US 11,810,006 B2
System for extending functionality of hypotheses generated by symbolic/logic-based reasoning systems
Jaehoon Choe, Agoura Hills, CA (US); Rajan Bhattacharyya, Sherman Oaks, CA (US); Kyungnam Kim, Oak Park, CA (US); and Kenji Yamada, Los Angeles, CA (US)
Assigned to GM GLOBAL TECHNOLOGY OPERATIONS LLC, Detroit, MI (US)
Filed by GM Global Technology Operations LLC, Detroit, MI (US)
Filed on Nov. 18, 2020, as Appl. No. 16/951,459.
Prior Publication US 2022/0156605 A1, May 19, 2022
Int. Cl. G06N 5/04 (2023.01); B60W 60/00 (2020.01); G06V 20/58 (2022.01); B60W 30/095 (2012.01); G06N 5/045 (2023.01)
CPC G06N 5/04 (2013.01) [B60W 60/001 (2020.02); B60W 60/0011 (2020.02); B60W 60/00272 (2020.02); B60W 60/00276 (2020.02); G06V 20/58 (2022.01); B60W 30/0956 (2013.01); B60W 60/0027 (2020.02); B60W 2556/10 (2020.02); G06N 5/045 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A method of operating an autonomous vehicle, comprising:
inferring a plurality of possible scenarios based on a current state of an environment of the autonomous vehicle;
tokenizing each of the plurality of possible scenarios;
determining a historical likelihood for each of the plurality of possible scenarios using each of the tokenized scenarios, wherein the historical likelihood for a tokenized scenario is based on a similarity percentage indicating a similarity of the tokenized scenario to one or more historical events in a database and an occurrence score indicating how often the one or more historical events in the database having a similarity to the tokenized scenario occurs in the database;
selecting a scenario from the plurality of possible scenarios using the historical likelihoods; and
operating the autonomous vehicle based on the selected scenario.