Object tracking prior to and during a collision

• US 10,427,677 B2
• Filed: 03/08/2016
• Issued: 10/01/2019
• Est. Priority Date: 04/17/2015
• Status: Active Grant

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Eisele, Sybille, Wilhelm, Ulf
• Primary Examiner(s): Ismail, Mahmoud S
• Assistant Examiner(s): Underwood, Bakari
• Application Number:
  US15/555,141
• Publication Number:
  US 20180043889A1
• Time in Patent Office: 1,302 Days
• CPC Class Codes: B60W 2030/082 Vehicle operation after collision
• CPC Class Codes: B60W 2050/0062 Adapting control system settings
• CPC Class Codes: B60W 2050/0215 Sensor drifts or sensor failures
• CPC Class Codes: B60W 2554/00 Input parameters relating to objects
• CPC Class Codes: B60W 30/08 Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes

Abstract

A method includes steps of detecting an object in an environment of a motor vehicle; in a first phase, tracking the object with respect to the motor vehicle with the aid of a first movement model of the motor vehicle; detecting a collision of the motor vehicle with an obstacle; and in a second phase, tracking the object with respect to the motor vehicle with the aid of a second movement model of the motor vehicle.

Claims

1. A method comprising:

detecting an object in an environment of a motor vehicle;

in a first phase;

a processor tracking the object relative to the motor vehicle based on sensor data obtained from at least one sensor and using a first movement model of the motor vehicle; and

the processor controlling movements of the motor vehicle based on the tracking of the first phase;

detecting a collision of the motor vehicle with an obstacle;

the processor determining from which direction the obstacle collides with the motor vehicle in the detected collision; and

in a second phase;

the processor tracking the object relative to the motor vehicle based on sensor data obtained from only that of the at least one sensor which faces away from the determined direction of the collision and using a second movement model of the motor vehicle; and

the processor controlling the movements of the motor vehicle based on the tracking of the second phase.

2. The method as recited in claim 1, wherein in the second phase, the object is also tracked on the basis of data of the detection of the object in the first phase.

3. The method as recited in claim 1, wherein an end of the collision is determined, and in a third phase, the object continues to be tracked with respect to the vehicle using the first movement model of the motor vehicle.

4. The method as recited in claim 3, wherein in the third phase, the object is also tracked on the basis of data of the detection of the object in the second phase.

5. The method as recited in claim 3, wherein, in the third phase, a movement of the motor vehicle is controlled on the basis of the tracked object.

6. The method as recited in claim 1, wherein the detection of the collision is on the basis of data from an acceleration sensor.

7. The method as recited in claim 6, wherein an acceleration caused by the collision, and an acceleration direction are taken into account in the tracking of the object in the second phase.

8. The method as recited in claim 1, wherein data from an upfront sensor are taken into account in the tracking of the object in the second phase.

9. The method as recited in claim 1, wherein data from a peripheral sensor are taken into account in the tracking of the object in the second phase.

10. The method as recited in claim 1, wherein data from a roll rate sensor are taken into account in the tracking of the object in the second phase.

11. The method as recited in claim 1, wherein data from a yaw rate sensor are taken into account in the tracking of the object in the second phase.

12. The method as recited in claim 1, wherein each of the first and second movement models identifies different respective extremums beyond which values of the sensor data are to be disregarded for the tracking.

13. The method as recited in claim 1, wherein:

the sensor data obtained in the first phase is interpreted by the processor according to the first movement model;

the tracking of the first phase is performed by the processor based on the interpretation;

responsive to the detection of the collision, the sensor data obtained in the second phase is interpreted by the processor according to the second movement model instead of the first movement model; and

the tracking of the second phase is performed based on the interpretation of the sensor obtained in the second phase.

14. A non-transitory computer readable storage medium on which is stored program code that is executable by a processor and that, when executed by the processor, causes the processor to perform a method, the method comprising:

detecting an object in an environment of a motor vehicle;

in a first phase;

tracking the object relative to the motor vehicle based on sensor data obtained from at least one sensor and using a first movement model of the motor vehicle; and

controlling movements of the motor vehicle based on the tracking of the first phase;

detecting a collision of the motor vehicle with an obstacle;

determining from which direction the obstacle collides with the motor vehicle in the detected collision; and

in a second phase;

tracking the object relative to the motor vehicle based on sensor data obtained from only that of the at least one sensor which faces away from the determined direction of the collision and using a second movement model of the motor vehicle; and

controlling the movements of the motor vehicle based on the tracking of the second phase.

15. The non-transitory computer readable storage medium as recited in claim 14, wherein:

the sensor data obtained in the first phase is interpreted according to the first movement model;

the tracking of the first phase is performed based on the interpretation;

responsive to the detection of the collision, the sensor data obtained in the second phase is interpreted according to the second movement model instead of the first movement model; and

the tracking of the second phase is performed based on the interpretation of the sensor obtained in the second phase.