Systems and methods for updating the parameters of a model predictive controller with learned external parameters generated using simulations and machine learning

Patent metadata

Field	Value
Publication number	US-12409841-B2
Application number	US-202418634715-A
Country	US
Kind code	B2
Filing date	Apr 12, 2024
Priority date	Feb 2, 2021
Publication date	Sep 9, 2025
Grant date	Sep 9, 2025

Abstract

A computer implemented method for determining optimal values for operational parameters for a model predictive controller for controlling a vehicle, can receive from a data store or a graphical user interface, ranges for one or more external parameters. The computer implemented method can determine optimum values for external parameters of the vehicle by simulating a vehicle operation across the ranges of the one or more operational parameters by solving a vehicle control problem and determining an output of the vehicle control problem based on a result for the simulated vehicle operation. A vehicle can include a processing component configured to adjust a control input for an actuator of the vehicle according to a control algorithm and based on the optimum values of the vehicle parameter as determined by the computer implemented method.

First claim

What is claimed is:

1. A computer implemented method for determining optimal operational parameters for a model predictive controller for controlling a vehicle, the method comprising:
determining a value for an operational parameter amongst a range of potential values of the operational parameter based on:
simulating a vehicle operation across the range of potential values of the operational parameter by determining any change of a command lateral force to satisfy a level of stability of the vehicle; and
determining an output based on a result for the simulated vehicle operation, the output corresponding to the value for the operational parameter; and

training a machine learning vehicle performance circuit based on the output.

2. The method of claim 1 , wherein the operational parameter comprises at least one of:
a friction coefficient between at least one tire and a road,
a gravitational constant,
a road surface roughness,
an external humidity,
a wind vector, or
an external temperature.

3. The method of claim 1 , wherein the operational parameter comprises at least one or more vehicle parameters.

4. The method of claim 3 , wherein the one or more vehicle parameters is selected from a group consisting of a distance a from the center of gravity (CG) of the vehicle to a front axle of the vehicle, a distance b from the CG to a rear axle of the vehicle, a distance L from a center of the front axle to a center of the rear axle of the vehicle, a tire distance from the CG to the rear axle of the vehicle, a vehicle speed V x , a vehicle yaw rate r, vehicle sideslip angle β, front steering angle δ, front and rear lateral tire forces F yf and F yf , a vehicle mass m, a yaw inertia I zz , a height h of the vehicle's CG, a wheel radius R, a cornering stiffness C, a front axle cornering stiffness C af , and a rear axle cornering stiffness C ar .

5. The method of claim 1 , wherein the operational parameter is not directly measurable by a vehicle sensor, and wherein the vehicle operation is simulated across a range of one or more lateral forces which are directly measurable by the vehicle.

6. The method of claim 1 , wherein the vehicle operation comprises at least one of a path tracking, corridor keeping, stabilization, or collision avoidance maneuver, and the value for the operational parameter permits for the vehicle to at least one of:
(i) track a path in the path tracking maneuver,
(ii) remain within the corridor in the corridor keeping maneuver,
(iii) stabilize the vehicle in the stabilization maneuver, or
(iv) maneuver to avoid vehicle collision in the collision avoidance maneuver.

7. The method of claim 1 , further comprising:
generating a training set comprising the operational parameter, wherein the training set is configured to be used as an initial parameter set for the model predictive controller operating on the vehicle.

8. The method of claim 7 , wherein the vehicle operation comprises at least one of a path tracking, corridor keeping, stabilization, or collision avoidance maneuver, and wherein the trained machine learning vehicle performance circuit is trained by:
simulating the vehicle operation across a range of the operational parameter by solving a model predictive control problem for at least one of the path tracking, corridor keeping, stabilization, and collision avoidance maneuver; and
determining the value for the operational parameter based on an outcome of the at least one of the path tracking, corridor keeping, stabilization, and collision avoidance maneuver during simulation.

9. The method of claim 1 , wherein the operational parameter
is determined based on one or more other parameters.

10. The method of claim 1 , wherein the operational parameter further comprises at least one control parameter.

11. The method of claim 10 , wherein the at least one control parameter comprise one or more of a gain Q on a vehicle state, a gain R on an input to the model predictive controller, or a gain W on a slack to the vehicle state.

12. The method of claim 11 , wherein the operational parameter further comprises a vehicle parameter, and wherein the gain Q on the vehicle state, the gain R on the input, or the gain W on the slack, are gains based on the vehicle parameter.

13. The method of claim 11 , wherein the vehicle operation comprises at least one of a path tracking, corridor keeping, stabilization, or collision avoidance maneuver, and the value for the operational parameter corresponds to a value of the at least one control parameter which was determined by the trained machine learning vehicle performance circuit to allow for the vehicle to at least one of:
(i) track a path in the path tracking maneuver,
(ii) remain within the corridor in the corridor keeping maneuver,
(iii) stabilize the vehicle in a stabilization maneuver, or
(iv) maneuver the vehicle to avoid vehicle collision in the collision avoidance maneuver.

14. The method of claim 1 , wherein the vehicle operation is simulated within a model predictive control problem which controls a control input based on:
a current vehicle state;
predicted boundaries for the value of the operational parameter; and
a future vehicle state determined based on the predicted boundaries for the value of the operational parameter.

15. The method of claim 1 , wherein the command lateral force corresponds to a steering angle input by an operator of the vehicle.

16. The method of claim 1 , wherein the operational parameter measures a characteristic that is external to the vehicle.

17. A computer implemented method comprising:
determining a future state of a vehicle based on operational information and configuration information;
determining, based on the operational information, boundaries of the operational information;
determining, based on the operational information and contextual information, threshold values of a trajectory metric representative of circumventions to avoid vehicle catastrophe, wherein the trajectory metric identifies a level of stability of the vehicle; and
controlling the vehicle according to future vehicle state, boundaries of the operational information, and threshold values of the trajectory metric, wherein the controlling of the vehicle comprises implementing any change of a command lateral force to satisfy the level of stability.

18. The method of claim 17 , further comprising:
solving a vehicle control problem which solves for how the vehicle performs in simulation of a vehicle maneuver across a range of potential values of an operational parameter;
determining a solution for the vehicle control problem, the solution based on the performance of the vehicle in simulation of the vehicle maneuver; and
determining the operational parameter based on the solution.

19. The method of claim 15 , wherein the operational information of the vehicle comprises at least one of a distance a from the center of gravity (CG) of the vehicle to a front axle of the vehicle, a distance b from the CG to a rear axle of the vehicle, a distance L from a center of the front axle to a center of the rear axle of the vehicle, a tire distance from the CG to the rear axle of the vehicle, a vehicle speed V x , a vehicle yaw rate r, vehicle sideslip angle β, front steering angle δ, front and rear lateral tire forces F yf and F yf , a vehicle mass m, a yaw inertia I zz , a height h of the vehicle's CG, a wheel radius R, a cornering stiffness C, a front axle cornering stiffness C af , or a rear axle cornering stiffness C ar ; and
the contextual information co

Assignees

• Toyota Res Inst Inc

Inventors

• Thompson Michael
• Bobier-Tiu Carrie
• Ahumada Manuel
• Bhargava Arjun
• Balachandran Avinash

Classifications

• B60W30/02

  Control of vehicle driving stability · CPC title

• B60W2555/20

  Ambient conditions, e.g. wind or rain · CPC title

• B60W60/0015

  specially adapted for safety · CPC title

• B60W50/14

  Means for informing the driver, warning the driver or prompting a driver intervention · CPC title

• B60W30/10

  Path keeping {(cruise control for automatically following a preceding vehicle B60W30/165)} · CPC title