Systems and methods to adapt and optimize human-machine interaction using multimodal user-feedback
Abstract
Systems and methods for human-machine interaction. An adaptive behavioral control system of a human-machine interaction system controls an interaction sub-system to perform a plurality of actions for a first action type in accordance with a computer-behavioral policy, each action being a different alternative action for the action type. The adaptive behavioral control system detects a human reaction of an interaction participant to the performance of each action of the first action type from data received from a human reaction detection sub-system. The adaptive behavioral control system stores information indicating each detected human reaction in association with information identifying the associated action. In a case where stored information indicating detected human reactions for the first action type satisfy an update condition, the adaptive behavioral control system updates the computer-behavioral policy for the first action type.
Claims
exact text as granted — not AI-modified1 - 24 . (canceled)
25 . A robot system comprising:
a robotic body assembly; a robotic head assembly mechanically attached to the robotic body assembly via a motor assembly; the motor assembly, the motor assembly being constructed to rotate the robotic head assembly about a vertical axis and a horizontal axis; an adaptive behavioral control system communicatively coupled to at least one of the robotic motor assembly and the robotic head assembly, and configured to detect an interaction participant using at least one sensor and store at least one computer-behavioral policy for the detected interaction participant; a human reaction detection sub-system communicatively coupled to the adaptive behavioral control system; and an interaction sub-system communicatively coupled to the adaptive behavioral control system, wherein the adaptive behavioral control system is further configured to: control at least one of the interaction sub-system, the motor assembly, the robotic body assembly, or the robotic head assembly to perform an action of a first action type for the detected interaction participant in accordance with a selected computer-behavioral policy for the detected interaction participant, detect a human reaction of the detected interaction participant to the performance of the action of the first action type from data received from the human reaction detection sub-system, and store information indicating the detected human reaction in association with information identifying the performed action.
26 . A method comprising:
an adaptive behavioral control system in a robot controlling an interaction sub-system to perform a plurality of actions for a first action type in accordance with a computer-behavioral policy, each action of the plurality of actions being a different alternative action for the action type; the adaptive behavioral control system controlling at least one of a human interaction detection sub-system, a motor assembly or a robotic head assembly to perform actions of a first action type for the detected interaction participant in accordance with a selected computer-behavioral policy for the detected interaction participant; the adaptive behavioral control system detecting an interaction participant by using at least one sensor and to store at least one computer-behavioral policy for the detected interaction participant; the adaptive behavioral control system detecting a human reaction of the detected interaction participant to the performance of the action of the first action type from data received from a human reaction detection sub-system which is coupled to the adaptive behavioral control system; the adaptive behavioral control system storing information indicating each detected human reaction in association with information identifying the action.
27 . The method of claim 26 ,
wherein the adaptive behavioral control system stores information indicating the detected human reaction in association with the computer-behavioral policy, and the method further comprising: responsive to a reaction information request from an external system via an API (Application Programming Interface) of the adaptive behavioral control system, the reaction information request specifying the computer-behavioral policy, the adaptive behavioral control system providing to the external system the stored information indicating the detected human reaction for the computer-behavioral policy as a response to the reaction information request.
28 - 33 . (canceled)
34 . The robot system of claim 25 , further comprising:
at least one first motorized appendance configured to perform movement with at least one human-interaction gesture.
35 . The robot system of claim 34 , further comprising:
the adapter behavioral control system communicatively coupled to the at least one first motorized appendage and control the at least one first motorized appendage to perform actions of a first action type for the detected interaction participant in accordance with a selected computer-behavioral policy for the detected interaction participant.
36 . The robot system of claim 25 , wherein the at least one sensor is a sensor of a heat detection sub-system, a sensor of a video capture sub-system, a sensor of an audio capture sub-system, a touch sensor, a piezoelectric pressor sensor, a capacitive touch sensor, a resistive touch sensor, a blood pressure sensor, a heart rate sensor, or a biometric sensor.
37 . The robot system of claim 25 , further comprising: responsive to a reaction information request from an external system via an API (application programming interface) of the adaptive behavioral control system, the reaction information request specifying a computer-behavioral policy, the adaptive behavioral control system to provide to the external system the stored information indicating the detected human reaction for the specified computer-behavioral policy as a response to the reaction information request.
38 . The robot system of claim 25 , further comprising: the adaptive behavioral control system to select a computer-behavioral policy for the detected interaction participant based on an identity of the interaction participant, a determined current interaction context for the interaction participant, an action type, or a current therapeutic goal for the interaction participant.
39 . The robot system of claim 25 , wherein at least one action for the first action type includes performing a facial expression by controlling the robotic head assembly of the robot.
40 . The robot system of claim 39 , wherein the robotic head assembly includes at least one mechanical facial feature, and the robotic head assembly configured to control movement of the at least one mechanical facial feature to perform the facial expression.
41 . The robot system of claim 39 , wherein the robotic head assembly includes at least one display device, and the robotic head assembly is configured to control display of the at least one display device to perform the facial expression.
42 . The robot system of claim 39 , wherein the robotic head assembly includes at least one light emission subsystem, and the robotic head assembly is constructed to control light emission of the at least one light emission display system to perform the facial expression.
43 . The robot system of claim 39 , wherein the robotic head assembly includes at least one LED ring, and the robotic head assembly is configured to control at least one LED of the at least one LED ring to perform the facial expression.
44 . The robot system of claim 25 , wherein at least one action for the first action type includes controlling a robotic head assembly to output audio in a particular voice, by controlling an audio output sub-system of the robotic head assembly.
45 . The robot system of claim 25 , the adaptive behavioral control system further to: detect a plurality of interaction participants by using at least one sensor, detect locations of each detected interaction participant, and generate a three-dimensional world model of detected locations of the detected interaction participants.
46 . The robot system of claim 45 , wherein during initiation of an interaction with a detected interaction participant, the adaptive behavioral control system is configured to control the motor assembly to orient the robotic head assembly in a direction of the detected interaction participant by using the detected location of detected interaction participant included in the three-dimensional world model.
47 . The robot system of claim 45 , the adaptive behavioral control system to: detect a face of each interaction participant when detecting the locations of each interaction participant, wherein the three-dimensional world model includes a detected orientation of the detected faces of each interaction participant
wherein during initiation of an interaction with the detected interaction participant, the adaptive behavioral control system is configured to control the motor assembly to orient the robotic head assembly in a direction of the face of the detected interaction participant by using the detected location and face orientation included in the three dimensional world model.
48 . The robot system of claim 25 , the adaptive behavioral control system to select the computer-behavioral policy for the interaction participant based on a current therapeutic goal.
49 . The robot system of claim 25 , the adaptive behavioral control system to determine a current therapy type being used during interaction with the interaction participant, and select the computer-behavioral policy based on the determined current therapy type.
50 . The robot system of claim 25 , the adaptive behavioral control system to select the computer-behavioral policy based on an identity of the interaction participant.Cited by (0)
No later patents cite this yet.
References (0)
No backward citations on record.