Provided is a technique for controlling a vehicle according to a group type for a target group moving object. Provided are: a group detection unit 102 that detects a group based on signals from sensors 101; an environment information collection unit 105 that collects information on a surrounding environment of a host vehicle; a group type determination unit 103 that determines a group type based on a feature of the group detected by the group detection unit 102 and environment information collected by the environment information collection unit 105; and a risk level determination unit 104 that determines a risk level based on the group type determined by the group type determination unit 103, a speed of the host vehicle and a distance to a group moving object. A warning or vehicle control is performed based on the risk level determined by the risk level determination unit 104.

Among other things, a command is received expressing an objective for operation of a vehicle within a denominated travel segment of a planned travel route. The objective spans a time series of (for example, is expressed at a higher or more abstract level than) control inputs that are to be delivered to one or more of the brake, accelerator, steering, or other operational actuator of the vehicle. The command is expressed to cause operation of the vehicle along a selected man-made travel structure of the denominated travel segment. A feasible manner of operation of the vehicle is determined to effect the command. A succession of control inputs is generated to one or more of the brake, accelerator, steering or other operational actuator of the vehicle in accordance with the determined feasible manner of operation.

Systems and methods are provided for navigating based on sensed brake light patterns. In one implementation, a navigation system for a host vehicle may include at least one processing device. The at least one processing device may be programmed to receive, from a camera, a plurality of images representative of an environment ahead of the host vehicle; analyze the plurality of images to identify at least one target vehicle in the environment ahead of the host vehicle; identify, based on analysis of the plurality of images, at least one brake light associated with the target vehicle and at least one characteristic associated with changes in an illumination state of the at least one brake light; and cause a navigational change for the host vehicle based on the identified at least one characteristic associated with the changes in the illumination state of the at least one brake light.

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.

Techniques to predict object behavior in an environment are discussed herein. For example, such techniques may include inputting data into a model and receiving an output from the model representing a discretized representation. The discretized representation may be associated with a probability of an object reaching a location in the environment at a future time. A vehicle computing system may determine a trajectory and a weight associated with the trajectory using the discretized representation and the probability. A vehicle, such as an autonomous vehicle, can be controlled to traverse an environment based on the trajectory and the weight output by the vehicle computing system.

An alarm device configured to generate an alarm to a driver inside a vehicle, includes processing circuitry configured to generate delay time information based on a first reference level and at least a portion of sound source signals that are generated by a plurality of microphones in the vehicle based on a sound generated from outside of the vehicle. The processing circuitry is further configured to generate position parameters based on a second reference level and at least a portion of the delay time information. The processing circuitry is further configured to generate, based on the position parameters, candidate position information representing candidate positions on which the sound source is expected to be located, and generate final position information based on a third reference level and the candidate position information.

Techniques are discussed for determining predicted trajectories based on a top-down representation of an environment. Sensors of a first vehicle can capture sensor data of an environment, which may include agent(s) separate from the first vehicle, such as a second vehicle or a pedestrian. A multi-channel image representing a top-down view of the agent(s) and the environment and comprising semantic information can be generated based on the sensor data. Semantic information may include a bounding box and velocity information associated with the agent, map data, and other semantic information. Multiple images can be generated representing the environment over time. The image(s) can be input into a prediction system configured to output a heat map comprising prediction probabilities associated with possible locations of the agent in the future. A predicted trajectory can be generated based on the prediction probabilities and output to control an operation of the first vehicle.

Aspects of the disclosure relate to an autonomous vehicle that may detect other nearby vehicles and designate stationary vehicles as being in one of a short-term stationary state or a long-term stationary state. This determination may be made based on various indicia, including visible indicia displayed by the detected vehicle and traffic control factors relating to the detected vehicle. For example, the autonomous vehicle may identify a detected vehicle as being in a long-term stationary state based on detection of hazard lights being displayed by the detected vehicle, as well as the absence of brake lights being displayed by the detected vehicle. The autonomous vehicle may then base its control strategy on the stationary state of the detected vehicle.

A method initiates a reaction of a first vehicle to a person in the environment of a second vehicle. The person is on a road on which the first vehicle is travelling and the second vehicle is detected. Measurement data determined by at least one sensor unit are received by a control unit. The control unit carries out a classification and registers the evaluated data as a person and as a second vehicle. Motion vectors of the person are determined and the expected movement of the person is calculated. A position and width of the vehicle doors of the second vehicle are determined or estimated on the basis of the measurement data. A probability of the person opening a vehicle door is calculated. A reaction of the first vehicle is initiated by the control unit depending on the calculated probability.

An autonomous driving control device is capable of starting an autonomous driving control without an operation of a driver and reducing a possibility that the driver can not start manual driving. An autonomous driving control is switched to manual driving when a determination section determines that the amount of operation by the driver is equal to or greater than a first threshold, before a predetermined time elapses since the autonomous driving control is automatically started. An autonomous driving control is switched to a manual driving when the determination section determines that the amount of operation by the driver is equal to or greater than a second threshold that is greater than the first threshold, after the predetermined time elapses.