A system for operating a vehicle includes an object-detector, and operator-monitor, and a controller. The object-detector is used to detect one or more targets proximate to a host-vehicle, said host-vehicle operable in an autonomous-mode and a manual-mode. The operator-monitor is used to detect a gaze-direction of an operator of the host-vehicle. The controller-circuit is in communication with the object-detector and the operator-monitor. The controller-circuit is configured to determine a classification of each target detected by the object-detector. The classification includes a primary-target and an ignored-target. The controller-circuit is further configured to determine that a hand-over of operation of the host-vehicle from the autonomous-mode to the manual-mode is recommended, perform a verification that the operator has gazed at each primary-target more recently than a primary-time, and in response to the verification, execute the hand-over.

An embodiment for dynamically creating a vehicle fence is provided. The embodiment may include receiving GPS data from one or more vehicles and a real-time video feed of one or more intersections along a first roadway. The embodiment may also include identifying a number of autonomous vehicles and one or more routes of the autonomous vehicles traveling on the first roadway. The embodiment may further include in response to determining an emergency vehicle is traveling on the first roadway, identifying a route and speed of the emergency vehicle. The embodiment may also include estimating a width of a second roadway intersecting the first roadway at a nearest intersection. The embodiment may further include identifying a moving direction of one or more objects along the second roadway. The embodiment may also include deploying a required number of autonomous vehicles to block the one or more objects from entering the nearest intersection.

A Light Detection And Ranging (LiDAR)-based object detection apparatus comprising a LiDAR sensor configured to obtain a point cloud, and a processor configured to detect at least one object of interest from the point cloud, wherein the processor is configured to perform determining representative points from LiDAR points corresponding to the object among the point cloud, determining outer points among the representative points, the outer points defining an outline of the object, and determining a confidence score for each of segments connecting at least two of the outer points.

The present disclosure provides an electronic control device and a vehicle control system capable of coping with an increase in communication load, caused by an increase in the number of objects to be monitored, and an increase in processing load at the time of acquiring surrounding monitoring information. An electronic control device 110 according to the present disclosure is mounted on a vehicle V and includes a scene prediction unit 111 and a filtering unit 112. The scene prediction unit 111 predicts driving scenes to be encountered by the vehicle V based on position information of the vehicle V, map information around the vehicle V, and a travel route of the vehicle V. The filtering unit 112 derives a risk index for each of recognition results of a plurality of objects around the vehicle V based on the driving scenes, the recognition results of the objects, and risk information in which the risk index is defined for each of the driving scenes and each of types of the recognition results of the objects. Furthermore, the filtering unit 112 selectively passes the recognition result of the object having the risk index exceeding the prescribed value.

A method and an apparatus for controlling an autonomous vehicle are provided according to the embodiments of the disclosure. The method includes: sending, in response to determining that a pedestrian is in a first target area, behavior prompt information representing prompting the pedestrian to make a corresponding behavior; determining whether a deceleration condition matching the behavior prompt information is satisfied based on acquired behavior information of the pedestrian; and sending control information for reducing a moving speed of the autonomous vehicle, in response to determining that the deceleration condition is satisfied and determining that a speed of the autonomous vehicle is greater than a preset deceleration threshold. According to the embodiments, deceleration control of the autonomous vehicle is achieved based on the response of the pedestrian to the behavior prompt information.

A system and a method for autonomous decisioning and operation by an autonomous agent includes: collecting decisioning data including: collecting a first stream of data includes observation data obtained by onboard sensors of the autonomous agent, wherein each of the onboard sensors is physically arranged on the autonomous agent; collecting a second stream of data includes observation data obtained by offboard infrastructure devices, the offboard infrastructure devices being arranged geographically remote from and in an operating environment of the autonomous agent; implementing a decisioning data buffer that includes the first stream of data from the onboard sensors and the second stream of data from the offboard sensors; generating current state data; generating/estimating intent data for each of one or more agents within the operating environment of the autonomous agent; identifying a plurality of candidate behavioral policies; and selecting and executing at least one of the plurality of candidate behavioral policies.

An autonomous vehicle and method are provided. The autonomous vehicle includes a memory to store a three-dimensional (3D) rendering of an environment surrounding the autonomous vehicle; one or more sensors of the autonomous vehicle to collect real-time data describing the environment surrounding the autonomous vehicle; and a processor to (i) revise the 3D rendering according to the real-time data, and (ii) navigate the autonomous vehicle according to the revised 3D rendering.

A vehicle information provision device includes a travel state detection unit, a surroundings situation detection unit, a potential hazard detection unit detecting a potential hazard based on the situation detected by the surroundings situation detection unit, a driver state detection unit detecting the driver state during self-driving of a vehicle; a driver state determination unit configured to determine whether or not the driver is observing the situation in the vehicle surroundings based on the state of the driver detected by the driver state detection unit, and an information control unit that provides information to the driver regarding the potential hazard in a case in which the driver is observing the situation in the vehicle surroundings, and restricts provision of information to the driver in a case in which the driver is not observing the situation in the vehicle surroundings during self-driving of the vehicle.

Systems and methods are provided for navigating an autonomous vehicle using reinforcement learning techniques. 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; analyze the plurality of images to identify a navigational state associated with the host vehicle; provide the navigational state to a trained navigational system; receive, from the trained navigational system, a desired navigational action for execution by the host vehicle in response to the identified navigational state; analyze the desired navigational action relative to one or more predefined navigational constraints; determine an actual navigational action for the host vehicle, wherein the actual navigational action includes at least one modification of the desired navigational action determined based on the one or more predefined navigational constraints; and cause at least one adjustment of a navigational actuator of the host vehicle in response to the determined actual navigational action for the host vehicle.

A collision-avoidance system for use with an autonomous-capable vehicle can continuously receive image frames captured of the roadway to determine drivable space in a forward direction of the vehicle. The system can determine, for each image frame, whether individual regions of the image frame depict drivable space. The system can do so using machine-learned image recognition algorithms such as convolutional neural networks generated using extensive training data. Using such techniques, the system can label regions of the image frames as corresponding to drivable space or non-drivable space. By analyzing the labeled image frames, the system can determine whether the vehicle is likely to impact a region of non-drivable space. And, in response to such a determination, the system can generate control signals that override other control systems or human operator input to control the brakes, the steering, or other sub-systems of the vehicle to avoid the collision.