Driving path determination for autonomous vehicles

• US 9,898,005 B2
• Filed: 06/24/2016
• Issued: 02/20/2018
• Est. Priority Date: 06/24/2016
• 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: Mei, Xue, Harada, Masahiro, Prokhorov, Danil V.
• Primary Examiner(s): Trivedi, Atul
• Application Number:
  US15/192,032
• Publication Number:
  US 20170371336A1
• Time in Patent Office: 606 Days
• Field of Search: 701 25
• CPC Class Codes: B60W 30/00 Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
• 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 30/095 Predicting travel path or likelihood of collision
• CPC Class Codes: B60W 30/18163 Lane change; Overtaking manoeuvres
• CPC Class Codes: G05D 1/0212 with means for defining a desired trajectory involving a plurality of land vehicles G05D1/0287

Abstract

A method of autonomous driving includes identifying, from detected information about an environment surrounding a vehicle on a roadway, a lateral surface profile of the roadway. Based on the lateral surface profile of the roadway, vertical wheel positions at identified candidate future lateral positions of the vehicle are determined. Based on the determined vertical wheel positions, as part of a driving path along the roadway, future lateral positions of the vehicle from among the identified candidates therefor are determined using an energy function that algorithmically favors low vertical wheel positions.

Claims

1. A method of autonomous driving, comprising:

identifying, using a perception module executable by at least one processor, from detected information about an environment surrounding a vehicle on a roadway, a lateral surface profile of the roadway;

determining, using a planning/decision making module executable by the at least one processor, based on the lateral surface profile of the roadway, vertical wheel positions at identified candidate future lateral positions of the vehicle; and

determining, using the planning/decision making module executable by the at least one processor, as part of a driving path along the roadway, and based on the determined vertical wheel positions, future lateral positions of the vehicle from among the identified candidates therefor using an energy function that algorithmically favors low vertical wheel positions.

2. The method of claim 1, wherein the vehicle is a host vehicle, further comprising:

operating, using a control module executable by the at least one processor, vehicle systems in the host vehicle to maneuver the host vehicle along the roadway according to a driving plan describing the driving path.

3. The method of claim 1, wherein the vehicle is a neighboring vehicle to a host vehicle, further comprising:

predicting, using the planning/decision making module executable by the at least one processor, based on the driving path, future maneuvering of the neighboring vehicle along the roadway; and

operating, using a control module executable by the at least one processor, vehicle systems in the host vehicle to maneuver the host vehicle along the roadway based on the predicted future maneuvering of the neighboring vehicle along the roadway.

4. The method of claim 1, further comprising:

determining, using the planning/decision making module executable by the at least one processor, in addition to the vertical wheel positions, one or more other aspects of the identified candidate future lateral positions of the vehicle, wherein the energy function further algorithmically favors the one or more other aspects; and

adjusting, using the planning/decision making module executable by the at least one processor, the extent which the energy function algorithmically favors low vertical wheel positions compared to the one or more other aspects based on an identified roadway condition.

5. The method of claim 4, further comprising:

identifying, using the perception module executable by the at least one processor, as the roadway condition, the lateral surface profile of the roadway, with the lateral surface profile of the roadway representing one or more ruts on the roadway, and with the energy function increasingly algorithmically favoring low vertical wheel positions compared to the one or more other aspects with increasing depths of the one or more ruts on the roadway.

6. The method of claim 4, wherein the one or more other aspects include one or more of low lateral curvature between the identified candidate future lateral positions of the vehicle for given future longitudinal positions of the vehicle, low lateral offsets from an identified lane center of the roadway at the identified candidate future lateral positions of the vehicle, far proximity from identified obstacles on the roadway at the identified candidate future lateral positions of the vehicle, and low deviation from a predetermined driving path along the roadway at the identified candidate future lateral positions of the vehicle.

7. The method of claim 1, wherein the energy function further algorithmically favors low lateral curvature between the identified candidate future lateral positions of the vehicle for given future longitudinal positions of the vehicle.

8. The method of claim 1, further comprising:

identifying, using the perception module executable by the at least one processor, from the detected information about the environment surrounding the vehicle, a lane center of the roadway; and

determining, using the planning/decision making module executable by the at least one processor, lateral offsets from the identified lane center of the roadway at the identified candidate future lateral positions of the vehicle, wherein the energy function further algorithmically favors low lateral offsets from the identified lane center of the roadway.

9. The method of claim 1, further comprising:

identifying, using the perception module executable by the at least one processor, from the detected information about the environment surrounding the vehicle, obstacles on the roadway; and

determining, using the planning/decision making module executable by the at least one processor, proximity from the identified obstacles on the roadway at the identified candidate future lateral positions of the vehicle, wherein the energy function further algorithmically favors far proximity from the identified obstacles on the roadway.

10. The method of claim 1, wherein the energy function further algorithmically favors low deviation from a predetermined driving path along the roadway.

11. The method of claim 1, further comprising:

detecting, using sensors, the information about the environment surrounding the vehicle.

12. A vehicle, comprising:

sensors configured to detect information about an environment surrounding the vehicle;

vehicle systems operable to maneuver the vehicle; and

one or more modules stored on memory and executable by at least one processor for initiating instructions, the instructions including;

identifying, from the detected information about the environment surrounding the vehicle, a lateral surface profile of the roadway;

determining, based on the lateral surface profile of the roadway, vertical wheel positions at identified candidate future lateral positions of the vehicle;

determining, as part of a driving path along the roadway, and based on the determined vertical wheel positions, future lateral positions of the vehicle from among the identified candidates therefor using an energy function that algorithmically favors low vertical wheel positions; and

operating the vehicle systems to maneuver the vehicle along the roadway according to a driving plan describing the driving path.

13. The vehicle of claim 12, wherein the instructions further include:

determining, in addition to the vertical wheel positions, one or more other aspects of the identified candidate future lateral positions of the vehicle, wherein the energy function further algorithmically favors the one or more other aspects; and

adjusting the extent which the energy function algorithmically favors low vertical wheel positions compared to the one or more other aspects based on an identified roadway condition.

14. The vehicle of claim 13, wherein the instructions further include:

identifying, as the roadway condition, the lateral surface profile of the roadway, with the lateral surface profile of the roadway representing one or more ruts on the roadway, and with the energy function increasingly algorithmically favoring low vertical wheel positions compared to the one or more other aspects with increasing depths of the one or more ruts on the roadway.

15. The vehicle of claim 13, wherein the one or more other aspects include one or more of low lateral curvature between the identified candidate future lateral positions of the vehicle for given future longitudinal positions of the vehicle, low lateral offsets from an identified lane center of the roadway at the identified candidate future lateral positions of the vehicle, far proximity from identified obstacles on the roadway at the identified candidate future lateral positions of the vehicle, and low deviation from a predetermined driving path along the roadway at the identified candidate future lateral positions of the vehicle.

16. The vehicle of claim 12, wherein the energy function further algorithmically favors low lateral curvature between the identified candidate future lateral positions of the vehicle for given future longitudinal positions of the vehicle.

17. The vehicle of claim 12, wherein the instructions further include:

identifying, from the detected information about the environment surrounding the vehicle, a lane center of the roadway.

18. The vehicle of claim 17, wherein the instructions further include:

determining lateral offsets from the identified lane center of the roadway at the identified candidate future lateral positions of the vehicle, wherein the energy function further algorithmically favors low lateral offsets from the identified lane center of the roadway.

19. The vehicle of claim 12, wherein the instructions further include:

identifying, from the detected information about the environment surrounding the vehicle, obstacles on the roadway; and

determining proximity from the identified obstacles on the roadway at the identified candidate future lateral positions of the vehicle, wherein the energy function further algorithmically favors far proximity from the identified obstacles on the roadway.

20. The vehicle of claim 12, wherein the energy function further algorithmically favors low deviation from a predetermined driving path along the roadway.