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 control system is provided. The control system may include a plurality of cameras to acquire a plurality of images of an area in a vicinity of a vehicle; and at least one processing device configured to: recognize a curve to be navigated based on map data and vehicle position information; determine an initial target velocity for the vehicle based on at least one characteristic of the curve as reflected in the map data; adjust a velocity of the vehicle to the initial target velocity; determine, based on the plurality of images, observed characteristics of the curve; determine an updated target velocity based on the observed characteristics of the curve; and adjust the velocity of the vehicle to the updated target velocity.

An apparatus for controlling a host vehicle may include: a processor configured to calculate a cut-in possibility in which a nearby vehicle cuts into a lane on which the host vehicle travels ahead of the host vehicle, to determine a plurality of cut-in steps of the calculated cut-in possibility, and to control operation of the host vehicle so as to perform an inter-vehicle distance control operation or to provide a warning to a user of the host vehicle based on a state of the user in each of the plurality of cut-in steps; and storage configured to store the calculated cut-in possibility.

A system for a vehicle is provided. The system may include a memory and at least one processor configured to: access a plurality of images of a forward-facing view from the vehicle, the plurality of images corresponding to image data obtained by a camera; determine from the images a first lane marking on a first side of a lane, the lane through which the vehicle can navigate, and a second lane marking on a second side of the lane opposite of the first side; navigate the vehicle autonomously relatively centered between the first and second lane markings; determine from the plurality of images that an object is on the first side or the second side of the lane, and the object beyond the first or second lane marking; and navigate the vehicle autonomously to travel over a driving path that is offset from a center of the lane.

In a host vehicle a threat number is determined for a target vehicle based on respective dimensions of the target and host vehicles, and a heading angle of the host vehicle. A host vehicle subsystem is actuated based on the threat number.

Aspects of the disclosure relate generally to detecting and avoiding blind spots of other vehicles when maneuvering an autonomous vehicle. Blind spots may include both areas adjacent to another vehicle in which the driver of that vehicle would be unable to identify another object as well as areas that a second driver in a second vehicle may be uncomfortable driving. In one example, a computer of the autonomous vehicle may identify objects that may be relevant for blind spot detecting and may determine the blind spots for these other vehicles. The computer may predict the future locations of the autonomous vehicle and the identified vehicles to determine whether the autonomous vehicle would drive in any of the determined blind spots. If so, the autonomous driving system may adjust its speed to avoid or limit the autonomous vehicle's time in any of the blind spots.

A system and method for navigating a vehicle automatically from a current location to a destination location without a human operator is disclosed. The method includes identifying a vehicle location using global positioning system (GPS) data regarding the vehicle. Also included is identifying that the vehicle location is near or at a parking location. Then, using mapping data defined for the parking location. The mapping data at least in part is used to find a path at the parking location to avoid a collision of the vehicle with at least one physical structure when the vehicle is automatically moved at the parking location. The method includes instructing the electronics of the vehicle to proceed with controlling the vehicle to automatically move from the current location to the destination location at the parking location. The electronics use as input at least part of the mapping data and sensor data collected from around the vehicle by at least two vehicle sensors. The path is configured to be updatable dynamically based on changes in the destination location or changes along the path. The destination location is a parking spot for the vehicle at the parking location.

A traffic signal recognition unit recognizes a traffic signal of a traffic signal machine to be next followed on the basis of outside information. A traffic participant recognition unit recognizes the motion of a traffic participant on the basis of the outside information. A prediction unit predicts a traffic signal to be followed next on the basis of the motion of traffic participant recognized by the traffic participant recognition unit. A comparison unit compares the traffic signal recognized by the traffic signal recognition unit with the traffic signal predicted by the prediction unit. An action planning unit makes an action plan of a host vehicle on the basis of the comparison result of the comparison unit. A control unit carries out prescribed control on the basis of the action plan.

Systems and method are provided for controlling a vehicle. In one embodiment, a method includes: receiving sensor data sensed from an environment associated with the vehicle; processing, by a processor, the sensor data to determine a plurality of objects within the environment of the vehicle; processing, by the processor, the sensor data to determine feature data associated with each of the plurality of objects, wherein the feature data includes current data of each object, history data of each object, and interaction data between each object and at least two other objects; processing, by the processor, the feature data associated with a first object of the plurality of objects with a model to determine a future position of the first object; and controlling, by the processor, the vehicle based on the future position.

A turn signal system for activating a turn signal of a vehicle includes an electronic control unit having a processor and a non-transitory computer readable memory including a machine-readable instruction set. The electronic control unit is communicatively coupled to one or more external vehicle environment sensors, a vehicle speed sensor, and a turn signal. The machine-readable instruction set causes the processor to determine a vehicle speed based on an output signal of the vehicle speed sensor, predict a vehicle turning maneuver based on one or more environment signals output by the one or more external vehicle environment sensors when the vehicle speed is below a threshold, and automatically activate the turn signal in response to predicting the vehicle turning maneuver.