A drive assistant (700) executes a drive assist function that is a function of a drive assist system. A first electronic control apparatus (401) has a first sensor (501). A second electronic control apparatus (402) has a second sensor (502). The first electronic control apparatus (401) is connected to the drive assistant (700) via a main network (10). The second electronic control apparatus (402) is connected to the first electronic control apparatus (401) via a sub-network (20) having no connection to the drive assistant (700). The first electronic control apparatus (401) outputs, to the main network (10), control assist information generated on the basis of first sensing information acquired by the first sensor (501) and second sensing information acquired by the second sensor (502).

Techniques for determining to modify a trajectory based on an object are discussed herein. A vehicle can determine a drivable area of an environment, capture sensor data representing an object in the environment, and perform a spot check to determine whether or not to modify a trajectory. Such a spot check may include processing to incorporate an actual or predicted extent of the object into the drivable area to modify the drivable area. A distance between a reference trajectory and the object can be determined at discrete points along the reference trajectory, and based on a cost, distance, or intersection associated with the trajectory and the modified area, the vehicle can modify its trajectory. One trajectory modification includes following, which may include varying a longitudinal control of the vehicle, for example, to maintain a relative distance and velocity between the vehicle and the object.

A vehicle for collision avoidance assistance may include: a camera to obtain an image of an object behind the vehicle, and obtain coordinates of a feature point spaced apart from the object, a controller, and a notification unit to output a collision warning. In particular, the controller sets an estimated value of a vector indicating a state of the vehicle based on coordinates of the vehicle, coordinates of the object, and the coordinates of the feature point, determine a predicted value of the estimated value of the vector based on a result of differentiating the estimated value of the vector with respect to time, correct the predicted value, determine the estimated value of the vector, and calculate a distance between the camera and the object to transmit a collision warning signal to the notification unit.

Techniques are discussed for controlling a vehicle, such as an autonomous vehicle, based on occluded areas in an environment. An occluded area can represent areas where sensors of the vehicle are unable to sense portions of the environment due to obstruction by another object. An occlusion grid representing the occluded area can be stored as map data or can be dynamically generated. An occlusion grid can include occlusion fields, which represent discrete two- or three-dimensional areas of driveable environment. An occlusion field can indicate an occlusion state and an occupancy state, determined using LIDAR data and/or image data captured by the vehicle. An occupancy state of an occlusion field can be determined by ray casting LIDAR data or by projecting an occlusion field into segmented image data. The vehicle can be controlled to traverse the environment when a sufficient portion of the occlusion grid is visible and unoccupied.

System and method to autonomously operate a vehicle during travel are disclosed. Exemplary implementations may: generate, by sensors, output signals conveying contextual information and operational information, the contextual information characterizing a contextual environment surrounding the vehicle; obtain a current set of operational regulations; implement the current set of operational regulations to operate the vehicle autonomously; assess the validity of the current set of operational regulations within the updated contextual environment; responsive to the determining that the current set of operational regulations are valid within the updated contextual environment, return to implementation; responsive to the determining that the current set of operational regulations are invalid within the updated contextual environment, generate an updated set of operational regulations that are valid within the updated contextual environment; and responsive to generation, replace the current set of operational regulations with the updated set of operational regulations.

A system for navigating an autonomous vehicle using reinforcement learning techniques is provided. The system includes at least one processing device programmed to: receive, from a camera, a plurality of images representative of an environment of the host vehicle; analyze the plurality of images to identify a present navigational state associated with the host vehicle; select a second potential navigational action based on a determination that an expected reward associated with a fourth indicator is greater than an expected reward associated with a second indicator.

A driving assist apparatus includes at least one electronic control unit. The at least one electronic control unit is configured to: detect a first object and assist a collision avoidance between a vehicle and the first object existing in a traveling direction of the vehicle; determine whether a first condition that a predetermined number or more of physical objects are detected is satisfied; determine whether a second condition that the vehicle travels at a predetermined speed or lower is satisfied; determine whether a third condition that a predetermined number or more of turning operations of a steering wheel of the vehicle are performed in a predetermined time is satisfied; and determine that a road on which the vehicle is traveling is a crowded environment road, based on a determination that all of the first to third conditions are satisfied.

A system for notifying emergency services of a vehicular crash may (i) receive sensor data of a vehicular crash from at least one mobile device associated with a user; (ii) generate a scenario model of the vehicular crash based upon the received sensor data; (iii) store the scenario model; and/or (iv) transmit a message to one or more emergency services based upon the scenario model. As a result, the speed and accuracy of deploying emergency services to the vehicular crash location is increased. The system may also utilize vehicle occupant positional data, and internal and external sensor data to detect potential imminent vehicle collisions, take corrective actions, automatically engage autonomous or semi-autonomous vehicle features, and/or generate virtual reconstructions of the vehicle collision.

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.

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.