A method for predicting a direction of movement of a target object, a method for training a neural network, a smart vehicle control method, a device, an electronic apparatus, a computer readable storage medium, and a computer program. The method for predicting a direction of movement of a target object comprises: acquiring an apparent orientation of a target object in an image captured by a camera device, and acquiring a relative position relationship of the target object in the image and the camera device in three-dimensional space (S100); and determining, according to the apparent orientation of the target object and the relative position relationship, a direction of movement of the target object relative to a traveling direction of the camera device (S110).

Systems, methods, and non-transitory computer-readable media can determine sensor data captured by at least one sensor of a vehicle while navigating an environment over a period of time. Information describing one or more agents associated with the environment during the period of time can be determined based at least in part on the captured sensor data. A schema-based encoding describing the environment during the period of time can be generated based at least in part on the determined information and a scenario schema, wherein the schema-based encoding provides a structured representation of the environment during the period of time.

A computer-implemented method for controlling a vehicle. The method includes: data of a digital road map are read in, zones are determined for the digital road map, possible sequences of drives along a road of the digital road map are ascertained as a function of the determined zones, a behavior of the vehicle or of a vehicle system of the vehicle is ascertained in a simulation for at least one of the possible sequences, and the vehicle is controlled in accordance with one of the possible sequences as a function of a comparison of the ascertained behavior with at least one predetermined requirement.

A machine-learned model is trained using human driving data to determine a desired vehicle speed based from a set of driving-environment characteristics. An autonomous-vehicle control system obtains, from cameras, sensors, services, and data sources, a variety of sensor data. The sensor data is used to determine a set of characteristics for the driving-environment for the autonomous vehicle. Using the machine-learned model, the autonomous-vehicle control system determines a human-like desired speed for the autonomous vehicle based at least in part on the determined characteristics of the driving-environment.

A vehicle control device includes: a recognizer configured to recognize a surrounding situation of a vehicle including a predetermined object located near the vehicle; and a driving controller configure to control steering and a speed of the vehicle. The driving controller controls the speed of the vehicle such that the vehicle passes the predetermined object at a greater speed when the vehicle passes the predetermined object which is located ahead in a traveling direction of the vehicle and is moving in an opposite direction to the traveling direction of the vehicle than a speed when the vehicle passes the predetermined object which is located ahead in the traveling direction of the vehicle and is moving in the same direction as the traveling direction of the vehicle.

Low variance detection training is described herein. In an example, annotated data can be determined based on sensor data received from a sensor associated with a vehicle. The annotated data can comprise an annotated low variance region and/or an annotated high variance region. The sensor data can be input into a model, and the model can determine an output comprising a high variance output and a low variance output. In an example, a difference between the annotated data and the output can be determined and one or more parameters associated with the model can be altered based at least in part on the difference. The model can be transmitted to a vehicle configured to be controlled by another output of the model.

The present disclosure relates to systems and methods for host vehicle navigation. In one implementation, a navigation system for a host vehicle may include at least one processing device programmed to receive, from a camera, a plurality of images representative of an environment of the host vehicle; receive, from a camera, a plurality of images representative of an environment of the host vehicle; analyze the images to identify a target vehicle in the environment of the host vehicle; cause a navigational change of the host vehicle to signal to the target vehicle an intent of the host vehicle to make a subsequent navigational maneuver; analyze the images to detect a change in a navigational state of the target vehicle; determine a navigational action for the host vehicle; and cause an adjustment of a navigational actuator of the host vehicle in response to the determined navigational action for the host vehicle.

A radar system includes a controller that receives radar data from a first radar sensor and a second radar sensor mounted to a vehicle. The controller determines, based on fields of view of both the first radar sensor and the second radar sensor, reduced fields of view that overlay a travel path of the vehicle. The reduced fields of view are enabled by reflecting portions of transmitted radar signals away from both the first radar sensor and the second radar sensor, thereby inhibiting detections of objects outside of the travel path of the vehicle. The controller determines whether a stationary object is detected by both the first radar sensor and the second radar sensor in the reduced fields of view while the vehicle is stationary.

A trajectory setting device that sets a trajectory of a host vehicle includes a first path generation unit configured to generate a first path by assuming all obstacles around the host vehicle to be stationary obstacles, a second path generation unit configured to generate a second path when the moving obstacle is assumed to move independently, a third path generation unit configured to generate a third path when the moving obstacle is assumed to move while interacting with at least one of the other obstacles or the host vehicle, a reliability calculation unit configured to calculate reliability of the second path and reliability of the third path, and a trajectory setting unit configured to set the trajectory for traveling from the first path, the second path, and the third path based on the reliability of the second path and the reliability of the third path.

An autonomous driving vehicle includes a user detection monitoring device and a start control device. The user detection monitoring device detects a user who got out of the autonomous driving vehicle after the autonomous driving vehicle stopped at a destination as an alighted user and monitors the alighted user. The start control device maintains a stopped state of the autonomous driving vehicle after the alighted user was detected until a start condition is satisfied and, if the start condition is satisfied, permits a start of the autonomous driving vehicle. The start condition is one of a condition indicating that the alighted user at least moves out of a movement determination area around the autonomous driving vehicle and a condition indicating that the alighted user is present in the movement determination area but remains at the same position for a certain period of time or longer.