A method is provided in which a device associated with a vehicle generates and transmits probe data samples comprising positional data. The method comprises obtaining detected event sequence data indicative of a sequence of detected events relating to the vehicle, obtaining search pattern data indicative of a search pattern of events and using the search pattern data and at least a portion of the detected event sequence data to determine whether a pattern of detected events matching the obtained search pattern of events is present in the at least a portion of the sequence of detected events. When a pattern of detected events matching the obtained search pattern of events is found in the at least a portion of the sequence of detected events, the device generates a probe data sample comprising data indicative of one or both of the search pattern and the matched pattern of events, and data indicative of a position of the device associated with the matched pattern of events. The device transmits the generated probe data sample.

Provided are an environmental map management apparatus, an environmental map management method, and a program that can correct an environmental map to achieve an accurate association between the environmental map and a map indicated by given map data provided by a given map service. A common environmental map data storage unit (64) stores environmental map data that is generated based on sensing data acquired by a tracker and that indicates an environmental map. A pattern identification unit (68) identifies a predetermined pattern in the environmental map on the basis of the environmental map data. A corresponding element identification unit (70) identifies a linear element that appears in a map indicated by given map data provided by a given map service and that is associated with the predetermined pattern. A common environmental map data update unit (72) updates the environmental map data on the basis of a location of the linear element in the map indicated by the given map data.

Disclosed embodiments include systems, vehicles, and methods for tracking off-road travel. In an illustrative embodiment, a system includes a computing device having computer-readable media storing computer-executable instructions configured to cause the computing device to monitor a vehicle location. The vehicle location is identified on map data for an area encompassing the location and including road data for recognized roads in the area. Off-road travel is detected in response to determining that the vehicle location is outside of the recognized roads. Travel data is recorded representing the off-road travel of the vehicle.

An information processing apparatus includes: a point group data acquisition unit configured to acquire, based on information from a sensor configured to detect an object existing in surroundings of a vehicle, point group data related to a plurality of points representing the object; a movement amount estimation unit configured to estimate a movement amount of the vehicle; a storage unit configured to store, as a point group map recorded in association with position information including a latitude and a longitude, relative positions of the plurality of points relative to a first reference position that is a place on a travel path of the vehicle; and a position estimation unit configured to estimate a position of the vehicle based on the point group map, the point group data, and the movement amount.

A map management system stores map information used by an automated driving vehicle. The automated driving vehicle detects an obstacle based on the map information, or acquires a margin distance when stopping in front of an obstacle based on the map information. When requiring a remote operator's decision about an action with respect to the obstacle, the automated driving vehicle issues a support request that requests the remote operator to give support. The map management system acquires an operator instruction to the automated driving vehicle issued by the remote operator in response to the support request. The map management system estimates a type of the obstacle based on a state of acquisition of the operator instruction or a content of the operator instruction. Then, the map management system updates the map information according to the type of the obstacle.

Systems and methods for generating motion forecast data for actors with respect to an autonomous vehicle and training a machine learned model for the same are disclosed. The computing system can include an object detection model and a graph neural network including a plurality of nodes and a plurality of edges. The computing system can be configured to input sensor data into the object detection model; receive object detection data describing the location of the plurality of the actors relative to the autonomous vehicle as an output of the object detection model; input the object detection data into the graph neural network; iteratively update a plurality of node states respectively associated with the plurality of nodes; and receive, as an output of the graph neural network, the motion forecast data with respect to the plurality of actors.

A navigation apparatus and a method for providing an individualization map service of the navigation apparatus are provided. The navigation apparatus includes a detector configured to sense a vehicle state and a travelling environment during travelling, and a processor configured to recognize a drive context based on the vehicle state and the travelling environment, and to make an individualization map to be serviced based on the recognized drive context.

The disclosed technology provides solutions for enriching map data with event information. In some aspects, the disclosed technology includes a process that includes steps for receiving a map query associated with the map for a user, aggregating one or more events that are associated with a respective location on a map, and processing the one or more events to generate one or more event clusters based on the map query. In some aspects, the process can further include steps for providing at least one of the one or more event clusters to the user. Systems and machine-readable media are also provided.

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.

The present invention relates to the efficient use of both local and remote computational resources and communication bandwidth to provide distributed environment mapping using a plurality of mobile sensor-equipped devices. According to a first aspect, there is provided a method of determining a global position of one or more landmarks on a global map, the method comprising the steps of determining one or more differences between sequential sensor data captured by one or more moving devices; determining one or more relative localisation landmark positions with respect to the one or more moving devices; determining relative device poses based one or more differences between sequential sensor data relative to the one or more relative localisation landmark positions; and determining a correlation between each device pose and the one or more relative localisation landmarks positions.