A method of controlling inertial driving of a vehicle is provided. The method includes, when in an inertial driving guidance mode, obtaining information related to at least one event in consideration of a vehicle ahead situation, wherein the at least one event is a stop event, a deceleration event, or a re-acceleration event, determining a target shift stage corresponding to the at least one event based on the information related to the at least one event, and performing a shift control to the target shift stage.

An approach is provided for detecting lane-level dangerous slowdown events based on probe data and/or sensor data. The approach, for example, involves splitting probe data, sensor data, or a combination thereof into at least one vehicle trajectory, wherein the data is collected from one or more vehicles traveling on a road segment. For each vehicle trajectory of the at least one vehicle trajectory, the approach also involves processing said each vehicle trajectory to detect a slowdown event based on a speed reduction greater than a threshold reduction. The approach further involves classifying a slowdown event type of the slowdown event based on a final driving location, a final driving speed, or a combination thereof of the at least one vehicle trajectory. The approach further involves providing the slowdown event, the slowdown event type, or a combination thereof as an output for the road segment.

A control device for a vehicle having: an engine; and a variator arranged downstream of the engine in a power transmission path connecting the engine and drive wheels, wherein the control device for the vehicle has a controller that executes a low standby control which downshifts the variator by moving a belt of the variator in a vertical direction (radial direction) during stopping of the vehicle. After starting the low standby control, the controller releases an output limit of the engine based on an actual secondary pressure of the variator.

A driving support apparatus (12) has: a setting device (122) for setting a first target position (31) on the basis of a first sign object (21), if the first sign object requesting a vehicle (1) to stop is detected; and a supporting device (123) for performing a first deceleration control for decelerating the vehicle to a first target speed before the vehicle reaches the first target position, if a second sign object (22) representing a stop position is detected during a period when the first decelerating control is performed, the setting device sets a second target position (32) on the basis of the second sign object and the supporting device performs a second decelerating control for decelerating the vehicle to a second target speed before the vehicle reaches the second target position.

A driving assistance device includes a guide line detecting unit configured to detect the guide line, a remaining distance acquiring unit configured to acquire a remaining distance to the scheduled stop position, and a braking control unit configured to control deceleration of a vehicle. The guide line detecting unit detects a base-point mark, a curvature of the guide line, and a curvature feature point. The remaining distance acquiring unit acquires the remaining distance on the basis of the position of the base-point mark when the guide line detecting unit has detected the base-point mark, and acquires the remaining distance on the basis of the position of the curvature feature point when the guide line detecting unit has not detect the base-point mark and has detected the curvature feature point.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting a pull-over location using machine learning. One of the methods includes obtaining data specifying a target pull-over location for an autonomous vehicle travelling on a roadway. A plurality of candidate pull-over locations in a vicinity of the target pull-over location are identified. For each candidate pull-over location, an input that includes features of the candidate pull-over location is processed using a machine learning model to generate a respective likelihood score representing a predicted likelihood that the candidate pull-over location is an optimal location. The features of the candidate pull-over location include one or more features that compare the candidate pull-over location to the target pull-over location. Using the respective likelihood scores, one of the candidate pull-over locations is selected as an actual pull-over location for the autonomous vehicle.

This document describes methods and systems for enabling an autonomous vehicle (AV) to determine a path to a stopping location. The AV will determine a desired stop location (DSL) that is associated with a service request. The AV's motion control system will move the AV along a path to the DSL. While moving along the path, the AV's perception system will detect ambient conditions near the DSL. The ambient conditions will be parameters associated with a stopping rule. The AV will apply the stopping rule to the ambient conditions to determine whether the stopping rule permits the AV to stop at the DSL. If the stopping rule permits the AV to stop at the DSL, the motion control system will move the AV to, and stop at, the DSL. Otherwise, the motion control system will not stop the AV at the DSL.

System that causes a first vehicle and a second vehicle to perform automated valet parking includes one or more processors configured to cause, a second vehicle to perform follow-up traveling to follow a first vehicle; set a stop position between the first vehicle and the second vehicle when the second vehicle is performing the follow-up traveling to follow the first vehicle in the parking place; calculate, between the stop position and a position where the second vehicle starts deceleration to stop at the stop position; and set a target vehicle-to-vehicle distance of the second vehicle from the first vehicle, and set, as the target vehicle-to-vehicle distance, a distance longer than a sum of the deceleration start distance and a margin distance from the stop position to the first vehicle.

Embodiments for operational envelope detection (OED) with situational assessment are disclosed. Embodiments herein relate to an operational envelope detector that is configured to receive, as inputs, information related to sensors of the system and information related to operational design domain (ODD) requirements. The OED then compares the information related to sensors of the system to the information related to the ODD requirements, and identifies whether the system is operating within its ODD or whether a remedial action is appropriate to adjust the ODD requirements based on the current sensor information. Other embodiments are described and/or claimed.

A method for providing instructions for controlling vehicle, the method comprising: predicting a near-future driving path for the vehicle using sensor data received from environmental sensors of the vehicle. Retrieving at least one acceptable spatial deviation value indicative of the acceptable deviation from the predicted driving path. Determining a limit velocity value or a longitudinal deceleration value based on predetermined relations between spatial deviations from the near-future driving path and vehicle motion parameters and corresponding error values. The limit velocity value and the longitudinal deceleration value are determined with the constraint that the acceptable spatial deviation is not violated along the predicted driving path. Providing an instruction signal comprising an instruction for the vehicle to travel below the limit velocity value, or comprising an instruction to decelerate according to the longitudinal deceleration value in the event of a safe stop procedure.