Autonomous vehicle positioning for trip optimization

A computer-implemented system for positioning vehicles, the system comprising:

• at least one processor unit, the at least one processor unit being programmed to execute operations comprising:
• identifying, from historical trip data, a plurality of trip endpoints within a geographical area;
• identifying from the historical trip data a number of trips between trip endpoints selected from the plurality of trip endpoints;
• generating a graph, the graph representing the plurality of trip endpoints with a plurality of nodes and a number of trips between a first trip endpoint and a second trip endpoint as a first edge between a node corresponding to the first trip endpoint and a node corresponding to the second trip endpoint;
• using the plurality of nodes of the graph and a plurality of edges of the graph to generate scores for the plurality of nodes, the scores for the plurality of nodes indicating activity levels for the plurality of nodes, the plurality of edges comprising the first edge;
• using the scores for the plurality of nodes to select a portion of the plurality of trip endpoints;
• and
• using the portion of the plurality of trip endpoints to position at least one vehicle for use in executing a future trip.

A computer readable medium comprising instructions thereon that, when executed by at least one processor, cause the at least processor to perform operations comprising:

• least one processor, cause the at least one processor to execute operations comprising:
• identifying, from historical trip data, a plurality of trip endpoints within a geographical area;
• identifying from the historical trip data a number of trips between trip endpoints selected from the plurality of trip endpoints;
• generating a graph, the graph representing the plurality of trip endpoints with a plurality of nodes and a number of trips between a first trip endpoint and a second trip endpoint as a first edge between a node corresponding to the first trip endpoint and a node corresponding to the second trip endpoint;
• using the plurality of nodes of the graph and a plurality of edges of the graph to generate scores for the plurality of nodes, the scores for the plurality of nodes indicating activity levels for the plurality of nodes, the plurality of edges comprising the first edge;
• using the scores for the plurality of nodes to select a portion of the plurality of trip endpoints;
• and
• using the portion of the plurality of trip endpoints to position at least one vehicle for use in executing a future trip.