An example method of generating a neural network control policy for a vehicle includes obtaining a performance objective parameter associated with a control system of a vehicle, obtaining a policy optimizing algorithm corresponding to the performance objective parameter, defining a system state space, a control action space, and a disturbance space, each associated with the control system, generating a neural network control policy, based on the system state space, the control action space, and the disturbance space, wherein the neural network control policy has a non-linear H-infinity robustness guarantee, and automatically controlling at least one vehicle component according to the neural network control policy.

A method for controlling in real time the path of a motor vehicle travelling in a traffic lane includes detecting a corner in the traffic lane, then, when the vehicle enters the corner, determining first and second quantities for a plurality of successive sampling increments, based on state variables characteristic of the movement of the vehicle, determining a first stored value dependent on the first quantity determined in the current sampling increment and one of the preceding sampling increments, determining a second stored value dependent on the second quantity determined in the current sampling increment and one of the preceding sampling increments, saving the first and second stored values determined for each sampling increment, then, when the vehicle exits the corner determining a value of the understeer gradient depending on the saved first and second stored values, and determining a command for the vehicle based on the understeer gradient.

An example method of generating a neural network control policy for a vehicle includes obtaining a performance objective parameter associated with a control system of a vehicle, obtaining a policy optimizing algorithm corresponding to the performance objective parameter, defining a system state space, a control action space, and a disturbance space, each associated with the control system, generating a neural network control policy, based on the system state space, the control action space, and the disturbance space, wherein the neural network control policy has a non-linear H-infinity robustness guarantee, and automatically controlling at least one vehicle component according to the neural network control policy.

A vehicle control device includes a vehicle position calculating unit, an obstacle determining unit, a collision possibility determining unit, an avoidance means selecting unit, an avoidance route calculating unit, and a steering control value calculating unit that calculates a steering control value and that outputs the steering control value to a steering actuator control unit. The avoidance route calculating unit calculates a target point for avoiding the obstacle, divides an avoidance section connecting the position of the vehicle to the target point into a plurality of partial sections, calculates a partial avoidance route in each of the partial sections, and calculates the avoidance route made up of the plurality of partial avoidance routes.

A computer system and computer-implemented method for determining a longitudinal slip limit for a steered axle of a vehicle having two steered axles are disclosed. The computer system has processing circuitry to acquire a reference body slip for a steered axle of the vehicle; acquire a current body slip for the steered axle; determine a first difference between the reference body slip and the current body slip; acquire an initial longitudinal slip limit for the steered axle; and determine an adjusted longitudinal slip limit for the steered axle based on the first difference and the initial longitudinal slip limit for the steered axle.

A computer system and computer-implemented method for determining a rotational speed limit for a steered axle of a vehicle having two steered axles are disclosed. The computer system has processing circuitry to acquire a combined slip limit for the steered axle based on a slip diamond; determine a longitudinal slip limit for the steered axle based on the combined slip limit and a current lateral slip of the steered axle; and determine a rotational speed limit for the steered axle based on the determined longitudinal slip limit, a radius of a wheel of the steered axle, and a current longitudinal velocity of the vehicle.

A method for automatically parking a vehicle on a sloped roadway. The method detects a roadway slope gradient, utilizing at least one vehicle sensor, at a roadway where the vehicle is presently located. The method calculates at least one vehicle slope value responsive to the detected slope gradient and a validation threshold over a period of time. The method instructs, using a vehicle controller, a plurality of vehicle tires to turn in a direction according to the at least one vehicle slope value. The method applies a parking brake to the vehicle, using the vehicle controller. The method sends an acknowledgement notification, using the vehicle controller, to inform a user of the vehicle.

Systems and methods actuate torque vectoring and independent wheel steering control capabilities of an over-actuated vehicle in order to compensate for instability in potentially dangerous driving scenarios, such as during towing of the over-actuated vehicle. The disclosed vehicle stabilization system can detect a condition associated with a movement of the over-actuated vehicle and dynamically generate a stabilization control command. A condition detected by the vehicle stabilization system can indicate instability of the over-actuated vehicle and include unstable conditions such as sway, jackknifing, oversteering, understeering, yaw instability, roll instability, and pitch instability. The stabilization control command indicates one or more independent wheel steering and torque vectoring controls for the over-actuated vehicle. The vehicle stabilization system can execute autonomous actions to maneuver the over-actuated vehicle based on the stabilization control command in a manner that compensate for the instability of the movement of the over-actuated vehicle.

The disclosure relates to a method for compensating a yaw moment acting on a vehicle which is caused by asymmetrical braking forces on at least one vehicle axle. In the method, at least one vehicle-related condition is queried after initiation of a braking operation, a yaw variable present on the vehicle is detected, the value of the detected yaw variable is compared with a yaw variable limit value, a corrective steering angle is determined depending on the difference and/or the change in the difference between the value of the detected yaw variable and the yaw variable limit value, taking into account the sign of the yaw variable, and, lastly, a corrective steering angle is automatically set on at least one vehicle wheel of a steered vehicle axle. The disclosure also relates to an apparatus for compensating a yaw moment acting on a vehicle.

A method for operating a self-driving vehicle is provided. The method includes specifying a lateral dynamics requirement for controlling the lateral dynamics of the self-driving vehicle along a route. The lateral dynamics requirement is communicated to a steering control device for controlling steering kinematics of the self-driving vehicle. The method checks whether the communicated lateral dynamics requirement satisfies a lateral dynamics criterion for the operation of the self-driving vehicle, and communicates a brake command to stop the self-driving vehicle depending on a checking result resulting from the checking step.