US 12,145,599 B2
Systems and methods for clustering human trust dynamics
Kumar Akash, Milpitas, CA (US); Teruhisa Misu, San Jose, CA (US); Xingwei Wu, Sunnyvale, CA (US); and Jundi Liu, Seattle, WA (US)
Assigned to HONDA MOTOR CO., LTD., Tokyo (JP)
Filed by Honda Motor Co., Ltd., Tokyo (JP)
Filed on Mar. 4, 2022, as Appl. No. 17/687,521.
Claims priority of provisional application 63/209,383, filed on Jun. 10, 2021.
Prior Publication US 2022/0396273 A1, Dec. 15, 2022
Int. Cl. B60W 40/09 (2012.01); B60W 60/00 (2020.01)
CPC B60W 40/09 (2013.01) [B60W 60/0013 (2020.02); B60W 2540/22 (2013.01); B60W 2554/4029 (2020.02); B60W 2554/4049 (2020.02)] 20 Claims
OG exemplary drawing
 
1. A computer implemented method for clustering human trust dynamics comprising:
sensing environmental conditions of one agent of one or more agents, and biometrics of each participant of a plurality of participants interacting with the one agent of the one or more agents;
receiving trust data including sensor data from the sensor for each participant of the plurality of participants interacting with the one agent of the one or more agents in an interaction;
identifying a plurality of phases for the interaction;
extracting features characterizing trust dynamics from the trust data for the interaction for each participant of the plurality of participants, wherein the interaction is between the participant and one agent of the one or more agents, wherein the features characterizing trust dynamics include environmental data and corresponding biometric data;
assigning the features characterizing the trust dynamics to a phase of the plurality of the phases;
grouping a subset of the participants of the plurality of participants into a trust group based on the features characterizing the trust dynamics; and
modifying behavior of the one agent of the one or more agents based on the trust group of a given participant of the plurality of participants.