Generating a map associated with an environment may include collecting sensor data received from one or more vehicles and generating a set of links to align the sensor data. A mesh representation of the environment may be generated from the aligned sensor data. A system may determine a proposed link to add, a proposed link deletion, and/or a proposed link alteration, and receive a modification comprising instructions to add, delete, or modify a link. Responsive to receiving a modification, the system may re-align a window of sensor data associated with the modification. The modification and/or sensor data associated therewith may be collected as training data for a machine learning model, which may be trained to generate link modification proposals and/or determine sensor data that may be associated with a poor sensor data alignment.

A method of generating a roadway map includes receiving an image of a roadway. The method further includes identifying features in the roadway. The method further includes assigning a feature identification (FID) number to each of the identified features. The method further includes generating a score for each of the identified features based on a comparison between the identified features and a corresponding feature having a same FID number from a previously generated roadway map. The method further includes determining whether each of the identified features have changed based on whether the corresponding score exceeds a predetermined threshold. The method further includes updating the roadway map by changing identified features determined to have changed and maintaining identified features determined to have remain unchanged.

An end-to-end system for data generation, map creation using the generated data, and localization to the created map is disclosed. Mapstreams—or streams of sensor data, perception outputs from deep neural networks (DNNs), and/or relative trajectory data—corresponding to any number of drives by any number of vehicles may be generated and uploaded to the cloud. The mapstreams may be used to generate map data—and ultimately a fused high definition (HD) map—that represents data generated over a plurality of drives. When localizing to the fused HD map, individual localization results may be generated based on comparisons of real-time data from a sensor modality to map data corresponding to the same sensor modality. This process may be repeated for any number of sensor modalities and the results may be fused together to determine a final fused localization result.

An apparatus for updating map information for a vehicle includes a vehicle information detecting device that detects information of a surrounding vehicle which accompanies a vehicle, when the vehicle travels through an intersection, a line analyzing device that analyzes line information based on information of the surrounding vehicle which accompanies the vehicle, a reliability determining device that determines reliability of the line information, and a controller that extracts a change point on a map based on the reliability and update map information based on the change point.

Methods, systems, and products for generating an updated map for use with an autonomous vehicle driving operation or a simulation thereof may include obtaining first map data associated with a first map of a geographic location including a roadway, and the first map data may include at least one first lane segment. Second map data associated with a second map of the geographic location may be obtained, and the second map data may include at least one second lane segment. A plurality of non-overlapping areas may be determined based on the first lane segment(s) and the second lane segment(s). A first non-overlapping and/or a first warp point within the first non-overlapping area may be selected. The first lane segment(s) may be warped around the first warp point to increase a total overlapping area based on the based on the second lane segment(s) and the first lane segment(s) after warping.

A method for: obtaining route request information characterizing a route to be provided to a terminal; determining, at least partially based on the route request information, an intermediate route comprising a plurality of link identifiers respectively identifying links in respective current versions of map regions; determining a final route by replacing, in the intermediate route, link identifiers by respective indications, wherein each indication of the indications respectively indicates whether or not a link or considered-to-be-suited link corresponding to a link, which is identified by the link identifier replaced by the indication and which is contained in a current version of a map region, is considered to be contained in a non-current-version of the map region available to the terminal, wherein the considered-to-be-suited-link is a link that is considered to be suited to be used for a route guiding process at the terminal; and outputting the final route.

A map information system includes a map database including map information; and a driving assist level determination device. The map information is associated with an evaluation value indicating a certainty of the map information for each location in an absolute coordinate system. Information indicating that the intervention operation is performed is included in driving environment information indicating a driving environment of a vehicle. The driving assist level determination device is configured to acquire, based on the driving environment information, intervention operation information indicating an intervention operation location where the intervention operation is performed, acquire, based on the map information, the evaluation value for each point or section in a target range, and determine, based on the evaluation value and the intervention operation location, an allowable level for each point or section within the target range.

An apparatus for updating a map includes one or more processors configured to: receive feature data from a vehicle traveling on a predetermined road section for a feature in the road section related to travel of vehicles via a communication circuit, the feature data indicating the position of the feature, measure the accuracy of the position of the feature indicated by feature data obtained by the vehicle, based on the difference between the position of the feature indicated by the received feature data and a reference position of a corresponding feature, determine whether the accuracy satisfies a predetermined accuracy condition, and set contribution of the feature data received from the vehicle to update of map information indicating the position of the feature. The contribution is set lower when the accuracy does not satisfy the accuracy condition than when the accuracy satisfies the accuracy condition.

Route provisioning techniques for an autonomous driving feature of a vehicle include receiving a user-generated route generated by a user using a second map database that differs from a first map database of the vehicle that stores a road graph specifying nodes and links representative of a map of roads proximate to the vehicle and specifies an array of geo-points between a current geo-location of the vehicle and a final geo-location for the vehicle, determining, using the road graph maintained by the first map database, a set of valid routes from the current geo-location to the final geo-location ordered based on relative likelihood, determining a best route from the set of valid routes based on a weighted comparison between each route of the set of valid routes and the user-generated route, and utilizing the selected route for control of the autonomous driving feature.

Methods described herein relate to updating a map model. Methods may include receiving data from a vehicle pertaining to a location; comparing the received data pertaining to the location to historical data pertaining to the same location; and based at least in part upon a comparison of the received data pertaining to the location and the historical data pertaining to the same location, generating an internal model for the location. A corresponding apparatus and computer program product are also provided.