Wheel force control system

Abstract

A wheel force control system includes a plurality of wheel height sensors, a vehicle IMU configured to measure lateral and longitudinal accelerations, and a vehicle control module configured to: obtain a wheel height parameter from the plurality of wheel height sensors; obtaining vehicle transverse and longitudinal acceleration parameters from the vehicle IMU; estimating a pitch arm rotation value of the vehicle; determining a pitch center of the vehicle based on the pitch arm rotation value, the wheel height parameter, and the vehicle lateral acceleration parameter and the vehicle longitudinal acceleration parameter; calculating the gravity center of the vehicle according to the determined pitching center; determining an estimated normal force on at least one wheel of the vehicle based at least in part on the calculated center of gravity of the vehicle; and controlling operation of at least one vehicle component according to the estimated normal force.

Description

[0001] Introduction

[0002] The information provided in this section is for the purpose of generally presenting the context of the present disclosure. The work of the currently listed inventors (to the extent described in this section) and aspects that may not have been in the prior art at the time of filing the description are neither expressly nor impliedly admitted as prior art against the present disclosure.

[0003] The present disclosure generally relates to a wheel force control system that includes estimating a wheel normal force via a combination of an inertial measurement unit (IMU)-based estimate and a spring-based estimate.

[0004] In many challenging driving scenarios, control actions such as wheel and / or axle torque can be optimally distributed so that tire capabilities are fully utilized in the longitudinal and lateral directions. Typical tire capability management is performed by an on-vehicle computing platform or controller and sensors, including an inertial measurement unit (IMU) configured to measure how the vehicle moves in space. The IMU can be configured to measure vehicle acceleration on three axes: x (front / rear), y (side-to-side), and z (up / down). The IMU can also measure the speed at which the motor vehicle rotates about the three axes, referred to as pitch rate (about y), yaw rate (about z), and roll rate (about x). The on-vehicle computing platform or controller uses this measurement data to estimate the forces acting on the vehicle. Summary of the Invention

[0005] A wheel force control system includes: a plurality of wheel height sensors, each wheel height sensor being configured to measure the wheel height position of a corresponding wheel of the vehicle; a vehicle inertial measurement unit (IMU) configured to measure the lateral acceleration of the vehicle and the longitudinal acceleration of the vehicle; and a vehicle control module in communication with the plurality of wheel height sensors and the vehicle IMU. The vehicle control module is configured to: obtain wheel height parameters from the plurality of wheel height sensors; obtain vehicle lateral acceleration parameters and vehicle longitudinal acceleration parameters from the vehicle IMU; estimate a pitch arm rotation value of the vehicle; determine a pitch center of the vehicle based on the pitch arm rotation value, the wheel height parameters, and the vehicle lateral acceleration parameters and the vehicle longitudinal acceleration parameters; calculate a center of gravity of the vehicle based on the determined pitch center; determine an estimated normal force on at least one wheel of the vehicle at least in part based on the calculated center of gravity of the vehicle; and control the operation of at least one vehicle component based on the estimated normal force.

[0006] In other examples, the estimated normal force is an IMU-based estimated normal force, and the vehicle control module is configured to: determine an anti-dive compensation value based on longitudinal acceleration at least according to the vehicle longitudinal acceleration parameter; determine an anti-dive compensation value based on pitch angle at least according to the vehicle longitudinal acceleration parameter; calculate a combined anti-dive compensation value according to the anti-dive compensation value based on longitudinal acceleration and the anti-dive compensation value based on pitch angle; and determine the spring-based estimated normal force on at least one wheel of the vehicle at least partially based on the combined anti-dive compensation value.

[0007] In other examples, the vehicle control module is configured to: determine a roll rate compensation value based on lateral acceleration at least according to the vehicle lateral acceleration parameter; determine a roll rate compensation value based on roll angle at least according to the vehicle longitudinal acceleration parameter; calculate a combined roll rate compensation value according to the roll rate compensation value based on lateral acceleration and the roll rate compensation value based on roll angle; and determine the spring-based estimated normal force on at least one wheel of the vehicle at least partially based on the combined roll rate compensation value.

[0008] In other examples, the vehicle control module is configured to: calculate a suspension spring displacement value of at least one spring of the vehicle suspension; calculate a suspension spring damping force value of the at least one spring of the vehicle suspension; and determine the spring-based estimated normal force on at least one wheel of the vehicle at least partially based on the suspension spring displacement value and the suspension spring damping force.

[0009] In other examples, the vehicle control module is configured to: determine a reliability score of the IMU-based estimated normal force and the spring-based estimated normal force via a trained machine learning model; and determine a combined estimated normal force on at least one wheel of the vehicle according to a weighted combination of the IMU-based estimated normal force and the spring-based estimated normal force, wherein the weighted combination is assigned based on the reliability scores of the IMU-based estimated normal force and the spring-based estimated normal force.

[0010] In other examples, the trained machine learning model is trained based on multiple failure modes, each failure mode being associated with at least one of the IMU-based estimated normal force and the spring-based estimated normal force; and each of the multiple failure modes is associated with one or more corresponding vehicle parameters indicating the failure mode.

[0011] In other examples, the vehicle control module is configured to: compare the vehicle longitudinal acceleration parameter with a specified excessive acceleration threshold; in response to the vehicle longitudinal acceleration parameter exceeding the specified excessive acceleration threshold, reset the value of the vehicle pitch angle; and in response to the vehicle longitudinal acceleration parameter being less than the specified excessive acceleration threshold, perform an integration of the vehicle pitch rate.

[0012] In other examples, the vehicle control module is configured to: obtain a pitch center position function, where the pitch center position function is determined offline based on at least one geometric mode of the vehicle suspension; and online determine the pitch center of the vehicle based at least in part on the pitch center position function.

[0013] In other examples, controlling the operation of at least one vehicle component includes at least one of the following: controlling the position of a movable aerodynamic surface of the vehicle based on the estimated normal force; or controlling the amount of torque supplied to at least one wheel of the vehicle based on the estimated normal force.

[0014] In other examples, the vehicle control module is configured to estimate the pitch arm rotation value of the vehicle by: calculating a rotational pitch acceleration value of the vehicle based on the vehicle longitudinal acceleration parameter; and using the least squares method to estimate the pitch arm rotation value of the vehicle based on the calculated rotational pitch acceleration value.

[0015] In other examples, the vehicle control module is configured to: determine a rigid body lateral load transfer value of the vehicle; determine a rigid body longitudinal load transfer value of the vehicle; determine a suspension compensated lateral load transfer value of the vehicle; determine a suspension compensated longitudinal load transfer value of the vehicle; and determine the estimated normal force on at least one wheel of the vehicle based at least in part on the rigid body lateral load transfer value, rigid body longitudinal load transfer value, suspension compensated lateral load transfer value, and suspension compensated longitudinal load transfer value of the vehicle.

[0016] A wheel force control system includes: a plurality of wheel height sensors, each wheel height sensor being configured to measure the wheel height position of a corresponding wheel of a vehicle; a vehicle inertial measurement unit (IMU) configured to measure a lateral acceleration of the vehicle and a longitudinal acceleration of the vehicle; and a vehicle control module in communication with the plurality of wheel height sensors and the vehicle IMU. The vehicle control module is configured to: obtain wheel height parameters from the plurality of wheel height sensors; obtain a vehicle lateral acceleration parameter and a vehicle longitudinal acceleration parameter; determine an anti-dive compensation value based on longitudinal acceleration at least according to the vehicle longitudinal acceleration parameter; determine an anti-dive compensation value based on pitch angle at least according to the vehicle longitudinal acceleration parameter; calculate a combined anti-dive compensation value based on the anti-dive compensation value based on longitudinal acceleration and the anti-dive compensation value based on pitch angle; determine an estimated normal force on at least one wheel of the vehicle at least partially based on the combined anti-dive compensation value; and control the operation of at least one vehicle component according to the estimated normal force.

[0017] In other examples, the vehicle control module is configured to: determine a roll rate compensation value based on lateral acceleration at least according to the vehicle lateral acceleration parameter; determine a roll rate compensation value based on roll angle at least according to the vehicle longitudinal acceleration parameter; calculate a combined roll rate compensation value based on the roll rate compensation value based on lateral acceleration and the roll rate compensation value based on roll angle; and determine the estimated normal force on the at least one wheel of the vehicle at least partially based on the combined roll rate compensation value.

[0018] In other examples, the vehicle control module is configured to: calculate a suspension spring displacement value of at least one spring of a vehicle suspension; calculate a suspension spring damping force value of the at least one spring of the vehicle suspension; and determine the estimated normal force on the at least one wheel of the vehicle at least partially based on the suspension spring displacement value and the suspension spring damping force.

[0019] In other examples, controlling the operation of at least one vehicle component includes at least one of the following: controlling the position of a movable aerodynamic surface of the vehicle based on the estimated normal force; or controlling the amount of torque supplied to at least one wheel of the vehicle based on the estimated normal force.

[0020] In other examples, the vehicle control module is configured to determine a reliability score of the estimated normal force via a trained machine learning model.

[0021] In other examples, the trained machine learning model is trained based on multiple fault modes, each fault mode being associated with the estimated normal force; and each of the multiple fault modes is associated with one or more corresponding vehicle parameters indicative of the fault mode.

[0022] A wheel force control system includes: a plurality of wheel height sensors, each wheel height sensor being configured to measure the wheel height position of a corresponding wheel of a vehicle; a vehicle inertial measurement unit (IMU) configured to measure a lateral acceleration of the vehicle and a longitudinal acceleration of the vehicle; and a vehicle control module in communication with the plurality of wheel height sensors and the vehicle IMU. The vehicle control module is configured to: obtain wheel height parameters from the plurality of wheel height sensors; obtain a vehicle lateral acceleration parameter and a vehicle longitudinal acceleration parameter from the vehicle IMU; determine an IMU-based estimated normal force on at least one wheel of the vehicle at least partially based on a calculated center of gravity of the vehicle; determine a spring-based estimated normal force on the at least one wheel of the vehicle at least partially based on a combined anti-dive compensation value and a calculated combined anti-dive compensation value; determine a reliability score of the IMU-based estimated normal force and the spring-based estimated normal force via a trained machine learning model; determine a combined estimated normal force on the at least one wheel of the vehicle based on a weighted combination of the IMU-based estimated normal force and the spring-based estimated normal force, wherein the weighted combination is assigned based on the reliability scores of the IMU-based estimated normal force and the spring-based estimated normal force; and control an operation of at least one vehicle component based on the combined estimated normal force.

[0023] In other examples, the trained machine learning model is trained based on multiple fault modes, each fault mode being associated with at least one of the IMU-based estimated normal force and the spring-based estimated normal force; and each of the multiple fault modes is associated with one or more corresponding vehicle parameters indicative of the fault mode.

[0024] In other examples, controlling an operation of at least one vehicle component includes at least one of: controlling a position of a movable aerodynamic surface of the vehicle based on the combined estimated normal force; or controlling an amount of torque supplied to at least one wheel of the vehicle based on the combined estimated normal force.

[0025] The present disclosure provides the following technical solutions:

[0026] Technical solution 1. A wheel force control system, comprising:

[0027] a plurality of wheel height sensors, each wheel height sensor being configured to measure the wheel height position of a corresponding wheel of a vehicle;

[0028] A vehicle inertial measurement unit (IMU) configured to measure a lateral acceleration of the vehicle and a longitudinal acceleration of the vehicle; and

[0029] A vehicle control module in communication with the plurality of wheel height sensors and the vehicle IMU, the vehicle control module being configured to:

[0030] Obtain wheel height parameters from the plurality of wheel height sensors;

[0031] Obtain a vehicle lateral acceleration parameter and a vehicle longitudinal acceleration parameter from the vehicle IMU;

[0032] Estimate a pitch arm rotation value of the vehicle;

[0033] Determine a pitch center of the vehicle based on the pitch arm rotation value, the wheel height parameters, and the vehicle lateral acceleration parameter and the vehicle longitudinal acceleration parameter;

[0034] Calculate a center of gravity of the vehicle based on the determined pitch center;

[0035] Determine an estimated normal force on at least one wheel of the vehicle based at least in part on the calculated center of gravity of the vehicle; and

[0036] Control an operation of at least one vehicle component based on the estimated normal force.

[0037] Technical solution 2. The wheel force control system according to technical solution 1, wherein the estimated normal force is an IMU-based estimated normal force, and the vehicle control module is configured to:

[0038] Determine an anti-dive compensation value based on longitudinal acceleration at least according to the vehicle longitudinal acceleration parameter;

[0039] Determine an anti-dive compensation value based on pitch angle at least according to the vehicle longitudinal acceleration parameter;

[0040] Calculate a combined anti-dive compensation value according to the anti-dive compensation value based on longitudinal acceleration and the anti-dive compensation value based on pitch angle; and

[0041] Determine a spring-based estimated normal force on the at least one wheel of the vehicle based at least in part on the combined anti-dive compensation value.

[0042] Technical solution 3. The wheel force control system according to technical solution 2, wherein the vehicle control module is configured to:

[0043] Determine a roll rate compensation value based on lateral acceleration at least according to the vehicle lateral acceleration parameter;

[0044] Determine a roll rate compensation value based on roll angle at least according to the vehicle longitudinal acceleration parameter;

[0045] Calculate a combined roll rate compensation value based on the roll rate compensation value based on lateral acceleration and the roll rate compensation value based on roll angle; and

[0046] Determine the spring-based estimated normal force on at least one wheel of the vehicle at least partially based on the combined roll rate compensation value.

[0047] Technical solution 4. The wheel force control system according to technical solution 3, wherein the vehicle control module is configured to:

[0048] Calculate a suspension spring displacement value of at least one spring of the vehicle suspension;

[0049] Calculate a suspension spring damping force value of the at least one spring of the vehicle suspension; and

[0050] Determine the spring-based estimated normal force on at least one wheel of the vehicle at least partially based on the suspension spring displacement value and the suspension spring damping force.

[0051] Technical solution 5. The wheel force control system according to technical solution 4, wherein the vehicle control module is configured to:

[0052] Determine reliability scores of the IMU-based estimated normal force and the spring-based estimated normal force via a trained machine learning model; and

[0053] Determine a combined estimated normal force on at least one wheel of the vehicle based on a weighted combination of the IMU-based estimated normal force and the spring-based estimated normal force, wherein the weighted combination is assigned based on the reliability scores of the IMU-based estimated normal force and the spring-based estimated normal force.

[0054] Technical solution 6. The wheel force control system according to technical solution 5, wherein:

[0055] Train the trained machine learning model based on multiple failure modes, each failure mode being associated with at least one of the IMU-based estimated normal force and the spring-based estimated normal force; and

[0056] Each of the multiple failure modes is associated with one or more corresponding vehicle parameters indicating the failure mode.

[0057] Technical solution 7. The wheel force control system according to technical solution 1, wherein the vehicle control module is configured to:

[0058] Compare the vehicle longitudinal acceleration parameter with a specified excessive acceleration threshold;

[0059] In response to the vehicle longitudinal acceleration parameter exceeding the specified excessive acceleration threshold, reset the value of the vehicle pitch angle; and

[0060] In response to the vehicle longitudinal acceleration parameter being less than the specified excessive acceleration threshold, perform integration of the vehicle pitch rate.

[0061] Technical solution 8. The wheel force control system according to technical solution 1, wherein the vehicle control module is configured to:

[0062] Obtain a pitch center position function, wherein the pitch center position function is determined offline according to at least one geometric mode of the vehicle suspension; and

[0063] Determine the pitch center of the vehicle online at least partially based on the pitch center position function.

[0064] Technical solution 9. The wheel force control system according to technical solution 1, wherein controlling the operation of at least one vehicle component includes at least one of the following:

[0065] Control the position of the movable aerodynamic surface of the vehicle based on the estimated normal force; or

[0066] Control the amount of torque supplied to at least one wheel of the vehicle based on the estimated normal force.

[0067] Technical solution 10. The wheel force control system according to technical solution 1, wherein the vehicle control module is configured to estimate the pitch arm rotation value of the vehicle in the following manner:

[0068] Calculate the rotational pitch acceleration value of the vehicle based on the vehicle longitudinal acceleration parameter; and

[0069] Estimate the pitch arm rotation value of the vehicle using the least squares method based on the calculated rotational pitch acceleration value.

[0070] Technical solution 11. The wheel force control system according to technical solution 1, wherein the vehicle control module is configured to:

[0071] Determine the rigid body lateral load transfer value of the vehicle;

[0072] Determine the rigid body longitudinal load transfer value of the vehicle;

[0073] Determine the suspension compensation lateral load transfer value of the vehicle;

[0074] Determine a suspension compensation longitudinal load transfer value for the vehicle; and

[0075] Determine the estimated normal force on at least one wheel of the vehicle based at least in part on the rigid body lateral load transfer value, rigid body longitudinal load transfer value, suspension compensation lateral load transfer value, and suspension compensation longitudinal load transfer value of the vehicle.

[0076] Technical solution 12. A wheel force control system, comprising:

[0077] A plurality of wheel height sensors, each wheel height sensor being configured to measure the wheel height position of a corresponding wheel of the vehicle;

[0078] A vehicle inertial measurement unit (IMU), configured to measure the lateral acceleration of the vehicle and the longitudinal acceleration of the vehicle; and

[0079] A vehicle control module in communication with the plurality of wheel height sensors and the vehicle IMU, the vehicle control module being configured to:

[0080] Obtain wheel height parameters from the plurality of wheel height sensors;

[0081] Obtain a vehicle lateral acceleration parameter and a vehicle longitudinal acceleration parameter;

[0082] Determine an anti-dive compensation value based on longitudinal acceleration at least according to the vehicle longitudinal acceleration parameter;

[0083] Determine an anti-dive compensation value based on pitch angle at least according to the vehicle longitudinal acceleration parameter;

[0084] Calculate a combined anti-dive compensation value according to the anti-dive compensation value based on longitudinal acceleration and the anti-dive compensation value based on pitch angle;

[0085] Determine the estimated normal force on at least one wheel of the vehicle based at least in part on the combined anti-dive compensation value; and

[0086] Control the operation of at least one vehicle component according to the estimated normal force.

[0087] Technical solution 13. The wheel force control system according to technical solution 12, wherein the vehicle control module is configured to:

[0088] Determine a roll rate compensation value based on lateral acceleration at least according to the vehicle lateral acceleration parameter;

[0089] Determine a roll rate compensation value based on roll angle at least according to the vehicle longitudinal acceleration parameter;

[0090] Calculate a combined roll rate compensation value based on the lateral acceleration-based roll rate compensation value and the roll angle-based roll rate compensation value; and

[0091] Determine the estimated normal force on at least one wheel of the vehicle based at least in part on the combined roll rate compensation value.

[0092] Aspect 14. The wheel force control system according to Aspect 13, wherein the vehicle control module is configured to:

[0093] Calculate a suspension spring displacement value of at least one spring of the vehicle suspension;

[0094] Calculate a suspension spring damping force value of the at least one spring of the vehicle suspension; and

[0095] Determine the estimated normal force on at least one wheel of the vehicle based at least in part on the suspension spring displacement value and the suspension spring damping force.

[0096] Aspect 15. The wheel force control system according to Aspect 12, wherein controlling the operation of at least one vehicle component includes at least one of the following:

[0097] Controlling the position of a movable aerodynamic surface of the vehicle based on the estimated normal force; or

[0098] Controlling the amount of torque supplied to at least one wheel of the vehicle based on the estimated normal force.

[0099] Aspect 16. The wheel force control system according to Aspect 12, wherein the vehicle control module is configured to determine a reliability score of the estimated normal force via a trained machine learning model.

[0100] Aspect 17. The wheel force control system according to Aspect 16, wherein:

[0101] The trained machine learning model is trained based on a plurality of fault modes, each fault mode being associated with the estimated normal force; and

[0102] Each of the plurality of fault modes is associated with one or more corresponding vehicle parameters indicating the fault mode.

[0103] Aspect 18. A wheel force control system, comprising:

[0104] A plurality of wheel height sensors, each wheel height sensor being configured to measure the wheel height position of a corresponding wheel of the vehicle;

[0105] A vehicle inertial measurement unit (IMU), configured to measure the lateral acceleration of the vehicle and the longitudinal acceleration of the vehicle; and

[0106] A vehicle control module in communication with the plurality of wheel height sensors and the vehicle IMU, the vehicle control module being configured to:

[0107] Obtain wheel height parameters from the plurality of wheel height sensors;

[0108] Obtain vehicle lateral acceleration and vehicle longitudinal acceleration parameters from the vehicle IMU;

[0109] Determine an IMU-based estimated normal force on at least one wheel of the vehicle, at least in part based on the calculated center of gravity of the vehicle;

[0110] Determine a spring-based estimated normal force on the at least one wheel of the vehicle, at least in part based on a combined anti-dive compensation value and the calculated combined anti-dive compensation value;

[0111] Determine a reliability score for the IMU-based estimated normal force and the spring-based estimated normal force via a trained machine learning model;

[0112] Determine a combined estimated normal force on the at least one wheel of the vehicle based on a weighted combination of the IMU-based estimated normal force and the spring-based estimated normal force, wherein the weighted combination is assigned based on the reliability scores of the IMU-based estimated normal force and the spring-based estimated normal force; and

[0113] Control the operation of at least one vehicle component based on the combined estimated normal force.

[0114] Technical solution 19. The wheel force control system according to technical solution 18, wherein:

[0115] The trained machine learning model is trained based on a plurality of fault modes, each fault mode being associated with at least one of the IMU-based estimated normal force and the spring-based estimated normal force; and

[0116] Each of the plurality of fault modes is associated with one or more corresponding vehicle parameters indicating the fault mode.

[0117] Technical solution 20. The wheel force control system according to technical solution 18, wherein controlling the operation of at least one vehicle component includes at least one of the following:

[0118] Control the position of the movable aerodynamic surface of the vehicle based on the combined estimated normal force; or

[0119] Based on the combined estimation, the amount of torque supplied to at least one wheel of the vehicle is controlled in a normal force manner.

[0120] Other application areas of the present disclosure will become apparent from the detailed description, the claims, and the drawings. The detailed description and the specific examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0121] The present disclosure will be more fully understood from the detailed description and the drawings, wherein:

[0122] Figure 1 is a diagram of an example vehicle including a vehicle control module configured to estimate a wheel normal force value.

[0123] Figure 2 is an orthographic view illustrating example directional forces experienced by the vehicle.

[0124] Figure 3 is a block diagram of an example IMU-based and spring-based compensation module for estimating a wheel normal force value.

[0125] Figure 4 is a flowchart depicting an example process for generating an IMU-based normal force estimation result.

[0126] Figure 5 is a flowchart depicting an example process for estimating the pitch rotation arm used in Figure 4 the process.

[0127] Figure 6 is a block diagram of an example spring-based compensation module for estimating a wheel normal force value.

[0128] Figure 7 is a flowchart depicting an example process for generating a spring-based normal force estimation result.

[0129] Figure 8 is a flowchart depicting an example process for combining IMU-based and spring-based normal force estimation results while accounting for fault modes.

[0130] Figure 9A and 9B is a graphical representation of an example recurrent neural network for predicting the reliability of a wheel normal force estimation value.

[0131] Figure 10 is a graphical representation of the layers of an example long short-term memory (LSTM) machine learning model.

[0132] Figure 11 is a flowchart depicting an example process for training a machine learning model.

[0133] In the accompanying drawings, reference numerals may be reused to identify similar and / or identical elements. Detailed Description

[0134] Some example embodiments described herein implement a vehicle control system that includes a reliable and robust algorithm for wheel normal force estimation. The IMU-based and spring-based normal force estimation methods can be used alone to address terms that are typically not modeled in the IMU-based and spring-based methods. The longitudinal and lateral vehicle accelerations measured by the IMU can be fused with information from the spring displacement sensor to provide a more accurate and robust response for calculating the anti-effects (anti-dive, anti-lift, etc.) used in the spring-based method.

[0135] In some examples, a data fusion strategy can be used to combine the IMU-based and spring-based normal force estimation methods based on a degradation mode analysis of them. The effects of changes in longitudinal load transfer, changes in the vehicle center of gravity, and the vehicle pitch center position during excessive longitudinal acceleration can be considered in various example vehicle control systems.

[0136] Combining vehicle lateral and longitudinal acceleration information with wheel-to-body sensor information can provide a more accurate and robust estimate of the anti-roll and anti-dive / anti-lift effects in the spring-based normal force estimation algorithm. Compensating for the unmodeled suspension effects due to roll / pitch dynamics in the IMU-based normal force estimation method can also improve accuracy. In some examples, a machine learning model can be used to fuse (e.g., combine) the spring-based and IMU-based estimation methods by finding the degradation modes (e.g., failure regions in the vehicle parameter space) of each technique to increase the accuracy and robustness of the estimated normal force.

[0137] Improved estimated normal force can enhance vehicle motion control reliability by improving stability and providing an enhanced customer experience in terms of improved performance and safety. For example, the vehicle control module can be configured to control one or more components of the vehicle based on the normal force estimation results, such as adjusting the position of the vehicle's aerodynamic components (e.g., the angle of the vehicle's rear wing), adjusting the torque applied to one or more wheels, etc.

[0138] In some examples, the IMU-based estimation result can include an inertia-based vertical tire force model that uses static vehicle parameters from an inertial measurement unit to estimate the wheel normal force. The spring-based estimation result can include a suspension-based vertical tire model that uses the force and displacement curves from VHF data and the relative displacement between the wheel and the body to perform normal force estimation.

[0139] Now refer toFigure 1 , vehicle 10 includes front wheels 12 and rear wheels 13. In Figure 1 , drive unit 14 selectively outputs torque to front wheels 12 and / or rear wheels 13 via drive lines 16, 18 respectively. Vehicle 10 can include different types of drive units. For example, the vehicle can be an electric vehicle, such as a battery electric vehicle (BEV), a hybrid vehicle or a fuel cell vehicle, a vehicle including an internal combustion engine (ICE), or other types of vehicles.

[0140] Some examples of drive unit 14 can include any suitable electric motor, power inverter, and motor controller, the motor controller being configured to control power switches within the power inverter to adjust motor speed and torque during propulsion and / or regeneration. The battery system supplies power to or receives power from the electric motor of drive unit 14 via the power inverter during propulsion or regeneration.

[0141] Although in Figure 1 vehicle 10 includes one drive unit 14, vehicle 10 can have other configurations. For example, two separate drive units can drive front wheels 12 and rear wheels 13, one or more individual drive units can drive individual wheels, etc. As can be understood, other vehicle configurations and / or drive units can be used.

[0142] Vehicle control module 20 can be configured to control the operation of one or more vehicle components (such as drive unit 14) (e.g., by commanding the torque setting of the electric motor of drive unit 14). Vehicle control module 20 can receive inputs for controlling vehicle components, such as signals received from a steering wheel, an accelerator pedal, a brake pedal, etc. For safety purposes, vehicle control module 20 can monitor vehicle telematics, such as vehicle speed, vehicle position, vehicle braking, and acceleration, etc.

[0143] Vehicle control module 20 can receive signals from any suitable component for monitoring one or more aspects of the vehicle, the component including one or more vehicle sensors (such as cameras, microphones, pressure sensors, steering wheel position sensors, brake sensors, position sensors such as global positioning system (GPS) antennas, wheel height and / or position sensors, accelerometers, etc.). Some sensors can be configured to monitor the current movement of the vehicle, the acceleration of the vehicle, the braking of the vehicle, the current steering direction of the vehicle, etc., the current height and / or position of one or more wheels, etc.

[0144] As Figure 1 shown, vehicle 10 includes an inertial measurement unit (IMU) 22. IMU 22 is configured to measure the movement of the vehicle in one or more directions, such as the lateral acceleration of the vehicle, the longitudinal acceleration of the vehicle, etc.

[0145] Figure 2 Illustrated are example directional forces and motions that vehicle 10 may experience. Some of the directional forces and motions may be measured by IMU 22. In some example embodiments, the lateral direction of vehicle 10 from side to side may be considered the “x” direction, the longitudinal direction of vehicle 10 from front to back may be considered the “y” direction, and the direction of the vehicle perpendicular to the road surface from top to bottom may be considered the “z” direction.

[0146] Referring again to Figure 1 , vehicle control module 20 communicates with IMU 22 (and may optionally include IMU 22 as part of vehicle control module 20). Vehicle control module 20 may be configured to obtain vehicle parameters sensed by IMU 22, such as the lateral acceleration and longitudinal acceleration of vehicle 10.

[0147] Vehicle 10 also includes other vehicle sensors 24, which may include any suitable sensors for detecting vehicle parameters. For example, vehicle sensors 24 may include: multiple wheel height sensors, each wheel height sensor being configured to measure the height and / or position of the front wheels 12 or rear wheels 13 of the vehicle; one or more accelerometers; one or more sensors configured to measure properties of the suspension of vehicle 10 (such as the displacement or damping force of the springs of the suspension), etc.

[0148] Vehicle control module 20 may communicate with another device via a wireless communication interface, which may include one or more wireless antennas for transmitting and / or receiving wireless communication signals. For example, the wireless communication interface may communicate via any suitable wireless communication protocol, which includes but is not limited to vehicle-to-everything (V2X) communication, Wi-Fi communication, wireless area network (WAN) communication, cellular communication, personal area network (PAN) communication, short-range wireless communication (e.g., Bluetooth), etc. The wireless communication interface may communicate with a remote computing device via one or more wireless and / or wired networks. Regarding vehicle-to-vehicle (V2X) communication, vehicle 10 may include one or more V2X transceivers (e.g., V2X signal transmission and / or reception antennas).

[0149] Figure 3 is an illustration of an example of an IMU- and spring-based compensation module for estimating wheel normal force values. As Figure 3 shown, vehicle control module 120 includes an inertial measurement unit (IMU) compensation module 126, a spring-based compensation module 128, and a fault mode module 130. Figure 3 Each module shown in

[0150] The inertial measurement unit compensation module 126 is configured to receive IMU vehicle parameters 132, such as the lateral acceleration of the vehicle, the longitudinal acceleration of the vehicle, and the like. The inertial measurement unit compensation module 126 is configured to calculate the rigid body lateral load transfer 136 and the rigid body longitudinal load transfer 138.

[0151] The inertial measurement unit compensation module 126 is configured to determine the suspension compensation lateral load transfer 140 and the suspension compensation longitudinal load transfer 142. Any suitable equation can be used to determine or calculate the values of the corresponding modules. In other example embodiments, the inertial measurement unit compensation module 126 may include more or fewer calculations, more or fewer modules, and the like.

[0152] Some IMU-based estimation models may treat the vehicle as a rigid body while ignoring the effects of the vehicle suspension system. However, calibration can be used to account for the effects of the vehicle suspension system during roll motion. The calibration can be linearly dependent on the lateral acceleration, where they only become effective when the lateral acceleration of the vehicle is high (e.g., above a lateral acceleration threshold). The following are example equations for determining the normal forces (Fz) of the left front (LF), right front (RF), left rear (LR), and right rear (RR) wheels:

[0153] K AxteCorr,i =(K ADL,i a x +1), i = F, R

[0154] F z，ij = K AxteCorr,i F z，ij , j = L, R

[0155]

[0156]

[0157]

[0158]

[0159] The spring-based compensation module 128 is configured to receive spring-based vehicle parameters 134, such as wheel height values obtained from wheel height sensors. The spring-based compensation module 128 is configured to determine the ride rate 144, the rollrate compensation 146 based on the roll angle, the anti-dive compensation 148, and the rollrate compensation 150 based on the lateral acceleration. Any suitable equation can be used to determine or calculate the values of the corresponding modules. Other example embodiments of the spring-based compensation module 128 may include more or fewer modules.

[0160] The fault mode module 130 includes a fusion module 156 and a fault mode detection module 158. The fusion module is configured to receive an IMU estimate 152 from the inertial measurement unit compensation module 126. The fusion module 156 is further configured to receive a spring-based normal force estimate 154 from the spring-based compensation module 128.

[0161] The fusion module 156 is configured to combine the IMU estimate 152 with the spring-based normal force estimate 154. This combination can be weighted by the fault mode detection module 158, which can include predicting the reliability of each of the IMU estimate 152 and the spring-based normal force estimate 154 based on a trained machine learning model for predicting the reliability of the normal force estimate. The fault mode module 130 is configured to output an estimated normal force 160 experienced by one or more wheels of the vehicle. For example, the fault mode module 130 can output multiple normal force estimates, each corresponding to a different wheel of the vehicle.

[0162] Figure 4 is a flowchart depicting an example process for generating an IMU-based normal force estimation result. The process can be performed by, for example Figure 1 the vehicle control module 20 or Figure 3 the vehicle control module 120. At 204, the process begins with obtaining inertial measurement unit (IMU) vehicle parameters, such as the lateral and longitudinal accelerations of the vehicle 10 measured by Figure 1 the IMU 22.

[0163] At 208, the vehicle control module is configured to estimate the pitch arm rotation of the vehicle. Further details of estimating the pitch arm rotation of the vehicle are described below with reference to Figure 5 . At 212, the vehicle control module is configured to obtain the vehicle longitudinal acceleration parameter from the IMU.

[0164] At 216, the vehicle control module is configured to determine whether the longitudinal acceleration is greater than an excessive acceleration value threshold. For example, if the longitudinal acceleration is greater than the specified threshold, the control proceeds to 220 to reset the pitch angle value of the vehicle. If the longitudinal acceleration is less than the excessive value threshold, the control proceeds to 224 to integrate the pitch rate of the vehicle.

[0165] The pitch center function can be generated offline, such as a function for determining the pitch center of the vehicle based on wheel height sensor values. Then the control obtains the current wheel height sensor values at 232 and online calculates the current vehicle pitch center position at 236 using the previously offline created pitch center function and the current sensor values.

[0166] When the vehicle is moving, especially in the case of excessive movement, the orientation of the suspension link changes, and thus the pitch center position also changes. The pitch center position has an algebraic relationship with the geometry of the suspension. In some examples, the algebraic position can be obtained offline from VHF test results. An example non-linear function for determining the pitch center based on wheel height sensor values is:

[0167] 〖(x_(P.C.),z_(P.C.))""〗 - =f(x fl , x fr , x rl , x rr )

[0168] This function can be used to calculate the position of the pitch center online in real time.

[0169] At 240, the vehicle control module is configured to calculate the vehicle's center of gravity based on the calculated pitch center. To calculate the position of the vehicle's center of gravity relative to the pitch center, the pitch angle θ can be used. This can be achieved by integrating the pitch rate under the condition of the longitudinal acceleration-based condition. The value of the pitch angle can be reset and updated only when excessive acceleration is detected to ensure the accuracy of the pitch angle estimation.

[0170] Figure 5 is a flowchart depicting an example process of the pitch rotation arm used for estimation in the Figure 4 process. At 304, the process starts with obtaining the vehicle speed, wheel torque, and road parameters. At 308, the vehicle control module is configured to calculate the vehicle's longitudinal acceleration.

[0171] For example, the vehicle's longitudinal acceleration can be determined based on the following equation (which may include a simplified assumption that the rolling resistance is not affected by the road grade):

[0172]

[0173]

[0174] At 312, the vehicle control module is configured to obtain the vehicle acceleration value from the inertial measurement unit. Then at 316, the control calculates the rotational pitch acceleration of the vehicle based on the longitudinal acceleration and the IMU acceleration value.

[0175] At 320, the control module is configured to estimate the vehicle's pitch rotation arm using the least squares method based on the rotational pitch acceleration. Example equations for calculating the rotational pitch acceleration and the estimated pitch rotation arm are provided below:

[0176]

[0177]

[0178] are the measurement results read by the IMU, which include the gravity term. The pitch angular velocity and acceleration can also be measured and provided by the PITR. Under normal driving conditions, can be calculated using the above vehicle longitudinal acceleration calculation. Some calculations can assume that the value of the arm h does not change dynamically, as it mainly depends on the suspension geometry. The only unknown in the above pitch rotation arm equation is h, which can be estimated using a least squares estimator.

[0179] Figure 6 is a block diagram of an example spring-based compensation module for estimating the wheel normal force value. As Figure 6 shown, the vehicle spring-based compensation module 428 is configured to receive vehicle parameters 430, such as the lateral acceleration of the vehicle, the longitudinal acceleration of the vehicle, wheel height sensor parameters, etc.

[0180] The vehicle spring-based compensation module 428 is configured to determine spring displacement force calculation 432, anti-dive / anti-lift compensation 434, roll rate compensation 440, and damping force calculation 446. The anti-dive / anti-lift compensation 434 includes anti-dive compensation 436 based on the lateral acceleration (Ax) and anti-dive compensation 438 based on the pitch angle. The roll rate compensation 440 includes roll rate compensation 442 based on the longitudinal acceleration (Ay) and roll rate compensation 444 based on the roll angle.

[0181] In some examples, the estimated roll angle may depend on the ground clearance sensor, where small deviations or inaccuracies in the corner displacement signal may reduce the reliability of the roll rate compensation term. The following provides an example equation for the roll rate compensation 444 based on the roll angle:

[0182]

[0183]

[0184]

[0185]

[0186] Roll rate compensation 442 based on longitudinal acceleration (Ay) can reduce the sensitivity / dependence on the spring group or spring displacement deviation. A small deviation at a corner may cause a large change in the roll angle estimation result, and thus cause a large change in the roll rate compensation term. In some examples, the reliability of the Ay signal can be higher than that of the ride height sensor, and the result of the roll rate compensation based on Ay can be more accurate than the result of the roll rate compensation based on the roll angle. The following provides an example equation for the roll rate compensation based on Ay:

[0187]

[0188]

[0189]

[0190]

[0191] Spring displacement force calculation 432, anti-dive / anti-lift compensation 434, roll rate compensation 440, and damping force calculation 446 can be combined by a spring-based normal force estimation module 448 to generate spring-based normal force estimation results 450 on one or more wheels.

[0192] In some examples, the spring displacement force calculation may include using the wheel-to-body relative distance for all four corners to generate a force from the vertical rate data. The vertical rate data can be used as a calibration input and found through a vertical suspension test independent of the longitudinal force. The following provides an example equation for the spring displacement force:

[0193]

[0194]

[0195]

[0196]

[0197] Anti-dive / anti-lift compensation may include quantifying the characteristics of some suspensions to absorb the longitudinal force in the vertical direction. An anti-dive / anti-lift factor can be used to quantify the characteristic, and the anti-dive / anti-lift factor is found through a vertical suspension test using the longitudinal force input. The following provides an example equation for the anti-dive / anti-lift compensation:

[0198]

[0199]

[0200]

[0201]

[0202] Figure 7 is a flowchart depicting an example process for generating spring-based normal force estimation results. This process can be performed by, for example, Figure 1 vehicle control module 20 or Figure 3 vehicle control module 120. At 504, the process begins with obtaining vehicle lateral and longitudinal acceleration parameters.

[0203] At 508, the vehicle control module is configured to obtain wheel height values from vehicle sensors (such as Figure 1 vehicle sensor 24). At 512, the vehicle control module is configured to calculate a suspension displacement force value based on the obtained parameters.

[0204] At 516, the control module is configured to determine an anti-dive compensation based on the longitudinal acceleration (Ay). At 520, the vehicle control module is configured to determine an anti-dive compensation based on the pitch angle. Then the control proceeds to 524 to calculate an anti-dive / anti-lift compensation value using the value based on the longitudinal acceleration and the value based on the pitch angle.

[0205] At 528, the vehicle control module is configured to determine a roll rate compensation value based on the lateral acceleration (Ax). Then the control proceeds to 532 to determine a roll rate compensation value based on the roll angle. At 536, the vehicle control module is configured to calculate a roll rate compensation using the value based on the lateral acceleration and the value based on the roll rate.

[0206] At 540, the control is configured to calculate a suspension spring damping force, which can be the damping force currently experienced at one of the suspension springs associated with one of the wheels. At 544, the vehicle control module is configured to estimate the normal force of the wheel based on the spring displacement, the anti-dive / anti-lift compensation value, the roll rate compensation value, and the damping force value.

[0207] Figure 8 is a flowchart depicting an example process for combining IMU-based and spring-based normal force estimation results while accounting for fault modes. This process can be performed by, for example, Figure 1 vehicle control module 20 or Figure 3 vehicle control module 120. At 604, the process begins with sourcing an estimation degradation mode.

[0208] Each normal force estimation degradation mode can correspond to a point in a visual parameter space where the normal force estimation result is unreliable due to the influence of certain parameters that make the normal force estimation method inaccurate.

[0209] At 608, the vehicle control module is configured to select a first degradation mode, which may correspond to a normal force estimation fault mode. At 612, the vehicle control module is configured to define vehicle parameters associated with the degradation mode. For example, the control may determine which vehicle parameters indicate positions in the vehicle parameter space where the selected degradation fault mode may render the normal force estimation results unreliable.

[0210] At 616, the vehicle control module determines whether any degradation modes remain. If so, the control proceeds to 622 to select the next degradation mode. If no degradation modes remain at 616, the control proceeds to 624 to label the degradation mode data based on the identified associated vehicle parameters.

[0211] At 628, a machine learning model is trained to predict the reliability of the spring-based normal force estimation result and the IMU-based normal force estimation result based on the degradation mode. Further details for training an example machine learning model are discussed further below with reference to FIGS. 9-11. At 632, the vehicle control module is configured to store the model for estimating the normal force of one or more wheels based on the obtained vehicle parameters.

[0212] In some examples, the fault mode is a specific operating range of the original system, where the system is highly sensitive to input / model / parameter uncertainties. The system may determine the fault mode region within the parameter space of the operating vehicle parameter range and calculate the distance to the fault mode for use in real-time reliability measurements using modeling.

[0213] For example, each normal force estimation method (e.g., IMU-based and spring-based) may have its own degradation mode and dependence on its input signal. In some examples, when the reliability of the ground clearance sensor is low, the reliability of the spring-based method decreases, and the performance of the IMU-based method is highly dependent on the reliability of the vehicle mass estimation and the lateral and longitudinal accelerations. The reliability assessment analysis of the input signal and subsystem degradation mode detection provides information for enhancing the reliability of the estimated normal force.

[0214] In various implementations, specific fault modes are identified for the IMU-based and spring-based normal force estimation values. Example fault modes may include, but are not limited to, alignment of the IMU-based and spring-based estimates, faulty sensor signals, ground clearance deviation, non-linear regions of the spring-based method, road roughness, road angle, hard braking, passive aerodynamic characteristics, and spring sag.

[0215] In some examples, a machine learning model is trained to determine the reliability of each operating point in a vehicle parameter space based on the identified fault modes. The model can perform fusion (e.g., combination) based on a weighted sum of IMU-based estimates and spring-based estimates, where the weight of each estimate is proportional to its reliability.

[0216] Figure 9A and 9B An example of a recurrent neural network for generating a model such as the above model using machine learning techniques is shown. Machine learning is a method for designing complex models and algorithms that help with prediction (e.g., patient and provider matching prediction). Models generated using machine learning (such as those described above) can produce reliable, repeatable decisions and results and reveal hidden insights by learning historical relationships and trends in the data.

[0217] The purpose of using a model based on a recurrent neural network and using machine learning as described above to train the model can be to directly predict the dependent variable without converting the relationships between the variables into a mathematical form. A neural network model includes a large number of parallel operating, hierarchically arranged virtual neurons. The first layer is the input layer and receives the raw input data. Each successive layer modifies the output from the previous layer and sends it to the next layer. The last layer is the output layer and produces the output of the system.

[0218] Figure 9A A fully connected neural network is shown, where each neuron in a given layer is connected to every neuron in the next layer. In the input layer, each input node is associated with a numerical value, which can be any real number. In each layer, each connection starting from an input node has a weight associated with it, which can also be any real number (see Figure 9B ). In the input layer, the number of neurons is equal to the number of features (columns) in the dataset. The output layer can have multiple successive outputs.

[0219] The layers between the input layer and the output layer are hidden layers. The number of hidden layers can be one or more (for most applications, one hidden layer may be sufficient). A neural network without hidden layers can represent a linearly separable function or decision. A neural network with one hidden layer can perform a continuous mapping from one finite space to another finite space. A neural network with two hidden layers can approximate any smooth mapping to any accuracy.

[0220] The number of neurons can be optimized. At the start of training, the network configuration is likely to have too many nodes. Some nodes that do not significantly affect network performance can be removed from the network during training. For example, nodes with weights close to zero after training can be removed (this process is called pruning). The number of neurons can lead to underfitting (inability to adequately capture the signals in the dataset) or overfitting (not enough information to train all neurons; the network performs well on the training dataset but poorly on the test dataset).

[0221] Various methods and criteria can be used to measure the performance of a neural network model. For example, the root mean square error (RMSE) measures the average distance between the observed values and the model's predicted results. The coefficient of determination (R2) measures the correlation (rather than accuracy) between the observed and predicted results. This method may not be reliable if the data variance is large. Other performance metrics include irreducible noise, model bias, and model variance. A high model bias of the model indicates that the model fails to capture the true relationship between the predictor variables and the outcome. Model variance can indicate whether the model is stable (a slight perturbation in the data will significantly change the model fit). A neural network can receive inputs, such as vectors, which can be used to generate a model that can be used to predict the reliability of normal force estimation, as described herein.

[0222] Figure 10 An example of a long short-term memory (LSTM) neural network 1002 for generating a model such as the above-mentioned model using machine learning techniques is illustrated, but other example embodiments can include other types of machine learning models, including transformer layers, other model topologies, etc. The general example LSTM neural network 1002 can be used to implement a machine learning model, and various implementations can use other types of machine learning networks (such as transformer layers, other model topologies or architectures, etc.). The LSTM neural network 1002 includes an input layer 1004, a hidden layer 1008, and an output layer 1012. The input layer 1004 includes inputs 1004a, 1004b... 1004n. The hidden layer 908 includes neurons 1008a, 1008b... 1008n. The output layer 1012 includes outputs 1012a, 1012b... 1012n.

[0223] Each neuron in the hidden layer 1008 receives an input from the input layer 1004 and outputs a value to the corresponding output in the output layer 1012. For example, neuron 1008a receives an input from input 1004a and outputs a value to output 1012a. Each neuron other than neuron 1008a also receives the output of the previous neuron as an input. For example, neuron 1008b receives inputs from input 1004b and output 1012a. In this way, the output of each neuron is fed forward to the next neuron in the hidden layer 1008. The last output 1012n in the output layer 1012 outputs a probability associated with inputs 1004a - 1004n. Although the input layer 1004, the hidden layer 1008, and the output layer 1012 are depicted as each including three elements, each layer can include any number of elements.

[0224] In various implementations, each layer of the LSTM neural network 1002 must include the same number of elements as every other layer of the LSTM neural network 1002. In some example embodiments, a convolutional neural network can be implemented. Similar to the LSTM neural network, a convolutional neural network includes an input layer, a hidden layer, and an output layer. However, in a convolutional neural network, the output layer includes one fewer output than the number of neurons in the hidden layer, and each neuron is connected to each output. Additionally, each input in the input layer is connected to each neuron in the hidden layer. In other words, input 1004a is connected to each of neurons 1008a, 1008b... 1008n.

[0225] In various implementations, each input node in the input layer can be associated with a numerical value, which can be any real number. In each layer, each connection originating from an input node has a weight associated with it, which can also be any real number. In the input layer, the number of neurons is equal to the number of features (columns) in the dataset. The output layer can have multiple consecutive outputs.

[0226] As described above, the layer(s) between the input layer and the output layer is / are the hidden layer(s). The number of hidden layers can be one or more (for many applications, one hidden layer may be sufficient). A neural network without a hidden layer can represent a linearly separable function or decision. A neural network with one hidden layer can perform a continuous mapping from one finite space to another finite space. A neural network with two hidden layers can approximate any smooth mapping to any degree of accuracy.

[0227] Figure 11 An example process for generating a machine learning model is illustrated. At 1107, control obtains data from a database 1102 (e.g., a data warehouse). This data can include any suitable data for developing a machine learning model.

[0228] At 1111, the control divides the data obtained from the database 1102 into training data 1115 and test data 1119. The training data 1115 is used to train the model at 1123, and the test data 1119 is used to test the model at 1127. Generally, depending on the desired model development parameters, the set of training data 1115 is selected to be larger than the set of test data 1119. For example, the training data 1115 can include approximately seventy percent, approximately eighty percent, approximately ninety percent, etc. of the data obtained from the database 1102. Then the remaining thirty percent, twenty percent, or ten percent is used as the test data 1119.

[0229] Dividing a portion of the obtained data into the test data 1119 allows the trained model to be tested against the actual output data to facilitate more accurate training and development of the model at 1123 and 1127. Any suitable machine learning model techniques can be used at 1123, including those described herein, such as random forests, generalized linear models, decision trees, and neural networks to train the model.

[0230] At 1131, the control evaluates the model test results. For example, the test data 1119 can be used at 1127 to test the trained model, and the results of the output data from the tested model can be compared with the actual output of the test data 1119 to determine the accuracy level. Any suitable machine learning model analysis (such as the example techniques further described below) can be used to evaluate the model results.

[0231] After evaluating the model test results at 1131, if the model test results are satisfactory, the model can be deployed at 1135. Deploying the model can include using the model to make predictions on a large-scale input data set with unknown outputs. If the evaluation of the model test results at 1131 is not satisfactory, the model can be further developed using different parameters, using different modeling techniques, using other model types, etc.

[0232] The foregoing description is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses. The broad teachings of the disclosure can be implemented in a variety of forms. Thus, while the disclosure includes specific examples, the true scope of the disclosure should not be so limited since other modifications will become apparent upon study of the drawings, the specification, and the appended claims. It should be understood that one or more steps within a method may be executed in different orders (or concurrently) without altering the principles of the disclosure. Further, while each embodiment above is described as having specific features, any one or more of those features described with respect to any embodiment of the disclosure can be implemented in and / or combined with the features of any other embodiment, even if the combination is not explicitly described. In other words, the described embodiments are not mutually exclusive, and arrangements of one or more of them with each other remain within the scope of the disclosure.

[0233] Spatial and functional relationships between elements (e.g., between modules, circuit elements, semiconductor layers, etc.) are described using a variety of terms, including “connected,” “engaged,” “coupled,” “adjacent,” “next to,” “on top of,” “above,” “below,” and “disposed.” Unless explicitly described as “direct,” when describing the relationship between a first element and a second element in the foregoing disclosure, the relationship can be a direct relationship in which no other intervening elements exist between the first and second elements, but can also be an indirect relationship in which one or more intervening elements (spatially or functionally) exist between the first and second elements. As used herein, the phrase “at least one of A, B, and C” should be construed to mean a logical (A or B or C), using non-exclusive logical “or,” and should not be construed to mean “at least one of A, at least one of B, and at least one of C.”

[0234] In the figures, the direction of an arrow as indicated generally shows the flow of information of interest (e.g., data or instructions) being illustrated. For example, when element A and element B exchange various information, but the information being transmitted from element A to element B is relevant to the illustration, the arrow can point from element A to element B. This one-way arrow does not mean that no other information is being transmitted from element B to element A. Further, for information being sent from element A to element B, element B can send a request for that information or receive an acknowledgement.

[0235] In this application, including the following definitions, the term "module" or the term "controller" may be replaced by the term "circuit". The term "module" may refer to, be part of, or include the following: application specific integrated circuit (ASIC); digital, analog, or mixed analog / digital discrete circuits; digital, analog, or mixed analog / digital integrated circuits; combinational logic circuits; field programmable gate array (FPGA); processor circuits (shared, dedicated, or group) that execute code; memory circuits (shared, dedicated, or group) that store code executed by the processor circuits; other suitable hardware components that provide the described functionality; or a combination of some or all of the above, such as in a system on a chip.

[0236] The module may include one or more interface circuits. In some examples, the interface circuit may include a wired or wireless interface connected to a local area network (LAN), the Internet, a wide area network (WAN), or a combination thereof. The functionality of any given module of the present disclosure may be distributed among multiple modules connected via the interface circuit. For example, multiple modules may allow load balancing. In a further example, a server (also referred to as remote or cloud) module may perform some functions on behalf of a client module.

[0237] As used above, the term "code" may include software, firmware, and / or microcode, and may refer to programs, routines, functions, classes, data structures, and / or objects. The term "shared processor circuit" encompasses a single processor circuit that executes some or all of the code from multiple modules. The term "group processor circuit" encompasses a processor circuit that, in combination with additional processor circuits, executes some or all of the code from one or more modules. References to multiple processor circuits encompass multiple processor circuits on separate die, multiple processor circuits on a single die, multiple cores of a single processor circuit, multiple threads of a single processor circuit, or a combination of the above. The term "shared memory circuit" encompasses a single memory circuit that stores some or all of the code from multiple modules. The term "group memory circuit" encompasses a memory circuit that, in combination with additional memory, stores some or all of the code from one or more modules.

[0238] The term "memory circuit" is a subset of the term "computer-readable medium". As used herein, the term "computer-readable medium" does not cover transitory electrical or electromagnetic signals propagated through a medium such as on a carrier wave; thus, the term "computer-readable medium" can be considered tangible and non-transitory. Non-limiting examples of non-transitory, tangible computer-readable media are non-volatile memory circuits such as flash memory circuits, erasable programmable read-only memory circuits, or mask read-only memory circuits, volatile memory circuits such as static random access memory circuits or dynamic random access memory circuits, magnetic storage media such as analog or digital magnetic tape or hard disk drives, and optical storage media such as CDs, DVDs, or Blu-ray discs.

[0239] The devices and methods described in this application can be implemented in part or in whole by a special-purpose computer created by configuring a general-purpose computer to execute one or more specific functions embodied in a computer program. The above functional blocks, flowchart components, and other elements serve as software specifications that can be translated into a computer program by the routine work of a skilled technician or programmer.

[0240] A computer program includes processor-executable instructions stored on at least one non-transitory, tangible computer-readable medium. The computer program may also include or rely on stored data. The computer program can cover a basic input / output system (BIOS) that interacts with the hardware of the special-purpose computer, device drivers that interact with specific devices of the special-purpose computer, one or more operating systems, user applications, background services, background applications, and so on.

[0241] A computer program can include: (i) descriptive text to be parsed, such as HTML (HyperText Markup Language), XML (eXtensible Markup Language), or JSON (JavaScript Object Notation), (ii) assembly code, (iii) object code generated from source code by a compiler, (iv) source code for execution by an interpreter, (v) source code for just-in-time compilation and execution, and so on. By way of example only, the source code can be written using the syntax of languages including: C, C++, C#, Objective C, Swift, Haskell, Go, SQL, R, Lisp, Fortran, Perl, Pascal, Curl, OCaml, HTML5 (HyperText Markup Language Fifth Edition), Ada, ASP (Active Server Pages), PHP (PHP: Hypertext Preprocessor), Scala, Eiffel, Smalltalk, Erlang, Ruby, Visual Lua, MATLAB, SIMULINK and

Claims

1. A wheel force control system, comprising: a plurality of wheel height sensors, each wheel height sensor configured to measure a wheel height position of a corresponding wheel of the vehicle; a vehicle inertial measurement unit (IMU) configured to measure a lateral acceleration of the vehicle and a longitudinal acceleration of the vehicle; and a vehicle control module in communication with the plurality of wheel height sensors and the vehicle IMU, the vehicle control module being configured to: obtaining wheel height parameters from the plurality of wheel height sensors; Obtaining a vehicle lateral acceleration parameter and a vehicle longitudinal acceleration parameter from the vehicle IMU; estimating a pitch arm rotation value of the vehicle; determining a pitch center of the vehicle based on the pitch arm rotation value, the wheel height parameter, and the vehicle lateral acceleration parameter and the vehicle longitudinal acceleration parameter; Calculating the center of gravity of the vehicle based on the determined pitch center; determining an estimated normal force on at least one wheel of the vehicle based at least in part on the calculated center of gravity of the vehicle; and Operation of at least one vehicle component is controlled based on the estimated normal force.

2. The wheel force control system of claim 1 , wherein the estimated normal force is an estimated normal force based on an IMU, and the vehicle control module is configured to: determining an anti-dive compensation value based on longitudinal acceleration at least according to the vehicle longitudinal acceleration parameter; determining an anti-dive compensation value based on a pitch angle at least according to the vehicle longitudinal acceleration parameter; Calculating a combined anti-dive compensation value according to the anti-dive compensation value based on the longitudinal acceleration and the anti-dive compensation value based on the pitch angle; and An estimated spring-based normal force on the at least one wheel of the vehicle is determined based at least in part on the combined anti-dive compensation value.

3. The wheel force control system of claim 2, wherein the vehicle control module is configured to: determining a roll rate compensation value based on lateral acceleration at least according to the vehicle lateral acceleration parameter; determining a roll rate compensation value based on a roll angle at least according to the vehicle longitudinal acceleration parameter; calculating a combined roll rate compensation value based on the lateral acceleration-based roll rate compensation value and the roll angle-based roll rate compensation value; and An estimated spring-based normal force on the at least one wheel of the vehicle is determined based at least in part on the combined roll rate compensation value.

4. The wheel force control system of claim 3, wherein the vehicle control module is configured to: calculating a suspension spring displacement value of at least one spring of a vehicle suspension; calculating a suspension spring damping force value for the at least one spring of a vehicle suspension; and An estimated spring-based normal force on the at least one wheel of the vehicle is determined based at least in part on the suspension spring displacement value and the suspension spring damping force.

5. The wheel force control system of claim 4, wherein the vehicle control module is configured to: determining, via the trained machine learning model, reliability scores for the IMU-based estimated normal force and the spring-based estimated normal force; and A combined estimated normal force on at least one wheel of the vehicle is determined based on a weighted combination of the IMU-based estimated normal force and the spring-based estimated normal force, wherein the weighted combination is assigned based on reliability scores of the IMU-based estimated normal force and the spring-based estimated normal force.

6. The wheel force control system according to claim 5, wherein: training the trained machine learning model based on a plurality of failure modes, each failure mode associated with at least one of the IMU-based estimated normal force and the spring-based estimated normal force; and Each of the plurality of failure modes is associated with one or more corresponding vehicle parameters indicative of the failure mode.

7. The wheel force control system of claim 1 , wherein the vehicle control module is configured to: comparing the vehicle longitudinal acceleration parameter to a specified excessive acceleration threshold; responsive to the vehicle longitudinal acceleration parameter exceeding the specified excess acceleration threshold, resetting the value of the vehicle pitch angle; and In response to the vehicle longitudinal acceleration parameter being less than the specified excess acceleration threshold, integration of the vehicle pitch rate is performed.

8. The wheel force control system of claim 1 , wherein the vehicle control module is configured to: obtaining a pitch center position function, wherein the pitch center position function is determined off-line based on at least one geometric model of a vehicle suspension; and The pitch center of the vehicle is determined online based at least in part on the pitch center position function.

9. The wheel force control system of claim 1 , wherein controlling the operation of at least one vehicle component comprises at least one of: controlling a position of a movable aerodynamic surface of the vehicle based on the estimated normal force; or An amount of torque supplied to at least one wheel of the vehicle is controlled based on the estimated normal force.

10. The wheel force control system of claim 1, wherein the vehicle control module is configured to estimate the pitch arm rotation value of the vehicle by: Calculating a rotational pitch acceleration value of the vehicle based on the vehicle longitudinal acceleration parameter; and The pitch arm rotation value of the vehicle is estimated based on the calculated rotational pitch acceleration value using a least square method.

Images