In one embodiment, a method by a computing system of a vehicle includes determining an environment of the vehicle. The method includes generating, based on the environment, multiple proposed vehicle actions with associated operational data. The method includes determining a comfort level for each proposed vehicle action by processing the environment and operational data using a model for predicting comfort levels of vehicle actions. The model is trained using records of performed vehicle actions. The record for each performed vehicle action includes environment data, operational data, and a perceived passenger comfort level for the performed vehicle action. The method includes selecting a vehicle action from the proposed vehicle actions based on the determined comfort level. The method includes causing the vehicle to perform the selected vehicle action.

An adaptive lane-keeping system for a commercial vehicle, including: an input module for entering sensor data from at least one sensor which is configured to detect the surroundings of the commercial vehicle; an evaluation module for evaluating the sensor data to determine a relative position of the commercial vehicle on a road; a lane-keeping module for controlling a steering system of the commercial vehicle based on a lane-keeping profile that defines a torque to be applied to a steering wheel of the commercial vehicle to support keeping in a lane; and a change module for changing the lane-keeping profile in response to a change in the detected environment. Also described is a related commercial vehicle, method, and computer readable medium.

A driving support apparatus comprises a controller for performing collision avoidance braking control and lane deviation suppressing control. When a performing condition of the lane deviation suppressing control is satisfied at a timing of the collision avoidance braking control is about to be performed, the controller makes direction determination processing for determining whether or not the own vehicle travels to a direction toward which it will collide with a target object or to a direction toward which it will avoid colliding with the target object. In the direction determination processing, when it is determined the own vehicle travels to a collision direction, the controller stops the lane deviation suppressing control to perform the collision avoidance braking control, and when it is determined the own vehicle travels to a collision avoidance direction, the controller performs cooperative control for making the lane deviation suppressing control cooperate with the collision avoidance braking control.

Provided is a control apparatus for a vehicle configured to perform driving support control when a driving support operation state is an on state, the control apparatus being further configured to, in a case where the driving support operation state is the on state and a driving operation switching request for changing the driving support operation state to an off state is issued, calculate a target speed at a driving operation switching time point at which the driving support operation state is changed from the on state to the off state, and perform deceleration control for decelerating the vehicle such that a speed of the vehicle matches the target speed at the driving operation switching time point.

This application is directed to on-vehicle behavior modeling of vehicles. A vehicle has one or more processors, memory, a plurality of sensors, and a vehicle control system. The vehicle collects training data via the plurality of sensors, and the training data include data for one or more vehicles during a collection period. The vehicle locally applies machine learning to train a vehicle driving behavior model using the collected training data. The vehicle driving behavior model is configured to predict a behavior of one or more vehicles. The vehicle subsequently collecting sensor data from the plurality of sensors and drives the vehicle by applying the vehicle driving behavior model to predict vehicle behavior based on the collected sensor data. The vehicle driving behavior model is configured to predict behavior of an ego vehicle and/or a distinct vehicle that appears near the ego vehicle.

This disclosure describes systems and methods for determining vehicle parking scores. An example method may include calculating, subsequent to a first vehicle parking within a first parking space of a parking lot and based on first sensor data obtained by the first vehicle, a first vehicle parking score. The example method may also include calculating, subsequent to a second vehicle parking within the first parking space of the parking lot and based on second sensor data obtained by the second vehicle, a second vehicle parking score. The example method may also include calculating a first average vehicle parking score for the first parking space based on the first vehicle parking score and the second vehicle parking score. The example method may also include presenting an indication of the first average vehicle parking score for the first parking space to a third vehicle within the parking lot.

An autonomous vehicle can obtain sensor data. Upon determining that the autonomous vehicle is in a lane adjacent a shoulder, and there is an object in the shoulder, the autonomous vehicle can determine if performing a lane change maneuver out of the lane prior to the autonomous vehicle being positioned adjacent to the object is feasible. If it is, the lane change maneuver can be performed. If it is not, a nudge maneuver and/or a deceleration can be performed.

Systems and techniques are described for detecting a lane departure event. In aspects, a method includes obtaining a lateral acceleration value of the vehicle, determining a time-to-lane boundary (TTLB) threshold value using a saturated linear function of the lateral acceleration value of the vehicle, determining a current TTLB value of the vehicle with respect to a lane boundary, comparing the current TTLB value to the TTLB threshold value, and outputting a signal indicative of vehicle proximity to the lane boundary if the current TTLB value satisfies a triggering condition with respect to the TTLB threshold value.

A driving recognition-based regenerative braking control method of an xEV vehicle according to an embodiment of the present invention relates to a driving recognition-based regenerative braking control method of an xEV vehicle which optimally adjusts an amount of regenerative braking using preceding vehicle sensing and driving position information.

A system and method of lane detection using density based spatial clustering of applications with noise (DBSCAN) includes capturing an input image with one or more optical sensors disposed on a motor vehicle. The method further includes passing the input image through a heterogeneous convolutional neural network (HCNN). The HCNN generates an HCNN output. The method further includes processing the HCNN output with DBSCAN to selectively classify outlier data points and clustered data points in the HCNN output. The method further includes generating a DBSCAN output selectively defining the clustered data points as predicted lane lines within the input image. The method further includes marking the input image by overlaying the predicted lane lines on the input image.