Aspects of the disclosure relate to controlling a vehicle having an autonomous driving mode. For instance, that the vehicle is approaching a crosswalk may be determined. A set of segments may be identified for the crosswalk. A set of potential occluded pedestrians may be generated. Each potential occluded pedestrian of the set is assigned a speed characteristic and a segment. The segments of the set of potential occluded pedestrians may be updated over time using the assigned speed characteristics. Sensor data from a perception system of the vehicle is received, and one or more potential occluded pedestrians an having an updated assigned segment corresponding to a segment that is visible to a perception system of the vehicle may be removed from the set of potential occluded pedestrians. After the removing, the set may be used to control the vehicle in the autonomous driving mode.

Disclosed are systems, apparatuses, methods, and computer-readable media to autonomous driving vehicles and, in particular, for tracking objects in an environment that an autonomous vehicle (AV) is navigating. A method includes receiving environment data from at least one sensor in an AV control system mounted to the AV, the environment data including online tracking data that identifies at least one object within the environment data that is recorded at drive time; annotating the at least one object from the environment data that are incorrectly identified by the AV control system; executing an offline tracking engine to generate offline tracking data that tracks the objects over time in the environment data; and identifying safety gaps between the online tracking data and the offline tracking data.

An autonomous vehicle uses machine learning based models such as neural networks to predict hidden context attributes associated with traffic entities. The hidden context represents behavior of the traffic entities in the traffic. The machine learning based model is configured to receive a video frame as input and output likelihoods of receiving user responses having particular ordinal values. The system uses a loss function based on cumulative histogram of user responses corresponding to various ordinal values. The system identifies user responses that are unlikely to be valid user responses to generate training data for training the machine learning mode. The system identifies invalid user responses based on response time of the user responses.

A driving assist system assists driving of a vehicle. A deceleration target includes at least one of a preceding vehicle, a mandatory stop line, a mandatory stop sign, a traffic signal, and a stop line before the traffic signal that exist ahead of the vehicle. A risk factor includes at least one of a pedestrian, a bicycle, a motorcycle, an oncoming vehicle, and a parked vehicle that exist ahead of the vehicle. The driving assist system executes: deceleration assist control that automatically decelerates the vehicle before the deceleration target; and risk avoidance control that automatically performs at least one of steering and deceleration of the vehicle so as to avoid the risk factor. When both the deceleration assist control and the risk avoidance control operate concurrently, the driving assist system notifies a driver of the vehicle of not the deceleration target but the risk factor.

The present invention refers to a method for providing a multi-lane scenario driving support for an ego vehicle (10) in a traffic situation. Traffic surroundings are measured by an environment sensor system (14), whereby the traffic surroundings include data about traffic and free space within an ego lane (16) of the ego vehicle (10) and at least an adjacent lane (12a, 12b), and data about front proximity area (18) and rear proximity area (20) of the ego vehicle (10). A decision device (22) evaluates the measured traffic surroundings and decides a driving operation to be executed by the ego vehicle (10) based on at least one strategy. In the decision device (22) a cost function is used for choosing one of at least six strategies, the cost function being based on at least a core priority, whereby the core priority is to avoid collision of the ego vehicle (10) and not cause collision of the ego vehicle (10) with a third party vehicle (24. The decision device (22) by means of the cost function chooses one of at least the following six strategies: braking in the ego lane (16), to combine braking and steering within the ego lane (16) of the ego vehicle (10), steering within the ego lane (16) of the ego vehicle (10) to avoid an obstacle, to full-brake in the ego lane (16) of the ego vehicle (10), to combine braking and steering towards or when entering temporarily an adjacent lane (12a, 12b) and steering towards or when entering temporarily an adjacent lane (12a, 12b).

A method for generating at least one school zone indicator, the method may include receiving by a vehicle computerized system, school zone indicators, wherein the school zone indicators are indicative of school zone elements; obtaining sensed information regarding an environment of the vehicle; processing the sensed information, wherein the processing comprises searching for one or more school zone indicators of the school zone indicators; wherein the school zone element is selected out of (i) a school zone object and (ii) a school zone situation; autonomously determining, when finding at least one of the one or more school zone identifiers, that the vehicle is driving towards a school zone or is within the school zone; and generating an alert when determining that the vehicle is driving towards the school zone or is within the school zone.

Provided is a vehicle control device which, when traffic participants are waiting in the vicinity of a railroad crossing for a train to pass, appropriately controls driving of a vehicle about to pass through the railroad crossing. Entry of the vehicle into the railroad crossing is restrained until a waiting time elapses since when the railroad crossing transitioned from a passage blocking state to a passage allowing state, the waiting time being set in accordance with the kind or the number of the traffic participants present in the vicinity of the railroad crossing. When the waiting time has elapsed, the vehicle is caused to enter the railroad crossing and pass (through) the railroad crossing.

A vehicular display device includes at least one display panel arranged on a vehicle body of a vehicle and configured to display an image, and a display control unit configured to control display of the image. The display panel includes a movable portion provided on the vehicle body, and the display control unit includes an image control unit configured to control a display form of an image when the movable portion is operated.

A vehicle cruise control device includes: an arithmetic circuitry and a device circuitry that controls actuation of traveling devices mounted in a vehicle. The arithmetic circuitry is configured to recognize a vehicle external environment; set a route to be traveled by the vehicle; determine a target motion of the vehicle to follow the set route; and generate an image to be displayed for driving assistance, by using an image taken by the camera and information on the recognized vehicle external environment. The control circuitry is configured to control actuation of one or more traveling devices mounted in the vehicle, based on the target motion determined.

The present disclosure provides autonomous vehicle systems and methods that include or otherwise leverage a machine-learned yield model. In particular, the machine-learned yield model can be trained or otherwise configured to receive and process feature data descriptive of objects perceived by the autonomous vehicle and/or the surrounding environment and, in response to receipt of the feature data, provide yield decisions for the autonomous vehicle relative to the objects. For example, a yield decision for a first object can describe a yield behavior for the autonomous vehicle relative to the first object (e.g., yield to the first object or do not yield to the first object). Example objects include traffic signals, additional vehicles, or other objects. The motion of the autonomous vehicle can be controlled in accordance with the yield decisions provided by the machine-learned yield model.