Disclosed is a method for determining the position of a vehicle, in which highly accurate localization data for positions of the vehicle are determined when traveling along a route. Odometric measured variables for the own odometry of the vehicle are captured when traveling along the route. The highly accurate localization data determined and the odometric measured variables captured are jointly evaluated. The own odometry of the vehicle is corrected on the basis of the evaluation. An error model is used to calculate a vehicle-specific drift for the own odometry of the vehicle and to continually correct the own odometry of the vehicle provided highly accurate localization data can be determined. The corrected own odometry of the vehicle can then be used in areas in which highly accurate localization data cannot be determined in order to determine the position of the vehicle.

This application discloses a navigation processing method and apparatus, a server, and an intelligent terminal. The method includes obtaining drawn route information, the drawn route information comprising N initial location points confirmed according to an electronic map, the N initial location points being determined according to a trajectory drawn based on a sliding operation on an interactive interface where the electronic map is displayed, and N being a positive integer; matching the N initial location points with road network information to obtain associated road information, the associated road information comprising M associated location points and L associated links, and M and L being positive integers; obtaining a location similarity between the N initial location points and the M associated location points; and determining a target navigation route corresponding to the drawn route information according to the L associated links when the location similarity meets a navigation condition.

Systems and methods for a stand-alone self-driving material-transport vehicle are provided. A method includes: displaying a graphical map on a graphical user-interface device based on a map stored in a storage medium of the vehicle, receiving a navigation instruction based on the graphical map, and navigating the vehicle based on the navigation instruction. As the vehicle navigates, it senses features of an industrial facility using its sensor system, and locates the features relative to the map. Subsequently, the vehicle stores the updated map including the feature on the vehicle's storage medium. The map can then be shared with other vehicles or a fleet-management system.

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 data collection system includes a vehicle-mounted sensor; a non-transitory computer readable medium configured to store instructions; and a processor connected to the non-transitory computer readable medium. The processor is configured to execute the instructions for generating an invariant feature map, using a first neural network; and comparing the invariant feature map to template data to determine a similarity between the invariant feature map and the template data, wherein the template data is received from a server. The processor is further configured to execute the instructions for determining whether the determined similarity is exceeds a predetermined threshold; and instructing a transmitter to send the sensor data to the server in response to a determination that the determined similarity exceeds the predetermined threshold.

A system and method for monitoring safety of an environment is provided. The system includes a plurality of sensors, a non-transitory memory storing an executable code, and a hardware processor executing the executable code to receive a first input from a first sensor, the first input including a first current condition information, compare the first current condition information with a current condition database, receive a second input from a second sensor, the second input including a second current condition information, compare the second current condition information with the current condition database, determine an event based on the comparison of the first current condition with the current condition database and the comparison of the second current condition with the current condition database, and transmit a signal in response the determination of the event.

The described technology is generally directed towards policy based navigation control. Map inputs including, e.g., information about blocked routes or other map information, can be collected from mobile devices. Policies can be applied to the map inputs in order to generate navigation advisories that synthesize information from multiple map inputs. For example, a size and shape of a route blockage zone can be determined from multiple discrete map inputs. In some embodiments, the techniques disclosed herein can be applied in connection with shared overlay maps to support automated, real-time, cross-platform sharing of map information, including navigation advisories, among digital navigational map users, including but not limited to unmanned ground vehicles.

A positioning method, which relates to the positioning field and is applied to target positioning in a spatially overlapping scenario, is disclosed. The positioning method can avoid a positioning error in the spatially overlapping scenario. The method includes: constructing a local topology map of a target at a current moment based on identifiers of segments and one or more connection relationships among at least some of the segments, wherein the identifiers of the segments and the one or more connection relationships are prestored in map information; and determining, by using the local topology map, a specific road segment in which a target located in a spatially overlapping region is located at a next moment. In addition, a positioning map linked with a road segment may be further stored in the map information, and a positioning map linked with a positioned road segment is determined based on the positioned road segment, to implement high-precision positioning.

A method for processing map data, a device, and a medium, which relates to a field of computer technology, in particular to fields of intelligent transportation technology and autonomous driving technology. The method for processing map data includes: acquiring an initial change information for a traffic object; acquiring incremental map data corresponding to the initial change information; determining, from the initial change information, a target change information based on the incremental map data and historical map data; and updating the historical map data based on the target change information.

Techniques for generating and validating map data that may be used by a vehicle to traverse an environment are described herein. The techniques may include receiving sensor data representing an environment and receiving map data indicating a traffic control annotation. The traffic control annotation may be associated, as projected data, with the sensor data based at least in part on a position or orientation associated with a vehicle. Based at least in part on the association, the map data may be updated and sent to a fleet of vehicles. Additionally, based at least in part on the association the vehicle may determine to trust the sensor data more than the map data while traversing the environment.