A driving support apparatus (10) executes collision prevention control for avoiding collision with the object when a possibility of a vehicle (VA) colliding with an object based on object information (e.g., distance, direction, and relative speed) acquired by a millimeter wave radar device (21) and a camera device (22) is high. Further, the driving support apparatus does not execute the collision prevention control when an accelerator pedal operation amount is equal to or larger than a stop threshold value. However, the driving support apparatus executes the collision prevention control even when the accelerator pedal operation amount is equal to or larger than the stop threshold value within a specific period of from a start point at which a predetermined erroneous operation condition is satisfied, to an end point, which is a time point after a predetermined consideration period has elapsed since the erroneous operation condition has no longer been satisfied.

In one embodiment, when speed control command (e.g., throttle, brake commands) is issued based on a target speed, a first feedback parameters is determined based on an expected speed and an actual speed of the ADV in response to the speed control command. A second feedback parameter is determined by applying a speed control parameter adjustment (SCPA) model to a set of input parameters that are captured or measured at the point in time. The set of input parameters represents a driving environment of the ADV at the point in time. One or more control parameters of a speed controller of the ADV is adjusted based on the first feedback parameter and the second feedback parameter, where the speed controller is configured to generate and issue speed control commands. Subsequent speed control commands can be generated based on the adjusted speed control parameters of the speed controller.

A vehicle safety support apparatus may include: a driver monitoring unit configured to monitor a driver; an external environment monitoring unit configured to monitor an external environment of a vehicle; and a control unit configured to determine a driving control for the vehicle based on data acquired from the driver monitoring unit and the external environment monitoring unit, and perform autonomous driving to move the vehicle to a safe area, when determining to take over the driving control from the driver.

Methods, apparatuses, systems, and non-transitory computer readable storage media for generating risk indicators are described. The disclosed technology includes determining a vehicle route of a vehicle and external object routes of external objects. The vehicle route is determined using vehicle route data including a vehicle location and a vehicle destination. The external object routes are determined using external object route data including external object locations and external object destinations. Based on a comparison of the vehicle route data and the external object route data, external object routes that satisfy a proximity criterion are determined. Risk data for the vehicle is generated based on a vehicle state of the vehicle and external object states of the external objects corresponding to the external object routes that satisfy the proximity criterion. In response to determining that the risk data satisfies a risk criterion, at least one risk indicator is generated.

The present disclosure provides a vehicle-mounted automatic drive control system, its control method and a vehicle containing the vehicle-mounted automatic drive control system. The vehicle-mounted automatic drive control system comprises at least one sensor, a controller, and a drive control feedback portion. The at least one sensor is coupled to the controller. The drive control feedback portion is coupled to the controller. The at least one sensor is configured to detect at least one object in an environment of the first vehicle and to send a detection result to the controller. The controller is configured to transmit a control signal to the drive control feedback portion if the detection result satisfies a preset condition. The drive control feedback portion is configured, upon receiving the control signal from the controller, to perform an operation such that the first vehicle can adjust a first driving status thereof.

Systems and methods are provided for navigating a host vehicle. In some embodiments, the system may include at least one processing device programmed to: receive at least one image representative of an environment of the host vehicle; determine a navigational action of the host vehicle; analyze the at least one image to identify a target vehicle in the environment of the host vehicle; determine a next-state distance between the host vehicle and the target vehicle that would result if the navigational action was taken; determine a maximum braking capability of the host vehicle, a maximum acceleration capability of the host vehicle, and a speed of the host vehicle; determine a stopping distance for the host vehicle; determine a speed of the target vehicle; and implement the navigational action if the determined stopping distance for the host vehicle is less than the next-state distance summed with a target vehicle travel distance.

A temporal prediction model for semantic intent understanding is described. An agent (e.g., a moving object) in an environment can be detected in sensor data collected from sensors on a vehicle. Computing device(s) associated with the vehicle can determine, based partly on the sensor data, attribute(s) of the agent (e.g., classification, position, velocity, etc.), and can generate, based partly on the attribute(s) and a temporal prediction model, semantic intent(s) of the agent (e.g., crossing a road, staying straight, etc.), which can correspond to candidate trajectory(s) of the agent. The candidate trajectory(s) can be associated with weight(s) representing likelihood(s) that the agent will perform respective intent(s). The computing device(s) can use one (or more) of the candidate trajectory(s) to determine a vehicle trajectory along which a vehicle is to drive.

An autonomous vehicle configured for active sensing may also be configured to weigh expected information gains from active-sensing actions against risk costs associated with the active-sensing actions. An example method involves: (a) receiving information from one or more sensors of an autonomous vehicle, (b) determining a risk-cost framework that indicates risk costs across a range of degrees to which an active-sensing action can be performed, wherein the active-sensing action comprises an action that is performable by the autonomous vehicle to potentially improve the information upon which at least one of the control processes for the autonomous vehicle is based, (c) determining an information-improvement expectation framework across the range of degrees to which the active-sensing action can be performed, and (d) applying the risk-cost framework and the information-improvement expectation framework to determine a degree to which the active-sensing action should be performed.

A vehicle control system includes: an automated driving controller that automatically controls at least one out of acceleration/deceleration or steering of a vehicle, and that performs automated driving control in one of a plurality of modes having different levels of automated driving; and a informing section that, in cases in which the automated driving mode transitions to one of the plurality of modes in accordance with a travel environment of the vehicle, predicts a timing at which the mode will transition, and informs the predicted timing.

Methods, devices, and systems of a sensor surface object detection system are provided. Output from sensors of a vehicle may be used to describe an environment around the vehicle. In the event that a sensor is obstructed by dirt, debris, or detritus the sensor may not sufficiently describe the environment for autonomous control operations. The sensor surface object detection system may receive output from the sensors of the vehicle to determine whether any of the sensors are obstructed. The determination may be made by comparing the output of one sensor to another, determining whether the output of a sensor is within a predetermined threshold, or comparing characteristics of multiple sensor outputs to one another. When a sensor is determined to be obstructed, the system may send a command to a cleaning system to automatically remove the obstruction.