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.

Disclosed herein is a vehicle control apparatus, vehicle control system and image sensor. The vehicle control apparatus includes a first sensor configured to be disposed on the vehicle to have a view to the outside of the vehicle and capture image data and a controller configured to include at least one processor to process the image data captured by the first sensor, wherein the controller recognizes a roundabout based on the processing result of the image data, sets a region of interest in front of the vehicle based on a state information of the roundabout obtained from the processing result of the image data, determines a target located in the region of interest based on information of the target location based on the processing result of the image data, and controls the vehicle based on the information of the target location in the region of interest. According to the embodiment of the disclosed invention, the vehicle may enter a roundabout safely.

A method includes the step of receiving traffic signal display information from a traffic control unit controlling a display of a traffic signal located near an intersection when a vehicle is driving toward the intersection. The traffic signal display information includes a current display state of the traffic signal and information indicating a remaining time for which the current display state of the traffic signal will continues. The method further includes the step of acquiring traffic signal recognition information when the vehicle is driving toward the intersection. The traffic signal recognition information is recognized by a traffic signal detector mounted on the vehicle and indicating a current display of the traffic signal. The method further includes the step of controlling driving of the vehicle when the vehicle enters the intersection based on the traffic signal display information and the traffic signal recognition information.

A system with control of vehicle driving through a roundabout includes: a position recognizer configured to recognize that a host vehicle is traveling around the roundabout; a front sensor disposed at a front of the host vehicle and configured to sense a vehicle that possibly enters the roundabout while the host vehicle is traveling around the roundabout; a rear sensor disposed at a rear of the host vehicle and configured to recognize a vehicle following the host vehicle while the host vehicle is traveling around the roundabout; a controller configured to calculate a possible entry time of the vehicle that possibly enters the roundabout, using information sensed by the rear sensor; and a communicator configured to provide the calculated possible entry time to the vehicle that possibly enters the roundabout.

Techniques for representing sensor data and predicted behavior of various objects in an environment are described herein. For example, an autonomous vehicle can represent prediction probabilities as an uncertainty model that may be used to detect potential collisions, define a safe operational zone or drivable area, and to make operational decisions in a computationally efficient manner. The uncertainty model may represent a probability that regions within the environment are occupied using a heat map type approach in which various intensities of the heat map represent a likelihood of a corresponding physical region being occupied at a given point in time.

A vehicle control apparatus selects an oncoming vehicle, based on the object information when the own vehicle turns right or left, sets the selected oncoming vehicle as a control target vehicle, and executes a collision avoidance control of avoiding a collision of an own vehicle with the control target vehicle when a predetermined execution condition is satisfied. The vehicle control apparatus selects at least one oncoming vehicle around the control target vehicle, sets the selected at least one oncoming vehicle as a surrounding vehicle, and changes the predetermined execution condition to a condition which becomes satisfied at a later timing when a first behavior condition that there is a predetermined behavior difference between a behavior of the control target vehicle and a behavior of the surrounding vehicle, is satisfied, compared with when the first behavior condition is not satisfied.

Techniques for representing sensor data and predicted behavior of various objects in an environment are described herein. For example, an autonomous vehicle can represent prediction probabilities as an uncertainty model that may be used to detect potential collisions, define a safe operational zone or drivable area, and to make operational decisions in a computationally efficient manner. The uncertainty model may represent a probability that regions within the environment are occupied using a heat map type approach in which various intensities of the heat map represent a likelihood of a corresponding physical region being occupied at a given point in time.

According to an aspect of an embodiment, operations may comprise accessing an HD map of a region comprising information describing an intersection of two or more roads and describing lanes of the two or more roads that intersect the intersection, automatically identifying constraints on the lanes at the intersection, automatically calculating, based on the constraints on the lanes at the intersection, lane connectivity for the intersection, displaying, on a user interface, the automatically calculated lane connectivity for the intersection, receiving, from a user through the user interface, confirmation that the automatically calculated lane connectivity for the intersection is an actual lane connectivity for the intersection, and adding the actual lane connectivity for the intersection to the information describing the intersection in the HD map.

This application relates to techniques for dynamically determining whether to engage an autonomous controller of a vehicle. A computing system may receive a request to engage the autonomous controller (e.g., autonomous mode) of the vehicle. In some examples, the request may be received from a simulation computing system configured to test an updated autonomous controller in a simulation. Based on a determination that conditions associated with engaging autonomy are satisfied, the computing system engages the autonomous controller. Based on a determination that conditions associated with engaging autonomy are not satisfied, the computing system disables the engagement of the autonomous controller such that the vehicle is controlled according to an initial operational mode (e.g., manual mode, semi-autonomous mode, previous version of the autonomous controller, etc.).

Disclosed is a method and apparatus with localization. The method includes determining a sensor-based reference position using a position sensor of the vehicle, determining an image-based reference position of the vehicle based on image information of the vehicle captured using a camera of the vehicle, setting an acceptance range for the image-based reference position based on a driving situation of the vehicle, and comparing an error level of the image-based reference position to the acceptance range and estimating a current position of the vehicle.