A map information correction method for correcting map information includes information of a lane boundary line, the method further including: detecting a position with respect to an own vehicle of a lane boundary line set in place on a road surface around the own vehicle; estimating an own position on a map of the own vehicle; and correcting, depending on the estimated own position and the detected position of the lane boundary line, a position of the lane boundary line included in the map information by, in a first region comparatively close to the own vehicle, a larger rotational correction amount than in a second region comparatively far from the own vehicle and, in the second region, a larger translational correction amount than in the first region.

This application provides a map generation method and system for a self-moving device, and an automatic working system. The method includes: obtaining first coordinate data of a plurality of location points on a boundary of a working region of a self-moving device; determining second coordinate data of at least two location points of the plurality of location points; and aligning the first coordinate data of the plurality of location points to a coordinate system in which the second coordinate data is located by using the second coordinate data of the at least two location points, to generate a target map of the working region, where positioning precision of a first positioner configured to obtain the first coordinate data of the plurality of location points is higher than positioning precision of a second positioner configured to obtain the second coordinate data of the at least two location points.

Methods, systems, and apparatus for receiving a reference to an object located in an environment of a robot, accessing mapping data that indicates, for each of a plurality of object instances, respective probabilities of the object instance being located at one or more locations in the environment, wherein the respective probabilities are based at least on an amount of time that has passed since a prior observation of the object instance was made, identifying one or more particular object instances that correspond to the referenced object, determining, based at least on the mapping data, the respective probabilities of the one or more particular object instances being located at the one or more locations in the environment, selecting, based at least on the respective probabilities, a particular location in the environment where the referenced object is most likely located, and directing the robot to navigate to the particular location.

Provided is an apparatus for providing obstacle information and reliability information to vehicle based on information received from roadside units. The apparatus includes a communication module that receives obstacle information from multiple roadside units, each roadside unit including multiple sensors for detecting obstacles within a predetermined field of view. A reliability judgement unit in the apparatus determines a reliability of the received obstacle information to output a reliability value based on a number of roadside units detecting a same obstacle, a number of sensor of one roadside unit detecting a same obstacle, and a difference value of detection of the same obstacle between different roadside units or different sensors.

Disclosed are high-precision-map data collection methods, devices and storage mediums, which relate to the field of computer technologies, and particularly to the fields of big data technologies, autonomous driving technologies, intelligent transportation technologies, or the like. The data collection method includes: receiving a collection task generated by a server, where the collection task includes to-be-collected track points; generating a navigation path based on the to-be-collected track points, and displaying the navigation path; and acquiring map data collected at the to-be-collected track points when a vehicle travels based on the navigation path.

A navigation method based on ground texture images, an electronic device and storage medium. The method includes: performing transform domain based image registration on an acquired image of a current frame and an image of a previous frame, and determining a first pose of the image of the current frame; determining whether the image of the current frame meets a preset condition, and if so, inserting the image of the current frame as the key-frame image into a map, and performing loop closure detection and determining a loop key-frame image; performing transform domain based image registration on the image of the current frame and the loop key-frame image, and determining a second pose of the image of the current frame; and determining an accumulated error according to the first pose and the second pose, and correcting the map according to the accumulated error.

An approach is provided for mapping based on pedestrian type. The approach, for instance, involves processing image data to a determine the pedestrian type of at least one pedestrian depicted in the image data. The approach also involves determining a classification of a geographic zone based on the detected pedestrian type. The approach further involves generating a digital map representation of the geographic zone based on the classification.

A method is provided for updating parking area information in a navigation system for a vehicle. The method includes the following steps: detecting a parking area by way of data received at least one device on at least one vehicle; determining information relating to the parking area which at least partially relates to characterizing characteristics of the parking area; analyzing the determined information in relation to an adequate characterization of the parking area; comparing the determined information with data of at least one database; and updating the database in the event of a deviation between the determined information and the data of the database.

According to an aspect of an embodiment, operations may comprise receiving, from a LIDAR mounted on a vehicle, a first 3D point cloud comprising points of a region around the vehicle as observed by the LIDAR. The operations may also comprise accessing an HD map comprising a second 3D point cloud comprising points of the region around the vehicle. The operations may also comprise segmenting LIDAR ground points from LIDAR non-ground points in the first 3D point cloud. The operations may also comprise segmenting map ground points from map non-ground points in the second 3D point cloud. The operations may also comprise determining a pose of the vehicle by matching the LIDAR ground points to the map ground points and by matching the LIDAR non-ground points to the map non-ground points.

Methods and server for updating a map representation of a geographical region is disclosed. For a given timestamp along a past trajectory of the SDC when the SDC has been located at a given location in the geographical region, the method includes: generating, using a localization algorithm, a set of candidate locations using a set of point clouds and the map representation, determining, using a convergence metric, a parameter for evaluating quality of localization of the localization algorithm when the SDC is located in the candidate portion of the map representation, identifying, using the parameter, the candidate portion of the map representation as an outdated portion of the map representation, and updating the outdated portion of the map representation using point cloud data captured by the LIDAR system.