US 11,709,475 B2
Systems and methods to adapt and optimize human-machine interaction using multimodal user-feedback
Stefan Scherer, Santa Monica, CA (US); Paolo Pirjanian, Pasadena, CA (US); and Albert Asatoorian, Pasadena, CA (US)
Assigned to Embodied, Inc., Pasadena, CA (US)
Filed by Embodied, Inc., Pasadena, CA (US)
Filed on Nov. 30, 2022, as Appl. No. 18/72,685.
Application 18/072,685 is a continuation of application No. 17/199,083, filed on Mar. 11, 2021, granted, now 11,526,147.
Application 17/199,083 is a continuation of application No. 16/531,118, filed on Aug. 4, 2019, granted, now 10,969,763, issued on Apr. 6, 2021.
Claims priority of provisional application 62/715,665, filed on Aug. 7, 2018.
Prior Publication US 2023/0087575 A1, Mar. 23, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G05B 19/04 (2006.01); G05B 19/408 (2006.01); B25J 11/00 (2006.01); B25J 13/08 (2006.01); G06V 40/20 (2022.01); G06V 40/16 (2022.01)
CPC G05B 19/4083 (2013.01) [B25J 11/0005 (2013.01); B25J 13/08 (2013.01); G06V 40/164 (2022.01); G06V 40/28 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
an adaptive behavioral control system of a robot detecting a plurality of interaction participants by using at least one sensor;
the adaptive behavioral control system storing at least one computer-behavioral policy for each detected interaction participant;
the adaptive behavioral control system controlling an interaction sub-system to perform actions of a first action type for each detected interaction participant in accordance with a selected computer-behavioral policy for the interaction participant;
for each detected interaction participant, the adaptive behavioral control system detecting a human reaction of the interaction participant to the performance of each action of the first action type from data received from a human reaction detection sub-system;
for each detected human interaction participant, the adaptive behavioral control system storing information indicating each detected human reaction in association with information identifying an associated action;
for at least one detected interaction participant, the adaptive behavioral control system determining a current therapy type being used during interaction with the at least one interaction participant, and
selecting the computer-behavioral policy based on the determined current therapy type.