A POI request comprising query criteria and information identifying a starting location is received. A network version starting segment is identified based on the information identifying the starting location. A route determination algorithm is expanded, starting at the starting segment. When the route determination algorithm is expanded to a new segment, it is determined whether any POIs associated with the new segment match the query criteria. Responsive to determining that a POI associated with the new segment satisfies the query criteria, a POI route from the starting segment to the POI is extracted. Map version agnostic identifiers are generated for each segment of the POI routes. Each of the map version agnostic identifiers are coded using at least one coding function. A bloom filter having the coded map version agnostic identifiers as members is generated. The bloom filter is provided such that a mobile apparatus receives the bloom filter.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for executing the operations represented by an asynchronous execution graph. One of the methods includes receiving data characterizing an asynchronous execution graph comprising one or more subgraphs, wherein each subgraph comprises a plurality of nodes connected by edges, the plurality of nodes comprising a source node, one or more processor nodes, and one or more sink nodes; receiving source data from an external system that corresponds to the source node of a first subgraph in the graph; in response, executing the operations represented by the processor nodes in the first subgraph; and executing the operations represented by each sink node in the first subgraph.

The present subject matter relates to determine a snapping position in a road network for a destination object by using a cost matrix indicative of accumulative cost values of cells of the matrix. The accumulative cost value of a cell is indicating a cost to travel a path from the cell to a road segment of the road network.

An estimated time of arrival (ETA) of a vehicle is predicted by receiving a request for the vehicle to conduct a trip that includes a first location. A predicted ETA for the vehicle to travel from a particular location to the first location is computed. The predicted ETA is refined to compute a refined ETA using a machine-learned model that takes as input a plurality of features associated with the trip. The plurality of features including at least geospatial features transformed using a locality-sensitive hashing function. An action is performed based on the refined ETA. The action may include one or more of estimating a pickup time or drop-off time for the trip, matching a driver to the trip, and planning a delivery.

A method of controlling a vehicle or robot. The method includes the following steps: determining a first control sequence, determining a second control sequence for controlling the vehicle or robot depending on the first control sequence, a current state of the vehicle or robot, and on a model characterizing a dynamic behavior of the vehicle or robot, controlling the vehicle or robot depending on the second control sequence, wherein the determining of the first control sequence is performed depending on a first candidate control sequence and a second candidate control sequence.

Various technologies described herein pertain to generating an occupancy grid movie for utilization in motion planning for the autonomous vehicle. The occupancy grid movie can be generated for a given time and can include time-stepped occupancy grids for future times that are at predefined time intervals from the given time. The time-stepped occupancy grids include cells corresponding to regions in an environment surrounding the autonomous vehicle. Probabilities can be assigned to the cells specifying likelihoods that the regions corresponding to the cells are occupied at the future times. Moreover, cached query objects that respectively specify indices of cells of a grid occupied by a representation of an autonomous vehicle at corresponding orientations are described herein. An occupancy grid for the environment surrounding the autonomous vehicle can be queried to determine whether cells of the occupancy grid are occupied utilizing a cached query object from the cache query objects.

Systems, apparatuses and methods may provide for technology that generates, via a first neural network such as a grid network, a first vector representing a prediction of future behavior of an autonomous vehicle based on a current vehicle position and a vehicle velocity. The technology may also generate, via a second neural network such as an obstacle network, a second vector representing a prediction of future behavior of an external obstacle based on a current obstacle position and an obstacle velocity, and determine, via a third neural network such as a place network, a future trajectory for the vehicle based on the first vector and the second vector, the future trajectory representing a sequence of planned future behaviors for the vehicle. The technology may also issue actuation commands to navigate the autonomous vehicle based on the future trajectory for the vehicle.

A method, apparatus, and computer program product are provided for anonymizing the trajectory of a vehicle. Methods may include: receiving a sequence of probe data points defining a trajectory; for a subset of the sequence of probe data points defining the trajectory beginning at an origin: updating a counter value at each probe data point, where the counter value is updated based, at least in part, on properties of a number of road links emanating from each junction through which the trajectory passed to reach a location associated with the respective probe data point; in response to the counter value satisfying a predetermined value after an update relative to a given probe data point, removing probe data points before the given probe data point in the sequence of probe data points to obtain origin-obscured probe data points; and creating a cropped trajectory including the origin-obscured probe data points.

A route guidance apparatus according to an embodiment of the present disclosure includes a route search unit that performs a route search based on a route search instruction from a user including information indicating a departure place and a destination, a difficulty level calculation unit that calculates a difficulty level for each of the multiple routes obtained as a search result, a required time calculation unit that calculates a required time for each of the multiple routes, a spatial cognitive ability value acquisition unit that acquires a spatial cognitive ability value representing spatial cognitive ability of the user, a route selection unit that selects a route recommended to the user from the multiple routes based on the calculated difficulty level, the calculated required time, and the acquired spatial cognitive ability value, and an output unit that outputs the selected route.

Embodiments of the present disclosure provide a method and an apparatus for generating a navigation route and a storage medium. The method includes: determining navigation points from a start point to an end point according to a preset navigation algorithm; determining a target panoramic point according to coordinates of the navigation points and a coordinate of a preset panoramic point; and performing fitting according to the navigation points and the target panoramic point to generate a navigation route map.