Autonomous vehicle operation relative to unexpected dynamic objects

• US 9,764,736 B2
• Filed: 08/14/2015
• Issued: 09/19/2017
• Est. Priority Date: 08/14/2015
• Status: Active Grant

• Current Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Motor Engineering & Manufacturing North America Incorporated (Toyota Motor Corporation)
• Inventors: Prokhorov, Danil V.
• Primary Examiner(s): Sample, Jonathan L
• Application Number:
  US14/826,715
• Publication Number:
  US 20170043768A1
• Time in Patent Office: 767 Days
• CPC Class Codes: B60W 10/04 including control of propulsion units
• CPC Class Codes: B60W 10/18 including control of braking systems
• CPC Class Codes: B60W 10/20 including control of steering systems
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2550/10 from obstacle detection
• CPC Class Codes: B60W 2550/30 Distance or speed relative to other vehicles
• CPC Class Codes: B60W 2554/00 Input parameters relating to objects
• CPC Class Codes: B60W 2554/20 Static objects
• CPC Class Codes: B60W 2554/40 Dynamic objects, e.g. animals, windblown objects
• CPC Class Codes: B60W 2554/80 Spatial relation or speed relative to objects
• CPC Class Codes: B60W 2554/801 Lateral distance
• CPC Class Codes: B60W 2554/802 Longitudinal distance
• CPC Class Codes: B60W 2556/10 Historical data
• CPC Class Codes: B60W 2710/18 Braking system
• CPC Class Codes: B60W 2710/20 Steering systems
• CPC Class Codes: B60W 2720/10 Longitudinal speed
• CPC Class Codes: B60W 30/085 Taking automatic action to adjust vehicle attitude in preparation for collision, e.g. braking for nose dropping
• CPC Class Codes: B60W 30/09 Taking automatic action to avoid collision, e.g. braking and steering
• CPC Class Codes: B60W 30/095 Predicting travel path or likelihood of collision
• CPC Class Codes: B60W 30/0953 the prediction being responsive to vehicle dynamic parameters
• CPC Class Codes: B60W 30/0956 : the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: B60W 60/0027 : using trajectory prediction for other traffic participants

Abstract

An autonomous vehicle may operate in an environment in which there is an unexpected dynamic object. The autonomous vehicle can detect the dynamic object. The dynamic object can have an associated movement. The movement of the dynamic object can be tracked. The movement of the dynamic object can be classified as being one ballistic or non-ballistic. It can be determined whether the dynamic object is on a collision course with the autonomous vehicle. Responsive to determining that the dynamic object is on a collision course with the autonomous vehicle, a driving maneuver for the autonomous vehicle can be determined. The driving maneuver can be based at least in part on the movement of the dynamic object. The autonomous vehicle can be caused to implement the determined driving maneuver.

Claims

1. A method of operating an autonomous vehicle relative to unexpected dynamic objects in an external environment, the method comprising:

detecting a dynamic object in the external environment of the autonomous vehicle, the dynamic object having an associated movement;

tracking the movement of the dynamic object;

classifying the movement of the dynamic object as one of ballistic or non-ballistic;

classifying a size of the dynamic object;

determining whether the dynamic object is on a collision course with the autonomous vehicle;

responsive to determining that the dynamic object is on a collision course with the autonomous vehicle, determining a driving maneuver for the autonomous vehicle based at least in part on the classified movement of the dynamic object and the classified size of the dynamic object; and

causing the autonomous vehicle to implement the determined driving maneuver.

2. The method of claim 1, wherein the size of the dynamic object is classified as one of small or large.

3. The method of claim 2, wherein, if the movement of the dynamic object is classified as being ballistic and the size of the dynamic object is classified as being large, the determined driving maneuver includes one or more aggressive evasive maneuvers.

4. The method of claim 2, wherein, if the movement of the dynamic object is classified as being ballistic and the size of the dynamic object is classified as being small, the determined driving maneuver includes one or more evasive maneuvers.

5. The method of claim 2, wherein, if the movement of the dynamic object is classified as being non-ballistic and the size of the dynamic object is classified as being large, the driving maneuver includes one or more evasive maneuvers.

6. The method of claim 2, wherein, if the movement of the dynamic object is classified as being non-ballistic and the size of the dynamic object is classified as being small, further including:

ignoring the dynamic object in determining a driving maneuver for the autonomous vehicle.

7. The method of claim 1, further including:

determining whether a collision between the dynamic object and the autonomous vehicle is avoidable or unavoidable; and

responsive to determining that a collision between the dynamic object and the autonomous vehicle is unavoidable, determining a collision mitigating maneuver for the autonomous vehicle.

8. The method of claim 7, wherein determining the collision mitigating maneuver for the autonomous vehicle is based at least partially on the location of at least one occupant within the autonomous vehicle.

9. The method of claim 1, wherein causing the autonomous vehicle to implement the determined driving maneuver includes automatically causing the autonomous vehicle to implement the determined driving maneuver.

10. The method of claim 1, wherein causing the autonomous vehicle to implement the determined driving maneuver includes causing the autonomous vehicle to implement the determined driving maneuver responsive to receiving a vehicle occupant input.

11. A system for operating an autonomous vehicle relative to unexpected dynamic objects in an external environment, the system comprising:

a sensor system configured to detect a dynamic object in the external environment of the autonomous vehicle, the dynamic object having an associated movement;

a processor operatively connected to the sensor system, the processor being programmed to initiate executable operations comprising;

tracking the movement of the dynamic object;

classifying the movement of the dynamic object as one of ballistic or non-ballistic;

classifying a size of the dynamic object;

determining whether the dynamic object is on a collision course with the autonomous vehicle;

responsive to determining that the dynamic object is on a collision course with the autonomous vehicle, determining a driving maneuver for the autonomous vehicle based at least in part on the classified movement of the dynamic object and the classified size of the dynamic object; and

causing the autonomous vehicle to implement the determined driving maneuver.

12. The system of claim 11, wherein the size of the dynamic object is classified as one of small or large.

13. The system of claim 12, wherein, if the movement of the dynamic object is classified as being ballistic and the size of the dynamic object is classified as being large, the determined driving maneuver includes one or more aggressive evasive maneuvers.

14. The system of claim 12, wherein, if the movement of the dynamic object is classified as being ballistic and the size of the dynamic object is classified as being small, the determined driving maneuver includes one or more evasive maneuvers.

15. The system of claim 12, wherein, if the movement of the dynamic object is classified as being non-ballistic and the size of the dynamic object is classified as being large, the driving maneuver includes one or more evasive maneuvers.

16. The system of claim 12, wherein, if the movement of the dynamic object is classified as being non-ballistic and the size of the dynamic object is classified as being small, further including:

ignoring the dynamic object in determining a driving maneuver for the autonomous vehicle.

17. The system of claim 11, further including:

determining whether a collision between the dynamic object and the autonomous vehicle is avoidable or unavoidable; and

responsive to determining that a collision between the dynamic object and the autonomous vehicle is unavoidable, determining a collision mitigating maneuver for the autonomous vehicle.

18. The system of claim 17, wherein determining the collision mitigating maneuver for the autonomous vehicle is based at least partially on the location of at least one occupant within the autonomous vehicle.

19. The system of claim 11, wherein causing the autonomous vehicle to implement the determined driving maneuver includes automatically causing the autonomous vehicle to implement the determined driving maneuver.

20. A computer program product for operating an autonomous vehicle relative to unexpected dynamic objects in an external environment, the computer program product comprising a computer readable storage medium having program code embodied therein, the program code executable by a processor to perform a method comprising:

detecting a dynamic object in the external environment of the autonomous vehicle, the dynamic object having an associated movement;

tracking the movement of the dynamic object;

classifying the movement of the dynamic object as one of ballistic or non-ballistic;

classifying a size of the dynamic object;

determining whether the dynamic object is on a collision course with the autonomous vehicle;

responsive to determining that the dynamic object is on a collision course with the autonomous vehicle, determining a driving maneuver for the autonomous vehicle based at least in part on the classified movement of the dynamic object and the classified size of the dynamic object; and

causing the autonomous vehicle to implement the determined driving maneuver.