Autonomous vehicle pickup directed by socially derived meta data in public environments

• US 10,304,148 B2
• Filed: 09/07/2017
• Issued: 05/28/2019
• Est. Priority Date: 03/14/2017
• Status: Expired due to Fees

• Current Assignee: AirBNB Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Goldberg, Itzhack, McGregor, Harry R., Moore, Christopher B., Mosqueda Mejia, Jose R.
• Primary Examiner(s): Mott, Genna M
• Application Number:
  US15/697,542
• Publication Number:
  US 20180267541A1
• Time in Patent Office: 628 Days
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/0212 with means for defining a desired trajectory involving a plurality of land vehicles G05D1/0287
• CPC Class Codes: G06Q 50/40 Business processes related to the transportation industry shipping G06Q10/083
• CPC Class Codes: G08G 1/202 Dispatching vehicles on the basis of a location, e.g. taxi dispatching

Abstract

Embodiments of the present invention disclose a method, computer program product, and system for directing movements of an autonomous vehicle. A vehicle operator exiting a vehicle is detected. A plurality of metadata is received wherein the plurality of metadata includes at least location data of a user and a timestamp. A pickup time and pickup location is identified based on received metadata. A route to the pickup location is generated based on at least a default location of the autonomous vehicle. The autonomous vehicle is directed to travel to the identified location such that the autonomous vehicle is arriving at the identified pickup time. Updates to the pickup location and pickup time are determined by dynamically monitoring received metadata. A modified route is generated, in response determining updates in one or more of the pickup location and pickup time and the autonomous vehicle is redirected to the updated pickup location.

Claims

1. A computer implemented method for directing movements of autonomous vehicles, the method comprising:

in response to crossing a predetermined geographical threshold, receiving metadata identifying at least a location of a vehicle operator, social media posts associated with the vehicle operator, and timestamps associated with the social media posts;

identifying an event attended by the vehicle operator based on the received metadata;

estimating a duration of the event based on the received metadata;

identifying a pickup time and a pickup location based on the identified event and the estimated duration;

receiving traffic data associated with the geographic threshold;

generating one or more routes to the identified pickup location at the identified pickup time from a plurality of autonomous vehicles;

determining a travel time value for each of the one or more generated routes based on the received traffic data;

selecting a first autonomous vehicle of the plurality of autonomous vehicles having a shortest determined travel time value;

directing the first autonomous vehicle to travel to the identified pickup location based on the estimated duration and determined travel time value such that the first autonomous vehicle arrives at the identified pickup location at the identified pickup time;

increasing a frequency at which updates to the pickup location, pickup time, and the first autonomous vehicle travel time value are reassessed as the estimated duration lapses;

generating a modified route based on the reassessments; and

redirecting the first autonomous vehicle to the updated pickup location based on the generated, modified route.