The present invention provides an automatic system for visual guidance and navigation using real-time visual anchor point detection, which includes an edge device, a cloud device, and a landmark database; the system of the present invention provides users with navigation directions via visual landmarks. A candidate visual landmark image is selected from the database; the system of the present invention can calculate the time of day, the current weather condition, the current season, etc. In addition, the system of the present invention can use the camera on the dashboard of the vehicle, the camera in the smartphone, or other cameras to collect real-time images; the system of the present invention can also provide feedback on the visibility or salience of landmarks to improve the visual landmark images obtained by subsequent users.

Aspects of the disclosure provide a method of providing a destination to an autonomous vehicle in order to enable the autonomous vehicle to collect data according to a targeted driving goal. For instance, a current location of an autonomous vehicle may be received. A set of destinations may be selected from a plurality of predetermined destinations. A route may be determined for each destination. A relevance score may be determined for each destination based on the determined routes and the targeted driving goal. Each destination may be assigned to one of a set of two or more buckets based on the relevance scores. A destination of the set may be selected based on a predetermined sampling probability. The selected destination is sent to the autonomous vehicle in order to cause the autonomous vehicle to travel to the selected destination in an autonomous driving mode.

A server device stores on a storage unit an advanced map database which includes feature information associated with a feature. The server device receives, from vehicle mounted devices equipped with external sensors which measure features, difference information indicative of a difference between feature information and the actual feature corresponding to the feature information. In accordance with the degree of reliability which is calculated based on a plurality of the difference information, the server device sends to the vehicle mounted device a raw data request signal for requesting the transmission of raw data which is measurement data of the actual feature.

A point which requires visual attention is added to map data. A map data generation device acquires image data in which the outside is captured from a vehicle by an input device and a point data of the vehicle, associates both data, and generates a visual saliency map acquired by estimating fluctuation of visual saliency based on the image data by the visual saliency extraction unit. Then, whether or not a point or a section indicated by position information corresponding to the visual saliency map is a point or a section which requires visual attention is analyzed based on the visual saliency map by an analysis unit, and the point or the section which requires the visual attention is added to the map data based on an analysis result of the analysis unit by an addition device.

In some implementations, a system may identify, using a machine learning model, a pattern of events based on account information associated with a user. The system may generate a prediction of a time period during which a predicted event, associated with the pattern of events, is predicted to occur. The system may receive an indication that a vehicle, associated with the user, is to travel a route from a starting location to an ending location during the time period. The system may identify a physical location associated with the predicted event based on a location associated with the vehicle or based on the route. The system may generate a new route that includes the starting location, the physical location as a waypoint along the new route, and the ending location. The system may transmit information that identifies the new route to a device associated with the vehicle.

A method for updating a high definition map according to one embodiment comprises: obtaining a two-dimensional image that captures a target area corresponding to at least a part of an area expressed by a three-dimensional high definition map, generating a three-dimensional local landmark map of the target area from a position of a landmark in the two-dimensional image, based on a position and an orientation of a photographing device which has captured the two-dimensional image and updating the high definition map with reference to the local landmark map corresponding to the target area of the three-dimensional high definition map.

A method for image reconstruction and domain transfer through an invertible depth network is described. The method includes training a first invertible depth network model using a first image dataset corresponding to a first geographic region to estimate a first depth map. The method also includes retraining the first invertible depth network model using a second image dataset corresponding to a second geographic region to estimate a second depth map. The method further includes reconstructing, by the first invertible depth network model, a third image dataset based on the second depth map. The method also includes training a second invertible depth network model using the third image dataset corresponding to the first geographic region and the second geographic region to estimate a third depth map.

Systems and methods for scheduling environment perception-based data offloading for numerous connected vehicles are disclosed. In one embodiment, a method for offloading data includes capturing an image of a view of interest from a vehicle, segmenting the image into a plurality of blocks, and determining a scheduling priority for each of one or more blocks among the plurality of blocks based on block values, wherein the block values relate to one or more objects of interest contained in each of the one or more blocks. The method further includes offloading, from the vehicle to a server, one or more blocks based on the scheduling priority of the one or more blocks.

The above measurement device acquires output data from a sensor unit for detecting surrounding feature, and extracts, from the output data, data corresponding to detection result in a predetermined range in a predetermined positional relation with an own position. The predetermined range is determined in accordance with accuracy of the own position. Then, the measurement device executes predetermined processing based on the extracted data.

Embodiments of the present disclosure disclose a method and apparatus for generating position information, a device and a medium. A specific embodiment of the method includes: acquiring an image and vehicle position information, wherein the image includes a target element; inputting the image into a pre-established depth map generation model to obtain a first depth map, wherein the focal length of sample images of sample data used during the training of the model is a sample focal length; generating a second depth map based on the sample focal length, the first depth map, and an estimated focal length of the image; determining depth information of the target element according to element position information of the target element in the image and the second depth map; and generating position information of the target element based on the vehicle position information and the depth information of the target element.