain a first prediction result;
accepting a second prediction of said behavior from a second prediction subsystem of the driver assistance system in order to obtain a second prediction result of the same behavior associated with said detected object;
combining the first prediction result and the second prediction result and assigning, during the combination, a weight to the first prediction subsystem and a weight to the second prediction subsystem, wherein the weights reflect a relative confidence or reliability of the first prediction subsystem and the second prediction subsystem relative to each other;
determining a control signal for controlling the vehicle in response to the predicted behavior, wherein a strength of the control signal is controlled by the combination; and
initiating, with respect to the predicted behavior, active control of the vehicle based on the control signal.

2. The method according to claim 1 ,
wherein the control signal indicates one value taken from a range of values associated with a particular operation of the vehicle.

3. The method according to claim 2 ,
wherein the control signal sets a maximum or minimum value of the range of values.

4. The method according to claim 1 ,
wherein in each of the first and second predictions, a probability value is assigned to the behavior, and the combination of the results of the first and second predictions comprises a combination of said probability values.

5. The method according to claim 1 ,
wherein the control signal indicates at least one of an acceleration or deceleration of the vehicle, and a steering angle of the vehicle.

6. The method according to claim 1 ,
wherein the first prediction subsystem is a context based prediction subsystem for predicting behavior based on indirect indicators observable before a start of a predicted behavior, and the second prediction subsystem is a physical prediction subsystem for predicting behavior based on direct indicators observable after a start of a predicted behavior.

7. The method according to claim 6 ,
wherein the context based prediction subsystem has associated therewith a lower weight than the physical prediction subsystem.

8. A non-transitory computer program product comprising program code portions for performing the method according to claim 1 when the computer program product is executed on a computing device.

9. A driver assistance system for actively controlling a vehicle, comprising:
a component adapted to accept a first prediction of a behavior associated with a detected object from a first prediction subsystem to obtain a first prediction result;
a component adapted to accept a second prediction of said behavior from a second prediction subsystem in order to obtain a second prediction result of the same behavior associated with said detected object;
a component adapted to combine the first prediction result and the second prediction result and to assign, during the combination, a weight to the first prediction subsystem and a weight to the second prediction subsystem, wherein the weights reflect a relative confidence or reliability of the first prediction subsystem and the second prediction subsystem relative to each other;
a component adapted to determine a control signal for controlling the vehicle in response to the predicted behavior, wherein a strength of the control signal is controlled by the combination; and
a component adapted to initiate, with respect to the predicted behavior, active control of the vehicle based on the control signal.

10. The system according to claim 9 ,
wherein the driver assistance system comprises a cruise control module adapted to perform an active control of the vehicle in response to a lane-change of a detected object cutting-in to or cutting-out from a lane of the vehicle.

11. A vehicle comprising a system according to claim 9 .

Assignees

• Honda Res Inst Europe Gmbh

Inventors

• Rebhan Sven
• Schmüdderich Jens
• Kleinehagenbrock Marcus
• Kastner Robert
• Mori Naoki
• Kusuhara Shunsuke
• Kamiya Hiroyuki

Classifications

• B60W2720/10

  Longitudinal speed · CPC title

• B60W2720/106

  Longitudinal acceleration · CPC title

• B60W30/16

  Control of distance between vehicles, e.g. keeping a distance to preceding vehicle · CPC title

• B60W2710/207

  Steering angle of wheels · CPC title

• B60W30/18163

  Lane change; Overtaking manoeuvres · CPC title