IP Library Granted Patent US 12,168,458
Granted Patent B2
US 12,168,458 · App. 17/717,416 · Granted Dec 17, 2024

Systems and methods for maneuvering vehicles using predictive control and automated driving

Inventors: Katherine Steele Schweidel (Berkeley, CA); Miroslav Baric (San Jose, CA); Sarah Koehler (San Jose, CA); Vishnu R. Desaraju (Ann Arbor, MI); Matthew Brown (Palo Alto, CA); Timothee Jean William Cazenave (Santa Clara, CA)
Assignee: Toyota Research Institute, Inc.
B60W60/0015B60W50/08B60W60/0013B60W60/0027
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,168,458
App. No.
17/717,416
Granted
Dec 17, 2024
Kind
B2
Abstract

System, methods, and other embodiments described herein relate to vehicle maneuvering using predictive control with automated driving and contingency planning to preserve safety and increase comfort. In one embodiment, a method includes receiving, by a controller, an operator command associated with a vehicle maneuver while automated driving is engaged. The method also includes adjusting a motion command associated with the vehicle maneuver by applying a predictive control according to motion estimates outputted from the automated driving and the operator command, the predictive control using motion constraints that are constant between time intervals for the vehicle maneuver. The method also includes controlling, by the controller, a vehicle using the motion command for a time step during the time intervals.

Claims (32)

1. A control system for improving maneuvering of a vehicle, comprising:

a processor; and

a memory storing instructions that, when executed by the processor, cause the processor to:

receive, by a controller, an operator command associated with a vehicle maneuver while automated driving is engaged;

adjust a motion command associated with the vehicle maneuver by applying a predictive control according to motion estimates outputted from the automated driving and the operator command and factoring manual control for the vehicle maneuver using a cost function, the predictive control using motion constraints that are constant between time intervals for the vehicle maneuver and the cost function includes weighted deviations from the operator command and predicted trajectories associated with the motion command; and

control, by the controller, the vehicle using the motion command for a time step during the time intervals.

2. The control system of claim 1 , further including instructions that when executed by the processor cause the processor to determine a nominal trajectory and a contingency trajectory for the vehicle maneuver by applying the predictive control using a model with the motion estimates, wherein the nominal trajectory is associated with predicted inputs from an operator for the vehicle maneuver using the motion estimates from the automated driving and the contingency trajectory is associated with the predicted inputs and actions by surrounding vehicles.

3. The control system of claim 2 , wherein the actions include braking or acceleration that decreases a safety margin of the vehicle maneuver and the contingency trajectory increases the safety margin of the vehicle maneuver.

4. The control system of claim 2 , wherein the motion command adopts the operator command when the vehicle maneuver meets a safety margin in the model.

5. The control system of claim 2 , wherein the nominal trajectory is equivalent to the contingency trajectory when a safety margin is satisfied in the model.

6. The control system of claim 2 , further including instructions that when executed by the processor cause the processor to control the vehicle maneuver according to the contingency trajectory by the automated driving in a response to a safety margin being unmet.

7. The control system of claim 1 , further including instructions that when executed by the processor cause the processor to prioritize, by a model, the manual control by an operator for the vehicle maneuver according to the cost function that is a sum of the weighted deviations from the operator command and the predicted trajectories from the automated driving associated with the motion command.

8. The control system of claim 1 , wherein the instructions to adjust the motion command further include instructions to maintain, by a model, a safe trajectory with the vehicle maneuver according to the operator command and a predicted command.

9. The control system of claim 1 , wherein the motion constraints are associated with the vehicle having a safe trajectory below a set speed when approaching an intersection and the motion command is used during shared control of the automated driving.

10. A non-transitory computer-readable medium comprising:

instructions that when executed by a processor cause the processor to:

receive, by a controller, an operator command associated with a vehicle maneuver while automated driving is engaged;

adjust a motion command associated with the vehicle maneuver by applying a predictive control according to motion estimates outputted from the automated driving and the operator command and factoring manual control for the vehicle maneuver using a cost function, the predictive control using motion constraints that are constant between time intervals for the vehicle maneuver and the cost function includes weighted deviations from the operator command and predicted trajectories associated with the motion command; and

control, by the controller, a vehicle using the motion command for a time step during the time intervals.

11. The non-transitory computer-readable medium of claim 10 , further including instructions that when executed by the processor cause the processor to determine a nominal trajectory and a contingency trajectory for the vehicle maneuver by applying the predictive control using a model with the motion estimates, wherein the nominal trajectory is associated with predicted inputs from an operator for the vehicle maneuver using the motion estimates from the automated driving and the contingency trajectory is associated with the predicted inputs and actions by surrounding vehicles.

12. A method comprising:

receiving, by a controller, an operator command associated with a vehicle maneuver while automated driving is engaged;

adjusting a motion command associated with the vehicle maneuver by applying a predictive control according to motion estimates outputted from the automated driving and the operator command and factoring manual control for the vehicle maneuver using a cost function, the predictive control using motion constraints that are constant between time intervals for the vehicle maneuver and the cost function includes weighted deviations from the operator command and predicted trajectories associated with the motion command; and

controlling, by the controller, a vehicle using the motion command for a time step during the time intervals.

13. The method of claim 12 , further comprising determining a nominal trajectory and a contingency trajectory for the vehicle maneuver by applying the predictive control using a model with the motion estimates, wherein the nominal trajectory is associated with predicted inputs from an operator for the vehicle maneuver using the motion estimates from the automated driving and the contingency trajectory is associated with the predicted inputs and actions by surrounding vehicles.

14. The method of claim 13 , wherein the actions include braking or acceleration that decreases a safety margin of the vehicle maneuver and the contingency trajectory increases the safety margin of the vehicle maneuver.

15. The method of claim 13 , wherein the motion command adopts the operator command when the vehicle maneuver meets a safety margin in the model.

16. The method of claim 13 , wherein the nominal trajectory is equivalent to the contingency trajectory when a safety margin is satisfied in the model.

17. The method of claim 13 , further comprising controlling the vehicle maneuver according to the contingency trajectory by the automated driving in response to determining that a safety margin is unmet.

18. The method of claim 12 , further comprising prioritizing, by a model, the manual control by an operator for the vehicle maneuver according to the cost function that is a sum of the weighted deviations from the operator command and the predicted trajectories from the automated driving associated with the motion command.

19. The method of claim 12 , wherein adjusting the motion command further includes maintaining, by a model, a safe trajectory with the vehicle maneuver according to the operator command and a predicted command.

20. The method of claim 12 , wherein the motion constraints are associated with the vehicle having a safe trajectory below a set speed when approaching an intersection and the motion command is used during shared control of the automated driving.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 31, 2024
From: TOYOTA RESEARCH INSTITUTE, INC.
To: TOYOTA JIDOSHA KABUSHIKI KAISHA
Reel/Frame 069706/0500 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 12, 2022
From: SCHWEIDEL, KATHERINE STEELE; BARIC, MIROSLAV; KOEHLER, SARAH; DESARAJU, VISHNU R.; BROWN, MATTHEW; CAZENAVE, TIMOTHEE JEAN WILLIAM
To: TOYOTA RESEARCH INSTITUTE, INC.
Reel/Frame 059571/0696 →
Continuity (2)
Provisional Application 63276164 · Nov 5, 2021
Related Publication 20230141801A1 · May 11, 2023