Systems and methods for neural ordinary differential equation learned tire models
View Patent ↗System, methods, and other embodiments described herein relate to NODE learned tire models. In one embodiment, a method includes calculating estimated tire forces based on vehicle measurements; solving a second order differential equation in a repetitive manner until an error calculation based on a tire force function and the estimated tire forces reaches a minimum value, by: using a first predictive model to provide one or more inflection points and initial conditions based on the vehicle measurements, using a second and third predictive model to act as, respectively, exponents to a positive and a negative exponential equation based on the one or more inflection points, the initial conditions, and the vehicle measurements, and integrating the exponential equations to obtain the tire force function; and applying the tire force function to new vehicle measurements to estimate current tire forces.
1. A method comprising:
receiving estimated tire forces and vehicle measurements;
solving a second order differential equation in a repetitive manner until an error calculation based on a tire force function and the estimated tire forces reaches a minimum value, by:
using a first predictive model to provide one or more inflection points and initial conditions based on the vehicle measurements,
using a second and third predictive model to act as, respectively, exponents to a positive and a negative exponential equation based on the one or more inflection points, the initial conditions, and the vehicle measurements, and
integrating the exponential equations to obtain the tire force function; and
wherein the tire force function when applied to further vehicle measurements provides a tire force estimate.
2. The method of claim 1 , wherein solving the second order differential equation further includes using a fourth predictive model to obtain scaling parameters for estimating a lateral tire force function or a longitudinal tire force function from the tire force function.
3. The method of claim 2 , further comprising generating a fifth predictive model to replicate the tire force function.
4. The method of claim 2 , further comprising receiving the tire force estimate from the tire force function and adjusting a vehicle control input based on the tire force estimate.
5. The method of claim 2 , further comprising selecting a confidence parameter.
6. The method of claim 1 , further comprising generating a fourth predictive model to replicate the tire force function.
7. The method of claim 1 , further comprising receiving the tire force estimate from the tire force function and adjusting a vehicle control input based on the tire force estimate.
8. The method of claim 1 , further comprising selecting a confidence parameter.
9. A system comprising:
a processor; and
a memory storing instructions that, when executed by the processor, cause the processor to:
receive estimated tire forces and vehicle measurements;
solve a second order differential equation in a repetitive manner until an error calculation based on a tire force function and the estimated tire forces reaches a minimum value, by:
using a first predictive model to provide one or more inflection points and initial conditions based on the vehicle measurements,
using a second and third predictive model to act as, respectively, exponents to a positive and a negative exponential equation based on the one or more inflection points, the initial conditions, and the vehicle measurements, and
integrating the exponential equations to obtain the tire force function; and
wherein the tire force function when applied to further vehicle measurements provides a tire force estimate.
10. The system of claim 9 , wherein the instruction to solve the second order differential equation further includes using a fourth predictive model to obtain scaling parameters for estimating a lateral tire force function or a longitudinal tire force function from the tire force function.
11. The system of claim 10 , wherein the instructions further include an instruction to generate a fifth predictive model to replicate the tire force function.
12. The system of claim 10 , wherein the instructions further include instructions to:
receive the tire force estimate from the tire force function; and
adjust a vehicle control input based on the tire force estimate.
13. The system of claim 10 , wherein the instructions further include an instruction to select a confidence parameter.
14. The system of claim 9 , wherein the instructions further include an instruction to generate a fourth predictive model to replicate the tire force function.
15. The system of claim 9 , wherein the instructions further include instructions to:
receive the tire force estimate from the tire force function; and
adjust a vehicle control input based on the tire force estimate.
16. The system of claim 9 , wherein the instructions further include an instruction to select a confidence parameter.
17. A system comprising:
a processor; and
a memory storing instructions that, when executed by the processor, cause the processor to:
receive vehicle measurements, one or more inflection points, and initial conditions;
apply a first and second predictive model to act as, respectively, exponents to a positive and a negative exponential equation based on the one or more inflection points, the initial conditions, and the vehicle measurements; and
perform integration of the exponential equations to obtain a tire force estimate.
18. The system of claim 17 , wherein the instructions further include to apply scaling parameters to estimate a lateral tire force estimate or a longitudinal tire force estimate from the tire force estimate.
19. The system of claim 18 , wherein the instructions further include to adjust a vehicle control input based on the lateral tire force estimate, the longitudinal tire force estimate, or the tire force estimate.
20. The system of claim 17 , wherein the instructions further include to adjust a vehicle control input based on the tire force estimate.