Disclosed herein is a method for exactly estimating the current location of a user and calling a vehicle to the estimated location on the basis of a GPS coordinate of a user terminal and a coordinate of a feature point recorded by the user terminal. The method for calling a vehicle according to an embodiment includes transmitting a GPS coordinate of a terminal to a server when a service request signal is input by a user, receiving tile data corresponding to the GPS coordinate of a terminal from the server, recording an external image using a camera, and extracting a feature point from the recorded external image, identifying any one reference feature point matched with the feature point extracted from the external image among a plurality of reference feature points included in the tile data, determining a terminal coordinate on the basis of a coordinate of the identified reference feature point and on the basis of a change in a location of the reference feature point in the external image, and transmitting the determined terminal coordinate to the server, and receiving a vehicle coordinate of a vehicle for transportation allocated to the terminal coordinate from the server.

Systems and methods for navigational map version management are disclosed. In one aspect, a map management server includes a processor and a computer-readable memory having stored thereon a navigational map including a plurality of units, each of the units covering an area and including a plurality of objects within or adjacent to roadways within the area. The processor is configured to receive update data for the navigational map, the update data including object data to update the navigational map. The processor is also configured to create a released version of the navigational map that includes one or more updated units. The processor is further configured to provide the released version of the navigational map to an autonomous vehicle.

Techniques for generating trajectories and drivable areas for navigating a vehicle in an environment are discussed herein. The techniques can include receiving a reference trajectory representing an initial trajectory for a vehicle, such as an autonomous vehicle, to traverse the environment. Portions of the reference trajectory can be identified as corresponding to actions to navigate around a double-parked vehicle or to change lanes, for example. In some cases, a portion of the reference trajectory can be identified based on a proximity to an object in the environment. A weight can be associated with the portions of the reference trajectory, and the techniques can include evaluating a reference cost function at points of the reference trajectory based on the associated weights to generate a target trajectory. Further, the techniques can include controlling the autonomous vehicle to traverse the environment based at least in part on the target trajectory.

A method performed by an apparatus is described. The method includes receiving map data that is based on first image data, second image data, and a similarity metric. The first image data can be received from a first vehicle and represent an object. The second image data can be received from a second vehicle and represent the object. The similarity metric can be associated with the object represented in the first image data and the object represented in the second image data. The method can also include storing, by a vehicle, the received map data and localizing the vehicle based on the stored map data.

Movement guidance information for performing traveling guidance for a vehicle is requested to a guidance information delivering server device based on an area update table and an area identification table for managing an update state of map information in a communication terminal, and traveling guidance for the vehicle is performed based on the movement guidance information delivered from the guidance information delivering server device in response to the request.

Systems and methods for providing one or more map segments to one or more vehicles are disclosed. In one implementation at least one processor is programmed to receive navigational information from a vehicle, the navigational information including an indicator of a location of the vehicle, an indicator of a speed of the vehicle, and an indicator of a direction of travel of the vehicle; analyze the received navigational information and determine a potential travel envelope for the vehicle; and send to the vehicle one or more map segments including map information for a geographical region at least partially overlapping with the potential travel envelope of the vehicle.

A computer system and related computer-implemented methods are disclosed. The system is programmed to simplify one or more digital maps for a geographical region by reducing their sizes while maintaining their physical appearances to the human eyes.

A graph generating device is provided, which may include an interface (an obstacle data acquiring module) and processing circuitry (a first graph generating module, a second graph generating module, and a graph synthesizing module). The interface (the obstacle data acquiring module) may acquire obstacle data including information on an obstacle. The processing circuitry is configured to generate a first graph having an area including the obstacle that is recursively divided with a quadtree splitting method into cells that are exclusive of the obstacle, the first graph has a first vertex set in each cell and adjacent first vertexes being interconnected, to generate a second graph that includes second vertexes interconnected by a different method from the quadtree splitting method, and to generate a combined graph from the first graph and the second graph.

Disclosed are systems (100) and (400) and a method (200) of evolution of a cartographic grid using map information. More specifically the evolution of context cognitive cartographic grid uses context cognitive data and historical data. For an identified reference geolocation on the map, various routes emanating from the reference geolocation are identified and then using pre-defined context parameters, a second geolocation is selected or updated. The process is repeated until all the possible routes associated with the identified reference geo-location are traversed. Subsequently, a convex grid is created using all the geolocations found, to evolve the context cognitive cartographic grid.

A method and a device for localization using grid-based localization of map constraints are described. In an example, an indoor space is divided into a grid of tessellated polygonal tiles in a hierarchical structure. The grid is correlated with physical entities in the indoor space by associating each physical entity with a polygonal tile. Further, an absolute probability value indicative of presence of a device therein is associated with each polygonal tile. As part of associating, the absolute probability value is allocated to each polygonal tile in each hierarchical level to create a probability map for the indoor space. The probability map is used to generate a grid map for the indoor space and the grid map is usable to determine location of the device in the indoor space.