Fuzzy-logic based traction control for electric vehicles is provided. The system detects a wheel slip ratio for each wheel. The system receives an input torque command. The system determines a slip error for each wheel based on the wheel slip ratio for each wheel and a target wheel slip ratio. The system, using the fuzzy-logic based control selection technique, selects a traction control technique from one of a least-quadratic-regulator, a sliding mode controller, a loop-shaping based controller, or a model predictive controller. The system generates a compensation torque value for each wheel. The system generates the compensation torque value based on the traction control technique selected via the fuzzy-logic based control selection technique and the slip error for each wheel. The system transmits commands to actuate drive units of the vehicles based on the compensation torque value.

Fuzzy-logic based traction control for electric vehicles is provided. The system detects a wheel slip ratio for each wheel. The system receives an input torque command. The system determines a slip error for each wheel based on the wheel slip ratio for each wheel and a target wheel slip ratio. The system, using the fuzzy-logic based control selection technique, selects a traction control technique from one of a least-quadratic-regulator, a sliding mode controller, a loop-shaping based controller, or a model predictive controller. The system generates a compensation torque value for each wheel. The system generates the compensation torque value based on the traction control technique selected via the fuzzy-logic based control selection technique and the slip error for each wheel. The system transmits commands to actuate drive units of the vehicles based on the compensation torque value.

A vehicle control device configured to control switching of drive mode of a vehicle including an internal combustion engine and a motor includes a processor configured to switch, in a case where a road surface of a perimeter of a geofencing zone is a road surface on which there is a high probability that the vehicle slips, in a movement route from an outside of the geofencing zone to an inside of the geofencing zone, the drive mode of the vehicle to drive by the motor in a state in which there is a low probability that the vehicle slips, outside the geofencing zone.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining causal models for controlling environments. One of the methods includes obtaining data specifying baseline probability distributions for each of a plurality of controllable elements; maintaining a causal model; repeatedly performing the following: selecting control settings for the environment based on the causal model and values for a particular internal parameter of the control system that are sampled from a range of possible values; selecting control settings for the environment based on the baseline probability distributions; monitoring environment responses to the control settings selected based on the causal model and the control settings selected based on the baseline probability distributions; determining, for each of the possible values, a measure of a difference between a current system performance and a baseline system performance; and updating how frequently each of the possible values is sampled.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining causal models for controlling environments. One of the methods includes obtaining data specifying baseline probability distributions for each of a plurality of controllable elements; maintaining a causal model; repeatedly performing the following: selecting control settings for the environment based on the causal model and values for a particular internal parameter of the control system that are sampled from a range of possible values; selecting control settings for the environment based on the baseline probability distributions; monitoring environment responses to the control settings selected based on the causal model and the control settings selected based on the baseline probability distributions; determining, for each of the possible values, a measure of a difference between a current system performance and a baseline system performance; and updating how frequently each of the possible values is sampled.

A method for estimating a grip of a tire supporting a vehicle includes generating a first set of data from a tire-mounted sensor unit, generating a second set of data from the tire-mounted sensor unit and from data obtained from the vehicle, and generating a third set of data from data obtained from the vehicle and from the Internet. A grip estimation module is provided. The first, second and third sets of data are received in the grip estimation module. A friction probability distribution is calculated with the grip estimation module using the first, second and third sets of data, and the friction probability distribution is input into at least one vehicle system.

A method for estimating a grip of a tire supporting a vehicle includes generating a first set of data from a tire-mounted sensor unit, generating a second set of data from the tire-mounted sensor unit and from data obtained from the vehicle, and generating a third set of data from data obtained from the vehicle and from the Internet. A grip estimation module is provided. The first, second and third sets of data are received in the grip estimation module. A friction probability distribution is calculated with the grip estimation module using the first, second and third sets of data, and the friction probability distribution is input into at least one vehicle system.

Embodiments of the present application disclose a safety control method and a safety control system based on environmental risk assessment for an intelligent connected vehicle. The method includes: when a vehicle is in an automatic driving mode, acquiring environmental parameter information of the vehicle in a current driving environment; determining a target driving control parameter which meets a preset safe driving condition under the current environmental parameter; and managing a current automatic driving level of the vehicle by using the target driving control parameter.

Embodiments of the present application disclose a safety control method and a safety control system based on environmental risk assessment for an intelligent connected vehicle. The method includes: when a vehicle is in an automatic driving mode, acquiring environmental parameter information of the vehicle in a current driving environment; determining a target driving control parameter which meets a preset safe driving condition under the current environmental parameter; and managing a current automatic driving level of the vehicle by using the target driving control parameter.

The disclosure relates to a method for monitoring behavior of a tire of a vehicle in a rolling condition of the tire, comprising the steps of: acquiring a signal representative of an acceleration of a specified point of the tire, deriving from the signal a curve which represents a profile of the acceleration of the point during a revolution of the tire, determining a leading portion and a trailing portion of the curve, corresponding to an entry of the point into a footprint region of the tire and corresponding to an exit of the point from the footprint region of the tire, respectively, determining a first measure of a volatility of the signal in the leading portion and a second measure of a volatility of the signal in the trailing portion, and determining an indication of the behavior of the tire based on the first measure and the second measure.