A system is disclosed for generating a storage lane marking for a map database. The system, for example, generates a candidate storage lane marking for a first topology based on: the candidate storage lane marking being (i) to the left of a leftmost through-traffic lane marking of the first topology or to the right of a rightmost through-traffic lane marking of the first topology, and (ii) on either start or end of the first topology. The system further makes a determination of whether the candidate storage lane marking is valid based on one or more of following: (i) whether one or more vehicle path locations are located within a polygon defined by (a) the candidate storage lane marking and (b) a corresponding edge of the first topology, or (ii) whether the candidate storage lane marking is located within another topology different from the first topology.

An apparatus comprising a processor and memory including computer program code, the memory and computer program code configured to, with the processor, enable the apparatus at least to: generate, in respect of a road intersection, grouped probe data using probe data derived from probed vehicular movements through the road intersection, wherein the grouped probe data is generated by grouping together probe data comprising vehicle trajectories which have respective common heading angles at points of entry to and exit from the road intersection; and provide the grouped probe data for use in lane-level mapping of the road intersection.

A travel control device includes an operation acquiring unit for acquiring an operation by a driver of a host moving body; an outside-world information acquiring unit for acquiring outside-world information of the periphery of the host moving body; a moving-body information acquiring unit for acquiring moving-body information relating to a travel state of the host moving body; a travelable-range management unit for managing the range travelable by the moving body; and a control unit for controlling travel by the moving body on the basis of the operation acquired by the operation acquiring unit, the outside-world information acquired by the outside-world information acquiring unit, the moving-body information acquired by the moving-body information acquiring unit, and the travelable range managed by the travelable-range management unit, the travelable-range management unit including a travelable-range enlargement unit for enlarging the travelable range, and a travelable-range evaluation unit for evaluating the travelable range.

In one aspect, a vehicle localization system implements the following steps: receiving a predetermined road map; receiving at least one captured image from an image capture device of a vehicle; processing, by a road detection component, the at least one captured image, to identify therein road structure for matching with corresponding structure of the predetermined road map, and determine a location of the vehicle relative to the identified road structure; and using the determined location of the vehicle relative to the identified road structure to determine a location of the vehicle on the road map, by matching the road structure identified in the at least one captured image with the corresponding road structure of the predetermined road map.

A trajectory data processing method is provided to a trajectory data apparatus. The method includes: obtaining trajectory data in a target geographical range, the trajectory data including moving trajectories of a plurality of moving objects, generating a feature map layer of the trajectory data, the feature map layer at least including a trajectory flow map layer, a moving speed map layer, and a travel direction map layer, fusing map layers in the feature map layer to obtain a fused feature map layer; displaying the fused feature map layer; and in response to obtaining a selection instruction of any pixel position on the fused feature map layer, displaying a trajectory flow at the pixel position and a moving speed and a travel direction of a moving object at the pixel position.

Local sensing based navigation maps can form a basis for autonomous navigation of a mobile platform. An example method includes obtaining real-time environment information that indicates an environment within a proximity of the mobile platform based on first sensor(s) carried by the mobile platform, detecting navigation features based on sensor data obtained from the first sensor(s) or second sensor(s) carried by the mobile platform, integrating information corresponding to the navigation features with the environment information to generate a local navigation map, and generating navigation command(s) for controlling a motion of the mobile platform based on the local navigation map.

An acquisition unit (110) acquires attribute information of a moving object, entry-exit information, and target position information. The entry-exit information is for specifying an entry position to an intersection and an exit position from the intersection. The attribute information of the moving object is information regarding the moving object. The target position information is information indicating a target position located in the intersection. The target position indicates a position at least near which a route of the moving object is to pass. A determination rule setting unit (120) sets a rule used when the route is determined, by using the attribute information of the moving object. A route setting unit (130) sets the above-described route using the rule set by the determination rule setting unit (120), and the entry-exit information and the target position information acquired by the acquisition unit (110).

Aspects of the disclosure provide for the generation of a service area map for autonomous vehicles. For instance, graph nodes of a road network may be iterated through in order to identify a set of reachable graph nodes based on a set of routing parameters that define driving limits for the autonomous vehicles. The road network may include the graph nodes as well as edges connecting ones of the graph nodes. A set of S2 cells may be identified based on the set of reachable graph nodes. Vertices of each S2 cell of the set of S2 cells may be determined based on whether each S2 cell of the set of S2 cells is occupied by any of the graph nodes of the set of reachable graph nodes. Contours through cells may be drawn based on the scores. The service area map may be generated using the contours.

Subjects of the present disclosure are methods for training deep learning models, methods for predicting a map matching parameter, methods for updating a digital road map, and a computer program making it possible to implement the methods and devices for updating a digital road map. The general principle is based on the use of machine learning. Accordingly, a statistical deep learning model is trained according to a “supervised” machine learning scheme. Thereafter, the pretrained statistical deep learning model is used to predict a map matching parameter on the basis of a measurement of geographic coordinates and of an identifier of the position sensor that has performed the measurement of geographic coordinates. Finally, the map matching parameter can be used to update a digital road map.

A method of constructing a map including a plurality of lanes and a system thereof are provided. The method includes: for each of the plurality of lanes, constructing corresponding lane geometry data based on a plurality of polyline segments, including constructing a general outline circumscribing the plurality of lanes and identifying an outline of each of the plurality of lanes based on the plurality of polyline segments and the general outline. Outline polyline segments as boundaries of the general outline are selected from the plurality of polyline segments.