Embodiments of the present disclosure provide a map updating method and apparatus, a device, a server, and a storage medium, which relate to the field of artificial intelligence, and in particular, to the field of autonomous parking. The specific implementation solution is: an intelligent vehicle obtains driving data collected by a vehicle sensor of its own vehicle on a target road section, where the driving data at least includes first video data related to an environment of the target road section, and determines at least one image feature corresponding to each first image frame in the first video data, where the image feature at least includes an image local feature related to the environment of the target road section, and then updates map data corresponding to the target road section according to the at least one image feature corresponding to each first image frame in the first video data.

A mapping system, comprising an inertial measurement unit; a camera unit; a laser scanning unit; and a computing system in communication with the inertial measurement unit, the camera unit, and the laser scanning unit, wherein the computing system computes first measurement predictions based on inertial measurement data from the inertial measurement unit at a first frequency, second measurement predictions based on the first measurement predictions and visual measurement data from the camera unit at a second frequency and third measurement predictions based on the second measurement predictions and laser ranging data from the laser scanning unit at a third frequency.

A map management system includes: at least one cloud server including a first processor configured to manage map data for a preset area; a plurality of edge servers, each edge server including a second processor configured to manage map data for a preset area; at least one vehicle including a third processor configured to collect raw data for updating map data during traveling; and a plurality of blockchains including the at least one cloud server and the plurality of edge servers.

A system may automatically create training datasets for training a segmentation model to recognize features such as lanes on a road. The system may receive sensor data representative of a portion of an environment and map data from a map data store including existing map data for the portion of the environment that includes features present in that portion of the environment. The system may project or overlay the features onto the sensor data to create training datasets for training the segmentation model, which may be a neural network. The training datasets may be communicated to the segmentation model to train the segmentation model to segment data associated with similar features present in different sensor data. The trained segmentation model may be used to update the map data store, and may be used to segment sensor data obtained from other portions of the environment, such as portions not previously mapped.

Disclosed herein is a technique for obtaining information relating to a navigable network from devices (12) that are associated with users travelling within the navigable network. For example, a central server can issue requests to the devices (12) for automatically obtaining sensor data, with a request including a set of instructions for obtaining sensor data from one or more sensor(s) (13) accessible by the device (12). The request also includes a location-specific trigger. Thus, when it is determined that the device (12) has reached the location associated with the trigger, the device is able to automatically action the instructions in order to obtain the requested sensor data, which can then be reported back to the server.

Embodiments are provided that include maintaining a map of a plurality of markers in an environment. The map includes a last detection time of each marker of the plurality of markers. The embodiments also include receiving a set of detected markers from a robotic device that is configured to localize in the environment using the plurality of markers. The embodiments further include updating, in the map, the last detection time of each marker which has a mapped position that corresponds to a detected position of a detected marker in the set of detected markers. The embodiments additionally include identifying, from the plurality of markers in the map, a marker having a last detection time older than a threshold amount of time. The embodiments still further include initiating an action related to the identified marker.

The present disclosure relates to a system for generating a digital map of an environment. The system comprises at least one sensor which is configured to record sensor data and a position of an object within the environment together with a time-stamp of recording the sensor data. Further, the system comprises a data processing circuitry configured to determine a time-dependent presence probability distribution of the object based on the sensor data. The presence probability distribution is indicative of a probability of the object being at its position before, after and/or at a time of the time-stamp. The data processing circuitry is further configured to register the presence probability distribution of the object in the digital map of an environment of the object.

A method for the simultaneous localization and mapping in 2D using a 3D scanner. An environment is scanned with the aid of the 3D scanner in order to generate a three-dimensional representation of the environment in the form of a 3D pixel cloud made up of a multitude of scanned pixels. A two-dimensional representation of the environment in the form of a 2D pixel cloud is subsequently generated from the 3D pixel cloud. The 2D pixel cloud is conveyed to a 2D SLAM algorithm for the generation of a map of the environment and for the simultaneous ascertainment of the current position of the 3D scanner within the map.

A navigation system for a host vehicle may include a processor programmed to: receive, from an entity remotely located relative to the host vehicle, a sparse map associated with at least one road segment to be traversed by the host vehicle; receive point cloud information from a LIDAR system onboard the host vehicle, the point cloud information being representative of distances to various objects in an environment of the host vehicle; compare the received point cloud information with at least one of the plurality of mapped navigational landmarks in the sparse map to provide a LIDAR-based localization of the host vehicle relative to at least one target trajectory; determine an navigational action for the host vehicle based on the LIDAR-based localization of the host vehicle relative to the at least one target trajectory; and cause the at least one navigational action to be taken by the host vehicle.

A vehicle computing system validates location data received from a Global Navigation Satellite System receiver with other sensor data. In one embodiment, the system calculates velocities with the location data and the other sensor data. The system generates a probabilistic model for velocity with a velocity calculated with location data and variance associated with the location data. The system determines a confidence score by applying the probabilistic model to one or more of the velocities calculated with other sensor data. In another embodiment, the system implements a machine learning model that considers features extracted from the sensor data. The system generates a feature vector for the location data and determines a confidence score for the location data by applying the machine learning model to the feature vector. Based on the confidence score, the system can validate the location data. The validated location data is useful for navigation and map updates.