Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for predicting future trajectories for an agent in an environment. A system obtains scene context data characterizing the environment. The scene context data includes data that characterizes a trajectory of an agent in a vicinity of a vehicle in an. environment up to a current time point. The system identifies a plurality of initial target locations in the environment. The system further generates, for each of a plurality of target locations that each corresponds to one of the initial target locations, a respective predicted likelihood score that represents a likelihood that the target location will be an intended final location for a future trajectory of the agent starting from the current time point. For each target location in a first subset of the target locations, the system generates a predicted future trajectory for the agent that is a prediction of the future trajectory of the agent given that the target location is the intended final location for the future trajectory. The system further selects, as likely future trajectories of the agent starting from the current time point, one or more of the predicted future trajectories.

Systems, apparatus and methods implemented in algorithms, hardware, software, firmware, logic, or circuitry may be configured to process data and sensory input to determine whether an object external to an autonomous vehicle (e.g., another vehicle, a pedestrian, road debris, a bicyclist, etc.) may be a potential collision threat to the autonomous vehicle. The autonomous vehicle may be configured to implement interior active safety systems to protect passengers of the autonomous vehicle during a collision with an object or during evasive maneuvers by the autonomous vehicle, for example. The interior active safety systems may be configured to provide passengers with notice of an impending collision and/or emergency maneuvers by the vehicle by tensioning seat belts prior to executing an evasive maneuver and/or prior to a predicted point of collision.

Technical solutions are described for generating a pedestrian detection warning in a vehicle. An example method includes constructing, by a vehicle controller, a pedestrian zone based on pedestrian information that is received from a traffic controller. The method further includes computing, by the vehicle controller, a vehicle trajectory that predicts a path for the vehicle. The method further includes determining, by the vehicle controller, a minimal distance between the pedestrian zone and the vehicle trajectory. The method further includes predicting, by the vehicle controller, a time to collision by computing a time for the vehicle to reach a location corresponding to the minimal distance along the vehicle trajectory. The method further includes in response to the time to collision being below a threshold, generating, by the vehicle controller, a warning for an operator of the vehicle.

The present radio system transmits an electromagnetic signal to nearby devices requesting the device respond. The radio system also receives responses to the electromagnetic signal from the nearby devices. Based on the radio technology used, the signaling of the transmitted electromagnetic signal may be varied. For example, the transmitted electromagnetic signal may be a Bluetooth, 802.11, or other radio signal. A device that received the signal from the radio unit may transmit a response signal with the same radio technology. However, in some instances, the radio technology used for communication may operate on several radio (e.g., frequency) channels. Both the transmitter and receiver must operate on the same channel at the same time in order to communicate. Thus, it may be desirable to transmit the electromagnetic signal on more than one channel at the same time, in order to increase the chances that a nearby device responds.

A mode switch controller controls mode switching for switching a drive mode of a vehicle between a manual drive mode and an automatic drive mode. The mode switch controller includes an obtaining unit and a calculation unit. The obtaining unit obtains sensing data representing a surrounding situation in a switching section defined for the mode switching from a sensor for monitoring surroundings of the vehicle. The calculation unit calculates a recommended mode switching position at which the mode switching is recommended in the switching section based on the sensing data.

Provided is a vehicle control apparatus (100) which includes a recognition unit (130) configured to recognize a surrounding situation of a vehicle, and driving control units (140 and 160) configured to automatically control acceleration or deceleration and steering of the vehicle on the basis of a surrounding situation recognized by the recognition unit, in which, in a case that a stop position of the vehicle is recognized in the traveling direction of the vehicle by the recognition unit, and a traffic participant proceeding at a speed lower than the speed of the vehicle in the traveling direction is recognized in front of the stop position, the driving control unit determines whether the traffic participant catches up with the vehicle before the vehicle reaches the stop position, and determines to cause the vehicle to reach further ahead of the traffic participant in the traveling direction on the basis of a result of the determination.

A system for operating an automated vehicle in a crowd of pedestrians includes an object-detector, optionally, a signal detector, and a controller. The object-detector detects pedestrians proximate to a host-vehicle. The signal-detector detects a signal-state displayed by a traffic-signal that displays a stop-state that indicates when the host-vehicle should stop so the pedestrians can cross in front of the host-vehicle, and displays a go-state that indicates when the pedestrians should stop passing in front of the host-vehicle so that the host-vehicle can go forward. The controller is in control of movement of the host-vehicle and in communication with the object-detector and the signal-detector. The controller operates the host-vehicle to stop the host-vehicle when the stop-state is displayed, and operates the host-vehicle to creep-forward after a wait-interval after the traffic-signal changes to the go-state when the pedestrians fail to stop passing in front of the host-vehicle.

This system of the present invention uses computer graphics techniques to generate a virtual sensor image. The computer graphics include: a means for creating a scenario of an object present in the image; a means for performing modeling for each object in the computer graphics on the basis of a scenario; a means for performing shading for each model of the modeling result; a means for outputting only one component of a shaded image; and a means for generating a depth image on the basis of three-dimensional profile information for each object in the computer graphics.

A speed control method for controlling the speed of an autonomous vehicle provided with at least one autonomous driving module and one geolocation module, the vehicle being capable of following a route, which is predefined and segmented according to at least one segmentation comprising of a plurality of segments, each associated with: an interval of geolocation data; and a set of values for nominal maximum travel speed of the autonomous vehicle, each speed value being associated with a distinct time slot; the method comprising: the acquisition, from the on-board geolocation module, of an instantaneous geolocation data item of the autonomous vehicle associated with a time instant; as a function of the instantaneous geo-location data item and the time instant, the determination, of the segment currently being traversed and/or to be traversed, and of the associated nominal maximum speed value.

Among other things, a model is maintained of an environment of a vehicle. A hypothetical object in the environment that cannot be perceived by sensors of the vehicle is included in the model.