The present disclosure discloses a map display method performed at a terminal. The method includes: obtaining a real scene image of a current location and target navigation data of navigation from the current location to a destination; determining, according to the current location and the target navigation data, virtual navigation prompt information to be overlaid in the real scene image; determining, according to a device configuration parameter of a target device capturing the real scene image, a first location on which the virtual navigation prompt information is overlaid in the real scene image; performing verification detection on the current device configuration parameter; and overlaying the virtual navigation prompt information on the first location when the current device configuration parameter passes through the verification detection. According to the present disclosure, an AR technology is applied to the navigation field so that map display manners are more diverse and diversified.

An apparatus for collecting feature data includes a memory configured to store, for each of vehicles, a mileage of the vehicle or the amount of feature data transmitted by the vehicle and representing a feature related to travel of the vehicles; and one or more processors configured to set a transmission condition for permitting transmission of the feature data for each of the vehicles so that, of the vehicles, the transmission condition for a vehicle with a lower mileage or a vehicle having transmitted a smaller amount of the feature data is more relaxed, and notify each of the vehicles via a communication circuit of a collection instruction to instruct the vehicle to collect the feature data under the transmission condition set for the vehicle.

A system for collecting traffic information includes a vehicle having at least one sensor for collecting dead reckoning (DR) information, and a global positioning system (GPS) receiver configured to receive GPS information, and a server that maps the DR information and the GPS information to a server map to generate first map matching information, and collects the first map matching information as the traffic information when it is determined that a version of a software platform of the vehicle is a latest version and all the DR information and the GPS information are received.

An apparatus for collecting feature data includes a memory configured to store map information including a probability distribution of reliability indicating how likely a feature related to travel of vehicles exists as a function of position; and one or more processors configured to store feature data indicating the position of the feature in the memory whenever receiving the feature data from any of one or more vehicles via a communication circuit, update the probability distribution of reliability indicating how likely the feature exists as a function of position, based on the position of the feature indicated by each of one or more pieces of received feature data, and transmit an instruction to stop collecting the feature data to the one or more vehicles via the communication circuit for a feature regarding which the extent of the updated probability distribution is not greater than a predetermined threshold.

A processor of a route provision apparatus according to an embodiment of the present invention is characterized in outputting map information received from a server, on a rollable display provided in a vehicle, determining a change in the size of a display area of the rollable display, and requesting the server for map information to be displayed on the changed display area, on the basis of the changed size of the display area, and receiving the map information.

Disclosed herein are system and method embodiments to implement a validation of a vector map. The validation process may merge proposed and persisted high-definition mapping data, evaluate the high-definition mapping data with a set of customizable validation rules, return/persist validation results, and provide a means to acknowledge validation failures to minimize creation of problematic vector map content.

A system of highly detailed mapping data for correcting the data format and detail level of the map data adaptively to a specification of a distribution destination. The system includes a data supplementing unit for supplementing medium-/low-detail map data to make the map data highly detailed, an authoring unit for editing the map data adapted to the multiple specifications which differ at least in one of the data format and the detail level, and a database for accumulating the edited map data to allow distribution of the map data as versatile data. The system includes a reliability evaluation unit communicating with the distribution destination via information, and allowing evaluation of reliability indicating a degree to which the versatile data are adapted to the specification, and a reliability registration unit for registering the reliability in the database by associating the evaluation of the reliability evaluation unit with the versatile data.

Disclosed herein is a technique for generating and providing an indication to an autonomous vehicle regarding the confidence level for the accuracy or quality of the map data in which the indication is determined from observation data received from other vehicles.

An on-board device for a vehicle includes an unavailability location determination unit configured to determine whether an area around where the vehicle is traveling is an autonomous driving unavailable location, and a transmission control unit configured to cause the on-board device to transmit to a server a result of determination made by the unavailability location determination unit.

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.