Gm Global Technolgoy Operations, Inc.

Mehdi Abroshan

Mohammadali Shahriari

Reza Zarringhalam

Ashraf Abualfellat

Khizar Ahmad Qureshi

Puneet Bagga

Hassan Askari

Jimmy Lu

Apral S Hara

Mohammed Raju Hossain

Jackson Barry McGrory

Zhi Li

Kin Man Michael Wong

Ami Woo

Michael B Peppard

Sadaf Mohammadi

Christopher Ratliff

An adaptive method for controlling the steering of an autonomous vehicle includes receiving a steering input. The steering input is indicative of a desired road wheel angle. The method also includes determining a commanded torque to achieve the desired road wheel angle. The method also includes measuring the road wheel angle of the vehicle (i.e., the measured road wheel angle). The method also includes executing a feedback control to determine a torque overlay. The feedback control includes determining, in real time, a current steering error vector of the vehicle. The feedback control includes determining the difference between the current steering error vector and a predetermined-steering error dynamics vector. The feedback control also includes determining a feedback gain correction vector. The feedback gain correction vector is a function of the difference between the current steering error vector and the predetermined-steering error dynamics vector.

Model-reference adaptive steering feedback control to reduce unforeseen oscillations in automated driving

A computer-implemented method that, when executed by data processing hardware of a vehicle, causes the data processing hardware to perform operations is provided. The operations include gathering sensor data, calculating one or more groove detection confidence values with the sensor data using one or more groove detection modules, evaluating the one or more groove detection confidence values using a road groove detection fusion module, determining whether a road groove is detected, communicating road groove data to an advanced driver-assistance system, and adapting trajectory and steering controls of the vehicle.

System and method for road groove detection and control in automated driving

Vehicles and related systems and methods are provided for predicting a future maneuver expected to be executed by a driver. One method involves determining a combined probability for a potential maneuver based on constituent probabilities corresponding to different vehicle state variables, and environmental conditions using one or more tuning parameters specific to the respective combination of maneuver and vehicle state variable, determining an adjusted probability for the potential maneuver based at least in part on the combined probability and one or more contextual state variables corresponding to a current operating context for the vehicle, adapted to driver behavior and driving style, identifying the potential maneuver as an expected maneuver to be executed by a driver of the vehicle based on the adjusted probability, and automatically initiating one or more actions in a manner that is influenced by the expected maneuver.

Vehicle systems and methods for probabilistic maneuver prediction

Methods and systems are provided that include one or more sensors configured to obtain sensor data pertaining to both a driver of a vehicle and an environment surrounding the vehicle; and a processor that is coupled to the one or more sensors and that is configured to at least facilitate determining, using the sensor data, when the driver is incapacitated; determining, using the sensor data, when a threat is detected for the vehicle; and taking action to avoid the threat when the driver is incapacitated and the threat is detected, via instructions provided by the processor.

Optimal engagement of automated features to assist incapacited drivers

Automated driver assistance systems and methods for towing predict vehicle/trailer instabilities and adapt automated driving control to avoid them. A tow-vehicle includes a controller that, through an actuator system, controls speed and/or steering. A map system and/or a sensor system monitor a roadway on which the vehicle is travelling to identify a road profile located ahead of the vehicle over a prediction horizon. A projected trajectory for navigating the vehicle through the road profile over the prediction horizon and considering environmental conditions is determined. Before travel over the road profile, whether the projected trajectory through the road profile will result in exceeding a vehicle dynamic threshold is determined. When the projected trajectory will result in exceeding the vehicle dynamic threshold through the road profile, a control action is determined to prevent instability and optimize driver experience. The vehicle is operated through the road profile using the control action.

Tow-vehicle driving methods and systems for automated driving

In accordance with an exemplary embodiment, methods and systems are provided for controlling steering of an autonomous vehicle. The method includes: operating, by a processor, the autonomous vehicle in a semi-automated mode; receiving, by the processor, driver input including a measured driver torque; receiving, by the processor, threat data; determining, by the processor, a steering command bias based on an impedance relation, impedance parameters, the measured driver torque, and the threat data; determining, by the processor, a reference angle based on the steering command bias and a desired angle; and generating, by the processor, control data to control the steering of the autonomous vehicle based on the reference angle.

Methods and systems for adaptive blending of driver and automated steering commands under external threat

Growing community of inventors

Waterloo, Canada

Mehdi Abroshan