CPC G01C 21/3446 (2013.01) [G01C 21/3617 (2013.01); G01C 21/3841 (2020.08)] | 20 Claims |
14. A method comprising:
identifying a first point that is a current location of an autonomous vehicle;
identifying a second point that is a drop-off or pick-up location of an item;
querying, by a computing device and based at least in part on the second point, historical drop-off or pick-up data, wherein the historical drop-off or pick-up data comprises time series data previously captured involving performance of off-street terrain routes utilized to at least one of drop-off or pick-up of items at the second point;
processing, by the computing device, the historical drop-off or pick-up data using an inference model to generate a first set of data comprising a first plurality of route portions from a plurality of intermediate points to the second point, wherein the inference model generates the first set of data by generating a flow graph of directional vectors representing predicted routes taken from the plurality of intermediate points to the second point, and each of the plurality of intermediate points represents a beginning of at least one of the off-street terrain routes;
querying, by the computing device and based at least in part on at least one of the first point or the second point, map data;
generating, by the computing device analyzing the map data, segmented map data, wherein the segmented map data corresponds to on-street terrain;
generating, by the computing device, a second set of data comprising a second plurality of route portions from the first point to at least a portion of the plurality of intermediate points by comparing the segmented map data to the flow graph to identify an area shared by both the segmented map data and the flow graph;
generating, by the computing device and from the first set of data and the second set of data, a plurality of routes from combinations of the first plurality of route portions and the second plurality of route portions, wherein each route of the plurality of routes connects the first point to the second point using at least one of the plurality of intermediate points;
selecting, by the computing device and based at least in part on selection criteria, a primary route from the plurality of routes;
generating, by the computing device, navigation instructions for the primary route; and
communicating, by the computing device, the navigation instructions to the autonomous vehicle to cause the autonomous vehicle to execute the navigation instructions and travel from the first point to the second point.
|