IP Library Granted Patent US 12,576,866
Granted Patent B2
US 12,576,866 · App. 18/355,678 · Granted Mar 17, 2026

Calibration framework for autonomous vehicle simulation technology

Inventors: Shen Qu (San Diego, CA); Liu Liu (San Diego, CA); Junbo Jing (San Diego, CA); Haoming Sun (San Diego, CA)
Assignee: CreateAI, Inc.
B60W50/06B60W60/00G05B17/02G07C5/02B60W2050/0056B60W2510/20B60W2520/10B60W2520/105B60W2520/125B60W2520/14B60W2520/16B60W2520/18B60W2552/15
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 12,576,866
App. No.
18/355,678
Granted
Mar 17, 2026
Kind
B2
Abstract

Vehicle dynamics related parameter(s) of an autonomous vehicle model can be calibrated so that the autonomous vehicle model can more accurately determine the driving related behaviors of the autonomous vehicle. An example method comprises obtaining, from sensor data, vehicle related parameters; performing a first determination of a slope of a road and a banking angle of the road based on a pitch angle of the vehicle and a roll angle of the vehicle, respectively; performing a second determination of a set of parameters that describe a driving-related operation of the vehicle; performing a third determination that at least one difference between at least one value from the set of parameters and a corresponding parameter from the plurality of vehicle related parameters exceeds at least one threshold value; and obtaining, in response to the third determination, a calibrated longitudinal dynamic-related parameter or a calibrated lateral dynamic-related parameter.

Claims (69)

1 . A method of calibrating a parameter related to a vehicle, comprising:

obtaining, from sensor data related to a road test previously performed by the vehicle, a plurality of vehicle related parameters associated with a same time stamp,

wherein the plurality of vehicle related parameters include a pitch angle of the vehicle and a roll angle of the vehicle;

performing a first determination of a slope of a road and a banking angle of the road based on the pitch angle of the vehicle and the roll angle of the vehicle, respectively;

performing a second determination, without performing an additional road test by the vehicle, of a set of parameters that describe a driving-related operation of the vehicle,

wherein the set of parameters include a first yaw rate of the vehicle that is determined based at least on the banking angle, and

wherein the set of parameters include a first amount of throttle of the vehicle that is determined based at least on the slope;

performing a third determination that at least one difference between at least one value from the set of parameters and a corresponding parameter from the plurality of vehicle related parameters exceeds at least one threshold value;

obtaining, in response to the third determination, a calibrated longitudinal dynamic-related parameter or a calibrated lateral dynamic-related parameter by calibrating a longitudinal dynamic-related parameter or a lateral dynamic-related parameter; and

sending the calibrated longitudinal dynamic-related parameter or the calibrated lateral dynamic-related parameter to the vehicle to cause the vehicle to use the calibrated longitudinal dynamic-related parameter or the calibrated lateral dynamic-related parameter to perform autonomous driving operations.

2 . The method of claim 1 , wherein the longitudinal dynamic-related parameter includes one or more constant coefficients that is related to a longitudinal acceleration of the vehicle, or a drive force applied by the vehicle.

3 . The method of claim 1 , wherein the lateral dynamic-related parameter includes one or more constant coefficients that is related to a lateral acceleration of the vehicle.

4 . The method of claim 1 , wherein the set of parameters are determined by simulating the driving-related operation of the vehicle.

5 . The method of claim 1 , wherein the slope of the road is determined by:

filtering the pitch angle of the vehicle using a second order low pass filter to obtain a filtered pitch angle;

determining an equivalent gravity force applied in a longitudinal direction of the vehicle using the filtered pitch angle; and

determining the slope of the road by using following equation:

sin (the slope)*gravity=the equivalent gravity force applied on the longitudinal direction,

wherein sin( ) is a trigonometric sine function.

6 . The method of claim 1 , wherein the banking angle of the road is determined by:

filtering the roll angle of the vehicle using a second order low pass filter to obtain the banking angle.

7 . The method of claim 1 ,

wherein the plurality of vehicle related parameters include a speed of the vehicle and a steering angle of the vehicle, and

wherein the set of parameters are determined by:

determining an amount of throttle of the vehicle based on the speed of the vehicle; and

determining the first yaw rate of the vehicle based on the amount of throttle, the steering angle of the vehicle, and the banking angle.

8 . The method of claim 7 ,

wherein the at least one value from the set of parameters is the first yaw rate, and

wherein the third determination is performed by determining that a difference between the first yaw rate and a second yaw rate obtained from the plurality of vehicle related parameters is greater than a first pre-determined threshold value.

9 . The method of claim 1 ,

wherein the plurality of vehicle related parameters include a speed of the vehicle and a steering angle of the vehicle,

wherein a second amount of throttle of the vehicle is determined based on the speed of the vehicle, and

wherein the set of parameters includes the first amount of throttle of the vehicle that is determined based on the second amount of throttle, the steering angle of the vehicle, and the slope.

10 . The method of claim 9 ,

wherein the third determination is performed by determining that a difference between the first amount of throttle and a third amount of throttle obtained from the plurality of vehicle related parameters is greater than a second pre-determined threshold value.

11 . The method of claim 1 , wherein the sensor data is obtained from sensors located on the vehicle and characterizes the road on which the vehicle is previously operated or an environment in which the vehicle is previously operated.

12 . An apparatus for autonomous vehicle operation, comprising:

at least one processor configured to implement a method, the at least one processor configured to: obtain, from sensor data related to a road test previously performed by a vehicle, a plurality of vehicle related parameters associated with a same time stamp,

wherein the plurality of vehicle related parameters include a pitch angle of the vehicle and a roll angle of the vehicle;

perform a first determination of a slope of a road and a banking angle of the road based on the pitch angle of the vehicle and the roll angle of the vehicle, respectively;

perform a second determination, without performing an additional road test by the vehicle, of a set of parameters that describe a driving-related operation of the vehicle,

wherein the set of parameters include a first yaw rate of the vehicle that is determined based at least on the banking angle, and

wherein the set of parameters include a first amount of throttle of the vehicle that is determined based at least on the slope;

perform a third determination that at least one difference between at least one value from the set of parameters and a corresponding parameter from the plurality of vehicle related parameters exceeds at least one threshold value;

obtain, in response to the third determination, a calibrated longitudinal dynamic-related parameter or a calibrated lateral dynamic-related parameter by calibrating a longitudinal dynamic-related parameter or a lateral dynamic-related parameter; and

send the calibrated longitudinal dynamic-related parameter or the calibrated lateral dynamic-related parameter to the vehicle to cause the vehicle to use the calibrated longitudinal dynamic-related parameter or the calibrated lateral dynamic-related parameter to perform autonomous driving operations.

13 . The apparatus of claim 12 , wherein the longitudinal dynamic-related parameter includes one or more constant coefficients that is related to a longitudinal speed of the vehicle.

14 . The apparatus of claim 12 , wherein the lateral dynamic-related parameter includes one or more constant coefficients that is related to a yaw rate of the vehicle.

15 . The apparatus of claim 12 , wherein the slope is determined by the at least one processor configured to:

filter the pitch angle of the vehicle to obtain a filtered pitch angle;

determine an equivalent gravity force applied in a longitudinal direction of the vehicle using the filtered pitch angle, and

determine the slope of the road based on gravity and the equivalent gravity force applied on the longitudinal direction.

16 . The apparatus of claim 12 , wherein the banking angle of the road is determined by the at least one processor configured to:

filter the roll angle of the vehicle to obtain the banking angle.

17 . A non-transitory computer readable program storage medium having code stored thereon, the code, when executed by a processor, causing the processor to implement a method, comprising:

obtaining, from sensor data related to a road test previously performed by a vehicle, a plurality of vehicle related parameters associated with a same time stamp,

wherein the plurality of vehicle related parameters include a pitch angle of the vehicle and a roll angle of the vehicle;

performing a first determination of a slope of a road and a banking angle of the road based on the pitch angle of the vehicle and the roll angle of the vehicle, respectively;

performing a second determination, without performing an additional road test by the vehicle, of a set of parameters that describe a driving-related operation of the vehicle,

wherein the set of parameters include a first yaw rate of the vehicle that is determined based at least on the banking angle, and

wherein the set of parameters include a first amount of throttle of the vehicle that is determined based at least on the slope;

performing a third determination that at least one difference between at least one value from the set of parameters and a corresponding parameter from the plurality of vehicle related parameters exceeds at least one threshold value;

obtaining, in response to the third determination, a calibrated longitudinal dynamic-related parameter or a calibrated lateral dynamic-related parameter by calibrating a longitudinal dynamic-related parameter or a lateral dynamic-related parameter; and

sending the calibrated longitudinal dynamic-related parameter or the calibrated lateral dynamic-related parameter to the vehicle to cause the vehicle to use the calibrated longitudinal dynamic-related parameter or the calibrated lateral dynamic-related parameter to perform autonomous driving operations.

18 . The non-transitory computer readable program storage medium of claim 17 , wherein the set of parameters are determined by determining the first yaw rate of the vehicle that is based on an amount of throttle, a steering angle of the vehicle, and the banking angle.

19 . The non-transitory computer readable program storage medium of claim 17 ,

wherein the set of parameters includes the first amount of throttle of the vehicle that is determined based on a second amount of throttle, a steering angle of the vehicle, and the slope, and

wherein the second amount of throttle of the vehicle is based on a speed of the vehicle.

20 . The non-transitory computer readable program storage medium of claim 19 , wherein the at least one value from the set of parameters is a drive force value.

Assignments (2)
CHANGE OF NAME Recorded Dec 3, 2025
From: TUSIMPLE, INC.
To: CREATEAI, INC.
Reel/Frame 073832/0553 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 18, 2023
From: QU, SHEN; LIU, LIU; JING, JUNBO; SUN, HAOMING
To: TUSIMPLE, INC.
Reel/Frame 064940/0786 →
Continuity (2)
Provisional Application 63369933 · Jul 29, 2022
Related Publication 20240034341A1 · Feb 1, 2024
References Cited (6)
US 20070260438A1 · Langer et al. · 2007 [cited by applicant]
US 20100168958A1 · Baino · 2010 [cited by examiner]
US 20110208402A1 · Sladek, Jr. · 2011 [cited by examiner]
US 20120067122A1 · Sakamoto · 2012 [cited by examiner]
US 20160068166A1 · Chen · 2016 [cited by examiner]
US 20200207412A1 · Al Assad · 2020 [cited by examiner]