Gm Global Technolgoy Operations, Inc.

The University of Waterloo

Beijing Institute of Technology

Ehsan Hashemi

Amir Khajepour

Bakhtiar Brian Litkouhi

SeyedAlireza Kasaiezadeh Mahabadi

Yechen Qin

Shih-Ken Chen

Hualin Tan

James Heath Holbrook

Amin Habibnejad Korayem

Nikolai K Moshchuk

Qingrong Zhao

Joseph K Moore

Seyedalireza Kasaiezadeh Mahabadi

Jin-Jae Chen

Mansoor Alghooneh

Christopher J Mettrick

Xueying Kang

Yiwei Huang

Gregory P Kakert

Zhenfeng Wang

A universal machine learning based system for estimating a vehicle state of a vehicle includes one or more controllers executing instructions to receive a plurality of dynamic variables and corresponding historical data. The controllers execute a sensitivity analysis algorithm to determine a sensitivity level for each dynamic variable and corresponding historical data and select two or more pertinent dynamic variables based on the sensitivity level of each dynamic variable and the corresponding historical data. The controllers standardize the two or more pertinent dynamic variables into a plurality of generic dynamic variables, wherein the plurality of generic dynamic variables are in a standardized format that is applicable to any configuration of vehicle, and estimate the vehicle state based on the plurality of generic dynamic variables by one or more machine learning algorithms.

Universal machine learning based system for estimating a vehicle state

A method for determining a tire tread wear estimation of a tire includes receiving, by a controller, a direct tire tread wear measurement, when available, performing an indirect tire tread wear estimation, performing a data fusion of the indirect tire tread wear estimation with the direct tire tread wear measurement when available, estimating a percentage tire life remaining and a mileage to end of tire life, and estimating a refined tire tread wear calibration coefficient for performing future indirect tire tread wear estimations.

Systems and methods for estimating tire wear

The present disclosure relates to a method and system for integrated path planning and path tracking control of an autonomous vehicle. The method includes: obtaining five input control variables and eleven system state variables of an autonomous vehicle at current time; constructing a vehicle path planning-tracking integrated state model according to the obtained variables at the current time; enveloping external contours of two autonomous vehicles using elliptical envelope curves to determine elliptical vehicle envelope curves of the two autonomous vehicles, respectively; determining time to collision (TTC) between the vehicles according to elliptical vehicle envelope curves and vehicle driving states; establishing an objective function of a model prediction controller (MPC) according to the model; and solving the objective function based on the TTC, and determining input control variables to the MPC at the next time. Autonomous vehicle collision avoidance can be achieved according to the present disclosure.

Method and system for integrated path planning and path tracking control of autonomous vehicle

A method for estimation of a vehicle tire force includes: receiving, by a controller of a vehicle, a measured vehicle acceleration of the vehicle; receiving, by the controller, a measured wheel speed and a measured yaw rate of the vehicle; forming, by the controller, inertia matrices based on an inertia of rotating components of the vehicle; calculating torques at corners of the vehicle using the inertia matrices; estimating tire forces of the vehicle based on the measured vehicle acceleration, the measured wheel speed, and the inertia matrices; and controlling, by the controller, the vehicle, based on the plurality of estimated longitudinal and lateral tire forces.

Architecture and reconfigurable tire force estimation for various powertrain configurations

A combined slip based driver command interpreter for a vehicle is provided which may be communicatively coupled to a steering wheel angle sensor, an acceleration pedal position sensor and a brake pedal position sensor, the combined slip based driver command interpreter including, but not limited to a memory configured to store a non-linear combined lateral slip model and a non-linear combined longitudinal slip model, and a processor, the processor configured to determine a driver's intended vehicle lateral velocity and a driver's intended vehicle yaw rate based upon the angle of the steering wheel, the position of the acceleration pedal, the position of the brake pedal, a longitudinal velocity of the vehicle, the non-linear combined lateral slip model and the non-linear combined longitudinal slip model.

Combined slip-based driver command interpreter

Methods and systems are provided for an improved system and method for validating vehicle lateral velocity estimation. The provided system and method employ an efficient validation algorithm to detect lateral velocity estimation faults. The method and system are robust to road uncertainties and do not require redundant estimations or measurements. The provided system and method offer a technological solution for real time validation of lateral velocity estimation using already existing vehicle sensors, and are independent of (i) road condition information, (ii) wheel torque information, (iii) tire model information, and (iv) tire wear information.

Systems and methods for fault detection in lateral velocity estimation

A system and method for computationally estimating a directional velocity of a vehicle in real time under different configurations and road conditions for use in vehicle antilock braking, adaptive cruise control, and traction and stability control by correcting measured accelerations with respect to the estimated road angles. A time window is used to provide reliable mapped acceleration for the transient regions and maneuvers on gravel surfaces with high fluctuations in the acceleration measurement. Longitudinal and lateral accelerations are mapped from the vehicle's CG into the tire coordinates using the vehicle's geometry, lateral velocity, yaw rate, and the steering wheel angle to generate system matrices of the combined kinematic-force estimation structure.

Corner-based longitudinal speed estimation

Growing community of inventors

Waterloo, Canada

Ehsan Hashemi