Abstract: A trajectory planning system for an autonomous vehicle includes one or more controllers in electronic communication with one or more external vehicle networks that collect data with respect to one or more moving obstacles located in an environment surrounding the autonomous vehicle. The one or more controllers determine, based on the discrete-time relative vehicle state, a position avoidance set representing relative lateral positions and longitudinal positions that the autonomous vehicle avoids while bypassing the one or more moving obstacles when performing a maneuver. The one or more controllers select a trajectory from the plurality of relative state trajectories for the autonomous vehicle, where the autonomous vehicle follows the trajectory while performing the maneuver.

Abstract: A method includes receiving planned path data, road data, and speed profile data, determining anticipatory constraints for each of the plurality of steps along a planned path using the planned path data, the road data, and the speed profile data, determining a plurality of control actions using a Model Predictive Control (MPC). The prediction model of the MPC is updated in real time with the plurality of anticipatory constraints for each of the plurality of steps along the planned path and the road data for each of the plurality of steps along the planned path. The method further includes controlling the vehicle using the plurality of control actions to cause the vehicle to autonomously follow the planned path.

Abstract: A method includes receiving sensed vehicle-state data, actuation-command data, and surface-coefficient data from a plurality of remote vehicles, inputting the sensed vehicle-state data, the actuation-command data, and the surface-coefficient data into a self-supervised recurrent neural network (RNN) to predict vehicle states of a host vehicle in a plurality of driving scenarios, and commanding the host vehicle to move autonomously according to a trajectory determined using the vehicle states predicted using the self-supervised RNN.

Abstract: A method of estimating a performance characteristic of a wheel of a vehicle, includes selecting relevant input features based on wheel dynamics and tire behavior, and collecting experimental data for each of the relevant input features at each of a plurality of vehicle operating conditions. The method further includes manually identifying and labeling wheel stability status over time from the experimental data and calculating tractive limit over time from the experimental data. The method also includes training a tractive limit model and training a wheel stability status model. The method further includes receiving a plurality of testing inputs, wherein each of the plurality of testing inputs is received from a sensor on-board the vehicle or from a controller on-board the vehicle and, processing the received testing inputs in a predetermined machine learning process to calculate in one or more data processors a prediction of the performance characteristic.

Abstract: A method for estimating lateral force includes receiving vehicle data. The vehicle includes a plurality of tires. The method further includes using a bicycle model to determine first lateral forces at each of the plurality of tires of the vehicle, using a double-track model to determine second lateral forces at each of the plurality of tires of the vehicle, fusing the first lateral forces determined using the bicycle model and the second lateral forces using the double-track model to determine third lateral forces at each of the plurality of tires of the vehicle, and controlling an actuator of the vehicle using the third lateral forces at each of the plurality of tires of the vehicle.

Abstract: A rule-based adaptive cruise control system for determining a vehicle-following behavior of a vehicle includes a plurality of perception sensors for collecting perception data representing an environment surrounding the vehicle and one or more controllers in electronic communication with the plurality of perception sensors. The one or more controllers categorize a profile of a roadway based on a route plan and the perception data into one of a plurality of roadway profiles that are each indicative of the geometry of the roadway, categorize detection of a preceding vehicle based on the perception data into one of a plurality of detection states, classify the selected roadway profile and the selected detection state into one of a plurality of scenarios based on a set of classification rules, and assign a specific vehicle-following behavior based on the selected scenario.

Abstract: A method includes receiving sensed vehicle-state data, actuation-command data, and surface-coefficient data from a plurality of remote vehicles, inputting the sensed vehicle-state data, the actuation-command data, and the surface-coefficient data into a self-supervised recurrent neural network (RNN) to predict vehicle states of a host vehicle in a plurality of driving scenarios, and commanding the host vehicle to move autonomously according to a trajectory determined using the vehicle states predicted using the self-supervised RNN.

Abstract: A system for managing chassis and driveline actuators of a motor vehicle includes a control module executing program code portions that: cause sensors to obtain vehicle state information, receive a driver input and generate a desired dynamic output based on the driver input and the vehicle state information, and then estimate actuator actions based on the vehicle state information, generate one or more control action constraints based on the vehicle state information and estimated actuator actions, generate a reference control action based on the vehicle state information, the estimated actions of the one or more actuators and the control action constraints, and integrate the vehicle state information, the estimated actuator actions, desired dynamic output, reference control action and the control action constraints to generate an optimal control action that falls within a range of predefined actuator capacities and ensures driver control of the vehicle.

Abstract: A system for imitating target vehicle behavior in automated driving includes sensors capturing ego and target vehicle condition information, actuators selectively altering an ego vehicle state, and control modules. The control modules execute a target vehicle imitating (TVI) application. A first TVI control logic estimates a target vehicle state and trajectory. The ego and target vehicle condition information partially define the target vehicle state and trajectory. A second control logic evaluates target vehicle safety and performance constraints. A third control logic selectively initiates an imitation mode of the ego vehicle based on target and ego vehicle statuses relative to the target vehicle safety and performance constraints. A fourth control logic, models the target vehicle and optimizes a planned ego vehicle path subject to actuator constraints. A fifth control logic generates outputs to the actuators to cause the ego vehicle to follow the planned path and imitate the target vehicle.

Abstract: A system for learning-model predictive control (LMPC) with multi-step prediction for motion control of a vehicle includes sensors and actuators. One or more control modules each having a processor, a memory, and input/output (I/O) ports are in communication with the sensors and actuators, the processor executing program code portions stored in the memory. The program code portions cause the sensors and actuators to obtain vehicle state information, receive a driver input, and generate a desired dynamic output based on the driver input and the vehicle state information. A program code portion estimates actions of the actuators based on the vehicle state information and the driver input, and utilizes the vehicle state information, the driver input, and the estimated actions of the actuators to select one or more models of a physics-based vehicle model and a machine-learning model of the vehicle to selectively adjust commands to the actuators.

Abstract: A system for real-time control selection and calibration in a vehicle using a deep-Q network (DQN) includes sensors and actuators disposed on the vehicle. A control module has a processor, memory, and input/output (I/O) ports in communication with the one or more sensors and the one or more actuators. The processor executes program code portions that cause the sensors actuators to obtain vehicle dynamics and road surface estimation information and utilize the vehicle dynamics information and road surface estimation information to generate a vehicle dynamical context. The system decides which one of a plurality of predefined calibrations is appropriate for the vehicle dynamical context, generates a command to the actuators based on a selected calibration. The system continuously and recursively causes the program code portions to execute while the vehicle is being operated.

Abstract: A method of estimating a performance characteristic of a wheel of a vehicle, includes selecting relevant input features based on wheel dynamics and tire behavior, and collecting experimental data for each of the relevant input features at each of a plurality of vehicle operating conditions. The method further includes manually identifying and labeling wheel stability status over time from the experimental data and calculating tractive limit over time from the experimental data. The method also includes training a tractive limit model and training a wheel stability status model. The method further includes receiving a plurality of testing inputs, wherein each of the plurality of testing inputs is received from a sensor on-board the vehicle or from a controller on-board the vehicle and, processing the received testing inputs in a predetermined machine learning process to calculate in one or more data processors a prediction of the performance characteristic.

Abstract: A method includes receiving planned path data, road data, and speed profile data, determining anticipatory constraints for each of the plurality of steps along a planned path using the planned path data, the road data, and the speed profile data, determining a plurality of control actions using a Model Predictive Control (MPC). The prediction model of the MPC is updated in real time with the plurality of anticipatory constraints for each of the plurality of steps along the planned path and the road data for each of the plurality of steps along the planned path. The method further includes controlling the vehicle using the plurality of control actions to cause the vehicle to autonomously follow the planned path.

Abstract: A method includes receiving sensed vehicle-state data, actuation-command data, and surface-coefficient data from a plurality of remote vehicles, inputting the sensed vehicle-state data, the actuation-command data, and the surface-coefficient data into a self-supervised recurrent neural network (RNN) to predict vehicle states of a host vehicle in a plurality of driving scenarios, and commanding the host vehicle to move autonomously according to a trajectory determined using the vehicle states predicted using the self-supervised RNN.

Abstract: A method includes receiving sensed vehicle-state data, actuation-command data, and surface-coefficient data from a plurality of remote vehicles, inputting the sensed vehicle-state data, the actuation-command data, and the surface-coefficient data into a self-supervised recurrent neural network (RNN) to predict vehicle states of a host vehicle in a plurality of driving scenarios, and commanding the host vehicle to move autonomously according to a trajectory determined using the vehicle states predicted using the self-supervised RNN.

Abstract: A trajectory planning system for an autonomous vehicle includes one or more controllers in electronic communication with one or more external vehicle networks that collect data with respect to one or more moving obstacles located in an environment surrounding the autonomous vehicle. The one or more controllers determine, based on the discrete-time relative vehicle state, a position avoidance set representing relative lateral positions and longitudinal positions that the autonomous vehicle avoids while bypassing the one or more moving obstacles when performing a maneuver. The one or more controllers select a trajectory from the plurality of relative state trajectories for the autonomous vehicle, where the autonomous vehicle follows the trajectory while performing the maneuver.

Abstract: A system comprises a computer including a processor and a memory. The memory includes instructions such that the processor is programmed to generate vehicle-level commands based on received vehicle operation commands. The received vehicle operation commands can comprise input commands corresponding to at least one of an autonomous vehicle (AV) mode of operation or a manual mode of operation. The processor is also programmed to generate target actuator commands based on the vehicle-level commands and transmit the target actuator commands to at least one actuator.

Abstract: A system includes a primary control module, a stability status module, and a supervisory control module. The primary control module is configured to determine at least one control action for at least one of an electronic limited slip differential and an aerodynamic actuator of a vehicle based on a driver command. The stability status module is configured to determine whether at least one component of the vehicle is stable or unstable based on an input from a sensor on the vehicle. The at least one component includes at least one of a vehicle body, a front axle, a rear axle, front wheels, and rear wheels. The supervisory control module is configured to adjust the at least one control action when the at least one component is unstable.

Abstract: A system for supervisory control for eAWD and eLSD in a motor vehicle includes a control module, and sensors and actuators disposed on the motor vehicle. The sensors measure real-time motor vehicle data, and the actuators alter behavior of the motor vehicle. The control module receives the real-time data; receives one or more driver inputs to the motor vehicle; determines a status of a body of the motor vehicle; determines a status of axles of the motor vehicle; determines a status of each wheel of the motor vehicle; and generates a control signal to the actuators from the driver inputs and the body, axle, and wheel statuses. The control module also exercises supervisory control by actively adjusting constraints on the control signal to each of the actuators where actively adjusting constraints on the control signal alters boundaries of control actions in response to the one or more driver inputs.

Abstract: Systems and methods for controlling a vehicle are provided. The systems and methods include a sensor system and a processor configured to execute program instructions, to cause the at least one processor to: receive yaw rate values, lateral acceleration values and longitudinal velocity values for the vehicle from the sensor system, determine side slip angle parameter values based on the yaw rate values, lateral acceleration values and longitudinal velocity values, determine phase portrait angles based on the side slip angle parameter values and the yaw rate values, wherein the phase portrait angles each represent an angle between yaw rate and side slip angle for the vehicle in a phase portrait of yaw rate and side slip angle, detect or predict vehicle instability based at least on the phase portrait angles, and when vehicle instability is detected or predicted, control motion of the vehicle to at least partly correct the vehicle instability.