Provided are a method for generating a lane changing decision-making model and a method and an apparatus for lane changing decision-making of an unmanned vehicle. The method for generating a lane changing decision-making model includes: obtaining a training sample set of vehicular lane changing, wherein the training sample set includes a plurality of training sample groups, each of the training sample groups includes a training sample under each time step length in a process that the vehicle completes lane changing based on a planned lane changing trajectory, the training sample includes a group of state variables and corresponding control variables; obtaining the lane changing decision-making model by training a decision-making model based on deep reinforcement learning network by use of the training sample set, wherein the lane changing decision-making model enables the state variable of the target vehicle and the corresponding control variable to be correlated.

An apparatus includes a front detection sensor detecting presence of a pedestrian on a driving lane of the vehicle, gaze information of the pedestrian, and a distance and a relative speed between the pedestrian and the vehicle; a vehicle sensor detecting at least one of a speed, an acceleration, a steering angle, a steering angular velocity, or a pressure of a master cylinder of the vehicle; an electronic control unit activating a function of a pedestrian detection and collision mitigation system based on information detected by the front detection sensor and the vehicle sensor; and a warning unit operated to inform a driver of a collision of the pedestrian with the vehicle by controlling the electronic control unit.

A vehicle may determine that erratic vehicle behavior has been sensed, based on comparison of a sensed vehicle behavioral characteristic at a given location compared to a predefined expected value of the characteristic. The vehicle may further determine whether an environmental anomaly has been detected in association with the given location and classify the sensed erratic behavior based on whether the environmental anomaly was detected. Responsive to classifying the behavior as erratic based on determining no environmental anomaly was detected, the vehicle may report the erratic behavior to a remote server, along with the given location. The remote server may receive a plurality of such reports for a given location and update a classification of the behavior based on data indicated in the plurality of reports.

A method for operating a driving assistant for the automated lateral guidance of a motor vehicle. The method includes: executing an automated lane guidance of the motor vehicle in a first traffic lane; ascertaining a hindrance situation of a further motor vehicle due to the motor vehicle; decision for the automated lane opening of the first traffic lane taking the hindrance situation into account; executing an automated lane change into a second traffic lane for opening the lane; executing an automated lane guidance in the second traffic lane after opening the lane. A device for carrying out the method is also described.

Embodiments of the present application provide a collision detection method and apparatus based on an autonomous vehicle, a device and a storage medium, where the method includes: acquiring first point cloud data of each obstacle in each region around the autonomous vehicle, where the first point cloud data represents coordinate information of the obstacle and the first point cloud data is based on a world coordinate system; converting the first point cloud data of the each obstacle into second point cloud data based on a relative coordinate system, where an origin of the relative coordinate system is a point on the autonomous vehicle; determining, according to the second point cloud data of the each obstacle in all regions, a possibility of collision of the autonomous vehicle. A de-positioning manner for collision detection is provided, thereby improving the reliability and stability of collision detection.

A driver assistance method for a vehicle includes the steps of establishing an energy prediction for a route on the basis of an anticipated driver behavior, determining a driving behavior which is optimized with regard to the energy prediction, and outputting an action recommendation on the basis of the optimized driving behavior.

A vehicle includes an electric machine and a controller. The controller is programmed to responsive to a threshold difference, indicative of wheel slip, between average wheel speed and a vehicle speed that is based on a difference between wheel acceleration and measured vehicle acceleration, command a speed to the electric machine to reduce the wheel slip.

Devices, systems, and methods related to prediction of tire performance using existing CAN data to improve overall vehicle performance. Machine learning tools are applied to CAN data, for example pilot data and/or vehicle dynamics data, to predict tire performance factors for use in a vehicle control system to provide vehicle lateral guidance control.

An onboard device estimates a traveling state of a vehicle that may be influenced by the psychological state of a driver, based on an utterance of the driver without the use of various sensors, and includes: a voice collection unit for collecting a driver's voice; a traveling state collection unit for collecting traveling state information representing a traveling state of a vehicle; a database generation unit for generating a database by associating voice information corresponding to the collected voice with the collected traveling state information; a learning unit for learning an estimation model, with pairs including the voice information and the traveling state information recorded in the generated database being used as learning data; and an estimation unit for estimating the traveling state of the vehicle that may be influenced by a psychological state of the driver by using the estimation model, based on an utterance of the driver.

A vehicle control device controls a driving device in such a manner that driving torque coincides with normal torque. The vehicle control device starts a traction control for controlling the driving device in such a manner that the driving torque coincides with suppressed torque which is smaller than the normal torque, when a predetermined traction control start condition is satisfied. The vehicle control device determines that the driver is in a non-grasp state, when an operation amount has changed to satisfy a condition in an initial determination time period. The vehicle control device starts, at an acceleration time point, an operation priority control for controlling the driving device in such a manner that the driving torque coincides with acceleration priority torque which is larger than the suppressed torque and smaller than the normal torque, if the control device had not determined that the driver was in the non-grasp state.