A parallel computing method for man-machine coordinated steering control of a smart vehicle based on risk assessment is provided, comprising the following steps: building a lateral kinetic equation model of a vehicle; building a target function by targeting at minimizing an offset distance of a vehicle driving track from a lane center line and making a change in a front wheel steering angle and a longitudinal acceleration as small as possible in a driving process; building a parallel computing architecture of a prediction model and the target function, and employing a triggering parallel computing method; solving and computing a gradient with a manner of back propagation and using a gradient descent method to obtain an optimal control amount of the front wheel steering angle and an optimal control amount of the longitudinal acceleration; and computing a driving weight, obtaining a desired front wheel steering angle and completing real time control.

Techniques are described to determine parameters and/or values for a control model that can be used to operate an autonomous vehicle, such as an autonomous semi-trailer truck. For example, a method of obtaining a data-driven model for autonomous driving may include obtaining data associated with a first set of variables that characterize movements of an autonomous vehicle over time and commands provided to the autonomous vehicle over time, determining, using at least the first set of data, non-zero values and an associated second set of variables that describe a control model used to perform an autonomous driving operation of the autonomous vehicle, and calculating values for a feedback controller that describes a transfer function used to perform the autonomous driving operation of the autonomous vehicle driven on a road.

A control method for a host vehicle (100), the method comprising the steps of: a) acquiring a speed Vx of the host vehicle, a relative speed Vr between a preceding vehicle (200) and the host vehicle (100), and a relative distance Dr between the preceding vehicle and the host vehicle; b) calculating a perceived risk level (PRL) as a function of said speed Vx of the host vehicle, said relative speed Vr, said relative distance Dr based on equation (1a):

PRL=PRL(Vr,Vx,Dr)  (1a) with the PRL function decreasing when Vx/dr increases, with Vr being constant; c) controlling at least one vehicle device (32, 34, 36, 38) of the host vehicle as a function of the perceived risk level (PRL).

A computer program, a non-transitory computer-readable medium, and an automated driving system for implementing the above method.

A driving skill evaluation system configured to evaluate a driving skill of a driver includes a correction operation detection unit configured to detect a correction operation of a driving operation of the driver, a cause estimation unit configured to perform an estimation of a cause of the correction operation based on vehicle traveling state information at a time point when the correction operation is performed and vehicle traveling state information at time points before a predetermined period and after a predetermined period of the time point when the correction operation is performed, and an evaluation unit configured to evaluate the driving skill of the driver based on a result of the estimation.

A travel plan generation device used for an autonomous driving system of a vehicle includes circuitry, in which the circuitry is configured to generate a restriction related to a quantity of state of the vehicle, and generate a target trajectory and a target vehicle speed of the vehicle as a travel plan so as to satisfy the restriction by using a Bayes filter as a state estimation calculation without a convergence calculation.

Embodiments disclose a system and method to automatically turn and return a steering of an autonomous driving vehicle (ADV) to a center position. According to a first aspect, a system performs a turn by applying a steering command to an autonomous driving vehicle (ADV). In response to turning, the system determines a current percentage steering, speed, and heading direction of the ADV. The system selects a steering return trajectory profile from one or more steering return trajectory profiles based on the determined speed of the ADV. The system generates a steering return trajectory based on the selection. The system controls the ADV to return a steering to a center position based on the generated steering return trajectory.

Provided are a full-automatic parking method and system. The full-automatic parking method comprises: receiving a start instruction sent by a user, and activating an automatic parking system according to the start instruction; controlling a vehicle to automatically move forward and search, during moving, whether there is an available parking space at the left side or the right side of the vehicle, and when there is an available parking space, identifying basic information of the target parking space; planning a parking path according to the identified basic information of the target parking space, and obtaining a start point of parking and a parking path from the start point of parking to an end point of parking; controlling the vehicle to automatically move to the start point of parking; and controlling the vehicle to automatically park in the parking space according to the planned parking path. Through the full-automatic parking method and system provided by the present disclosure, a vehicle searches and identifies a free parking space while automatically moving forward, and automatically parks in the parking space; no human involvement is required in the whole process of searching a parking space and parking, thereby implementing full-automatic parking.

A control unit is provided for an ego vehicle equipped with a transverse guidance actuator which is designed to transversely guide the ego vehicle in an at least partly automated manner during a follow-on drive. The control unit is designed to detect a transverse guidance maneuver of the ego vehicle required for the follow-on drive. The control unit is additionally designed to ascertain driver information with respect to the driver of the ego vehicle, the driver information including at least one indication of how engaged the driver is with monitoring and/or carrying out the transverse guidance of the ego vehicle. The control unit is further designed to set a dynamic of an intervention, which is automatically carried out by the transverse guidance actuator of the ego vehicle, for the transverse guidance maneuver on the basis of the ascertained driver information.

A vehicle control system includes a controller circuit in communication with a steering sensor and one or more perception sensors. The steering sensor is configured to detect a steering torque of a steering wheel of a host vehicle. The one or more perception sensors are configured to detect an environment proximate the host vehicle. The controller circuit is configured to determine when an operator of the host vehicle requests a take-over from fully automated control of the host vehicle based on the steering sensor. The controller circuit classifies the take-over request based on the steering sensor.

An information processing apparatus according to one embodiment includes a processing circuit. The processing circuit calculates a first presence probability of an object present around a moving body with positional information measured by each of a plurality of sensors having different characteristics, acquires non-measurement information indicating that the positional information on the object has not been obtained for each of the sensors, and determines a second presence probability of the object based on the first presence probability and the non-measurement information.