Abstract: A mapping system creates feature data associated with a first section of a route, stores the feature data in the local storage system as stored feature data, fuses the feature data with the stored feature data to create map data associated with the first section when the vehicle has traversed the first section and collected the stored feature data at least a threshold number of times, stores the map data in the local storage system, identifies one or more route sections as being part of one or more commute routes, and when space in the local storage system is insufficient for storage of the map data or the feature data, enables the storage by removing stored map data from the location storage system based at least in part on a determination that the removed data is not associated with the one or more commute routes.

Abstract: The present disclosure provides a method and an apparatus for updating road network data. The method for updating the road network data is specifically implemented as follows: acquiring trajectory data reported by a terminal; determining a plurality of out-of-road trajectories within a preset area coverage according to the trajectory data; determining a fitting trajectory according to the plurality of out-of-road trajectories; and updating existing first road network data according to the fitting trajectory to acquire second road network data.

Abstract: An occlusion detection system for an autonomous vehicle is described herein, where a signal conversion system receives a three-dimensional sensor signal from a sensor system and projects the three-dimensional sensor signal into a two-dimensional range image having a plurality of pixel values that include distance information to objects captured in the range image. A localization system detects a first object in the range image, such as a traffic light, having first distance information and a second object in the range image, such as a foreground object, having second distance information. An occlusion polygon is defined around the second object and the range image is provided to an object perception system that excludes information within the occlusion polygon to determine a configuration of the first object. A directive is output by the object perception system to control the autonomous vehicle based upon occlusion detection.

Abstract: A method and a related system for allocating target locations to optimize trajectories between several objects and the target locations may be provided. The method comprises capturing location data of the target locations as well as location and movement data of the objects, building a graph using the target locations as well as the location and movement data and integrating constraints into the graph. Furthermore, the method comprises determining for each of the several objects a desired target location using a first optimization system, thereby determining endpoints of a trajectory between each of the objects and its respective desired target location and selecting for each of the several objects an optimal path as the trajectory between the object and the desired target location, using a second optimization system, and taking into account movements of other objects along their trajectories.

Abstract: A navigation system includes an operation input unit, a temporary storage unit, and a control unit that executes processing concerning the navigation operation using the information for applications. The control unit sets analysis priority levels for analysis processing performed for each of the kinds of the map information and sets generation priority levels for each of the kinds of the information for applications, performs, with at least one kind of map information as an analysis target, the analysis processing generates the information for applications in order according to the generation priority levels based on results of the analysis processing respectively obtained for the map information set as the analysis target, saves the generated information for applications in the temporary storage unit, and executes processing concerning the navigation operation using the information for applications saved in the temporary storage unit.

Abstract: In one embodiment, when planning a path for a current driving cycle for an autonomous driving vehicle (ADV), a current location of the ADV is determined based on sensor data provided by a variety of sensors mounted on the ADV. A path is generated for the current driving cycle to drive the ADV from the current location for a predetermined period of time. An expected location of the ADV calculated based on a previous path, which was generated during a previous driving cycle. A drifting error is then calculated based on the expected location and the current location of the ADV. At least a starting point of the path for the current driving cycle is modified based on the drifting error, generating a modified path. The ADV is then controlled according to the modified path.

Abstract: The present invention provides an automatic train protection method, a vehicle on-board controller and a train based on vehicle-vehicle communication. The method includes: after a present train runs onto a main track, determining an OC with which the present train needs to establish communication; communicating, by the present train, with the OC to obtain train identifiers of all trains within the jurisdiction of the OC; respectively communicating, by the present train, with the train corresponding to each train identifier to obtain current running information of the train corresponding to each train identifier; identifying a front communication neighbor train of the present train; determining that no hidden train exists between the present train and the front communication neighbor train; and calculating current movement authority MA of the present train according to the current position information of the present train and of the front communication neighbor train.