Social robot with environmental control feature
A method and apparatus for controlling a social robot includes operating an electronic output device based on social interactions between the social robot and a user. The social robot utilizes an algorithm or other logical solution process to infer a user mental state, for example a mood or desire, based on observation of the social interaction. Based on the inferred mental state, the social robot causes an action of the electronic output device to be selected. Actions may include, for example, playing a selected video clip, brewing a cup of coffee, or adjusting window blinds.
1 . A method for controlling an environment of an interactive machine, the method comprising:
interacting, according to a social behavior algorithm, with a user via a human-recognizable expressive feature controlled by one or more processors;
determining, by the one or more processors, user behavior on data obtained by one or more sensors of the interactive machine;
correlating, by the one or more processors, the user behavior to social behavior of the interactive machine;
determining, by the one or more processors, a current mental state indicator based on the correlating;
identifying, based on the current mental state indicator, a prospective response from a plurality of prospective responses by:
comparing metadata for the plurality of prospective responses to a representation of the current mental state indicator, wherein the metadata comprises semantic information; and
outputting a control signal configured based on the prospective response, the control signal for causing an electronic output device to take an action, wherein the control signal includes a prerecorded audio-video content clip.
2 . The method of claim 1 , further comprising:
determining one or more characteristics of a space in which the interacting occurs; and
adjusting the control signal based on the one or more characteristics.
3 . The method of claim 2 , wherein the one or more characteristics include one or more of a voice, a trait, a mood, an expression, or a mannerism.
4 . The method of claim 1 , wherein identifying the prospective response from the plurality of prospective responses further comprises:
selecting the prerecorded audio-video content clip based on comparing the metadata for prospective responses to the representation of the current mental state indicator.
5 . The method of claim 1 , wherein identifying the prospective response from the plurality of prospective responses further comprises identifying one or more similarities between the prospective response and the current mental state indicator.
6 . The method of claim 1 , wherein determining the user behavior comprises determining one or more of a direction of user gaze or a relative position and orientation of the user by using photographic data or proximity sensor data.
7 . The method of claim 1 , further comprising executing a content-selection algorithm including selection of the identifier based on the current mental state indicator.
8 . An interactive machine, comprising:
one or more processors for driving components of the interactive machine;
a social expression component connected to a at least one circuit, the social expression component comprising a human-recognizable expressive feature controlled by the one or more processors according to a social behavior algorithm;
one or more sensors positioned for observing a user interacting with the interactive machine; and
a program memory, coupled to the at least one circuit and to the one or more processors, wherein the program memory holds program instructions that when executed by the one or more processors, cause the interactive machine to perform operations comprising:
interacting, according to a social behavior algorithm, with a user via a human-recognizable expressive feature controlled by one or more processors;
determining, by the one or more processors, user behavior on data obtained by one or more sensors of the interactive machine;
correlating, by the one or more processors, the user behavior to social behavior of the interactive machine;
determining, by the one or more processors, a current mental state indicator based on the correlating;
identifying, based on the current mental state indicator, a prospective response from a plurality of prospective responses by:
comparing metadata for the plurality of prospective responses to a representation of the current mental state indicator, wherein the metadata comprises semantic information; and
outputting a control signal configured based on the prospective response, the control signal for causing an electronic output device to take an action, wherein the control signal includes a prerecorded audio-video content clip.
9 . The interactive machine of claim 8 , wherein the program instructions, when executed by the one or more processors, cause the interactive machine to perform additional operations comprising:
determining one or more characteristics of a space in which the interacting occurs; and
adjusting the control signal based on the one or more characteristics.
10 . The interactive machine of claim 8 , wherein the metadata comprises semantic information and wherein the program instructions, when executed by the one or more processors, cause the interactive machine to perform additional operations comprising selecting the prerecorded audio-video content clip based on the comparing.
11 . The interactive machine of claim 8 , wherein identifying the prospective response from the plurality of prospective responses further comprises identifying one or more similarities between the prospective response and the current mental state indicator.
12 . The interactive machine of claim 8 , wherein determining the user behavior comprises determining one or more of a direction of user gaze or a relative position and orientation of the user by using photographic data or proximity sensor data.
13 . The interactive machine of claim 8 , wherein the program memory holds program instructions that when executed by the one or more processors, cause the interactive machine to perform additional operations comprising executing a content-selection algorithm including selection of the identifier based on the current mental state indicator.
14 . The interactive machine of claim 9 , further comprising a biometric sensor coupled to the at least one circuit, the biometric sensor configured to provide a control signal responsive to a bodily state of the user, wherein the program memory holds program instructions that when executed by the one or more processors, cause the interactive machine to perform additional operations comprising determining the current mental state from the biometric sensor.
15 . The interactive machine of claim 9 , wherein the human-recognizable expressive feature comprises a display screen and wherein the control signal comprises a video signal that encodes one or more human-recognizable expressive features for display on the display screen.
16 . A non-transitory computer-readable medium comprising program instructions that when executed by a processor, cause the processor to perform operations comprising:
interacting, according to a social behavior algorithm, with a user via a human-recognizable expressive feature controlled by one or more processors;
determining, by the one or more processors, user behavior on data obtained by one or more sensors of an interactive machine;
correlating, by the one or more processors, the user behavior to the interactions;
determining, by the one or more processors, a current mental state indicator based on the correlating;
identifying, based on the current mental state indicator, a prospective response from a plurality of prospective responses by:
comparing metadata for the plurality of prospective responses to a representation of the current mental state indicator, wherein the metadata comprises semantic information; and
outputting a control signal configured based on the prospective response, the control signal for causing an electronic output device to take an action, wherein the control signal includes a prerecorded audio-video content clip.
17 . The non-transitory computer-readable medium of claim 16 , wherein when executed by a processor, the program instructions cause the processor to perform additional operations comprising:
determining characteristics of a space in which the interacting occurs, wherein the characteristics include one or more of a voice, a trait, a mood, an expression, or a mannerism; and
adjusting the control signal based on the characteristics.
18 . The non-transitory computer-readable medium of claim 16 , wherein identifying the prospective response from the plurality of prospective responses further comprises identifying one or more similarities between the plurality of prospective response and the current mental state indicator.