Provided are methods for scalable and realistic camera blockage dataset generation, which can include generating synthetic images depicting a blockage on or near an imaging sensor. The synthetic images may be created by combining one or more chroma key-extracted partial blockage image with one or more background images, the combination of which can provide a scalable blockage dataset. Metadata for each synthetic image can be generated along with the synthetic image, by annotating the portion of the synthetic image represented by the chroma key-extracted partial blockage image as constituting blockage. The synthetic images can be used to increase the accuracy of machine learning models trained to identify blockage by increasing the volume of data available for such training.

The present disclosure relates to an apparatus and method for controlling an autonomous vehicle to allow an autonomous vehicle to safely pass through a road according to a driver's choice when the width of the road is narrow. The apparatus includes a sensor for acquiring information data of obstacles and vehicles in front of and on a side of a host vehicle, a signal processor for outputting data with respect to positions and media of obstacles and a determination signal representing presence or absence of a vehicle on a driving path, a controller for determining whether driving is possible by analyzing information acquired by the sensor and outputting a control signal corresponding to a selection signal of the driver, an interface for displaying an image processed by the signal processor, and an autonomous driving function unit for performing autonomous driving according to the control signal.

A device may receive emergency data, traffic data, network performance data, crime data, and gunshot data associated with a geographical area and may identify a location within the geographical area based on the emergency data, the traffic data, the network performance data, the crime data, and the gunshot data. The device may determine, based on the emergency data, the traffic data, the network performance data, the crime data, and the gunshot data for the location, a risk level for the location and may identify an autonomous vehicle based on the risk level, the traffic data, and the network performance data for the location. The device may determine a route for the autonomous vehicle to the location based on the traffic data and the network performance data for the location, and may perform actions based on the autonomous vehicle and the route.

Systems and methods for determining precise pick-up locations for passengers who have requested autonomous vehicle rides. In particular, systems and methods are provided for using wireless signals to determine user location. In some examples, wireless ranging technology, such as Ultra Wide Band (UWB), is used to determine the user location. Wireless transceivers are used to determine a mobile device's range, and range information from multiple transceivers is used to determine the mobile's device's position. In some examples, triangulation is used to determine user location, such as triangulation between one or more wireless transceivers and the mobile device. In various examples, wireless transceivers are installed on autonomous vehicles, and in some examples, wireless transceivers are installed in various static locations (e.g., on buildings, lamp posts, or other structures.

A test system includes a master electronic control module (ECM) configured to receive user input for performing a test action. The master ECM determines one or more subsystem ECMs associated with the requested test action and a sequence of operations to be controlled by the subsystem ECMs to perform the requested test action. The master ECM provides instructions to the subsystem ECMs to perform the operations, along with parameters for those operations. The master ECM may determine whether a test action is appropriate to perform, based on sensor data, before instructing subsystem ECMs to perform the operations of the test action.

The offline map generation process may collect multiple point cloud data of the same area. A perception algorithm may operate on the point cloud data to detect static objects, which may be fixed road features that do not change among the point cloud data, allowing the perception algorithm to more accurately detect the static objects. During online operation of the ADV through the area, the ADV may trim regions-of-interest (ROI) of the area to exclude the predefined static objects. The perception algorithm may execute the sensor data of the ROI in real-time to detect objects in the ROI. The may be added back to the output of the perception algorithm to complete the perception output.

Devices, systems, and methods for a vehicular safety system in autonomous vehicles are described. An example method for safely controlling a vehicle includes selecting, based on a first control command from a first vehicle control unit, an operating mode of the vehicle, and transmitting, based on the selecting, the operating mode to an autonomous driving system, wherein the first control command is generated based on input from a first plurality of sensors, and wherein the operating mode corresponds to one of (a) a default operating mode, (b) a minimal risk condition mode of a first type that configures the vehicle to pull over to a nearest pre-designated safety location, (c) a minimal risk condition mode of a second type that configures the vehicle to immediately stop in a current lane, or (d) a minimal risk condition mode of a third type that configures the vehicle to come to a gentle stop.

A distance measuring method and device using image tracking for autonomous driving are proposed. The distance measuring method using image tracking for autonomous driving performed in a computing device includes recognizing a grid matching part marked on a road photographed by a camera; generating a virtual grid applied to the road using the grid matching part; and calculating a distance to a target object using the virtual grid.

A vehicle includes: an input configured to receive a destination; a display; a driver assistance system configured to control a behavior of the vehicle based on surrounding environment information; and a controller configured to control the display to display a driving route. The controller may be configured to determine, when a distance between a branch point on the driving route and the vehicle reaches a first distance, a possibility that the vehicle deviates from the driving route based on GPS information, vehicle speed information, and the surrounding environment information, and search for, when the possibility is greater than or equal to a preset threshold, a deviation route for reaching the destination based on the deviated direction and control the display to display the deviation route until the distance between the branch point on the driving route and the vehicle reaches a second distance.

System, methods, and other embodiments described herein relate to training a depth model for joint depth completion and prediction. In one arrangement, a method includes generating depth features from sparse depth data according to a sparse auxiliary network (SAN) of a depth model. The method includes generating a first depth map from a monocular image and a second depth map from the monocular image and the depth features using the depth model. The method includes generating a depth loss from the second depth map and the sparse depth data and an image loss from the first depth map and the sparse depth data. The method includes updating the depth model including the SAN using the depth loss and the image loss.