Control of social robot based on prior character portrayal

Abstract

A method and apparatus for controlling a social robot includes providing a set of quantitative personality trait values, also called a “personality profile” to a decision engine of the social robot. The personality profile is derived from a character portrayal in a fictional work, dramatic performance, or by a real-life person (any one of these sometime referred to herein as a “source character”). The decision engine controls social responses of the social robot to environmental stimuli, based in part on the set of personality trait values. The social robot thereby behaves in a manner consistent with the personality profile for the profiled source character.

1 . A social robot, comprising:
 one or more processors coupled to a memory and to at least one circuit for driving components of the robot;   wherein the memory holds instructions, that when executed by the one or more processors, causes the social robot to:
 control social responses of the social robot to environmental stimuli, based in part on a set of quantitative personality trait values stored in the memory, whereby behavior of the social robot is consistent with a personality of a source character expressed by a prior character portrayal in a cinematic or video program, and wherein each of the quantitative personality trait values represents a score of the prior character portrayal against a scale that measures the each of the personality trait values for corresponding ones of stimulus-response pairs applicable to the prior character portrayal in the cinematic or video program. 
   
     
     
         2 . The social robot of  claim 1 , wherein the instructions provide for user-initiated modification of the set of quantitative personality trait values, causing the social robot to behave in a manner consistent with a second character different from the source character. 
     
     
         3 . The social robot of  claim 1 , wherein each member of the set of quantitative personality trait values characterizes a personality trait based on a bipolar scale between opposite extremes. 
     
     
         4 . The social robot of  claim 3 , wherein the bipolar scale between opposite extremes, for each member of the set of quantitative personality trait values, is defined by distinct trait pairs. 
     
     
         5 . The social robot of  claim 1 , wherein the memory further holds data for generating verbal responses based on a set of characteristic phrases for the source character stored in the memory. 
     
     
         6 . The social robot of  claim 1 , wherein the social responses comprise a configuration of a human-recognizable expressive feature, a type of verbal response, and a phrasing of verbal response. 
     
     
         7 . The social robot of  claim 1 , further comprising a video screen displaying the at least two human-recognizable expressive features. 
     
     
         8 . The social robot of  claim 1 , wherein the instructions are further configured for selecting a social response from a set of possible social responses to an environmental stimulus stored in the memory, based on the set of quantitative personality trait values. 
     
     
         9 . The social robot of  claim 8 , wherein the instructions are further configured for calculating a probability score for each of the possible social responses, based on a set of correlation factors stored in the memory, wherein each of the set of correlation factors scores one of the possible social responses relative to a personality trait scale used for the scaling the set of quantitative personality trait values. 
     
     
         10 . The social robot of  claim 9 , wherein the instructions are further configured for the selecting a high level response, at least in part based on the probability score for each of the possible social responses. 
     
     
         11 .- 31 . (canceled) 
     
     
         32 . A non-transitory computer-readable medium for configuring a social robot based on a prior character portrayal in fiction or performance, comprising instructions that when executed by at least one processor cause a social robot to perform:
 accessing, by the at least one processor, behavioral data characterizing a prior character portrayal in a cinematic or video program;   deriving, by the at least one processor, quantitative personality trait values from the behavioral data, each measuring a corresponding personality trait based on one or more stimulus-response pairs included in the prior character portrayal; and   recording a personality profile for the social robot comprising the quantitative personality trait values mapped to the stimulus-response pairs in a memory for access by the social robot, configured for use by a processor of the social robot for selecting social responses to stimuli that emulate the prior character portrayal based at least in part on the personality trait values.   
     
     
         33 . The non-transitory computer-readable medium of  claim 32 , wherein the deriving instructions further comprise instructions for evaluating the behavioral data against a personality scale unique to the social robot. 
     
     
         34 . The non-transitory computer-readable medium of  claim 32 , wherein the deriving instructions further comprise instructions for using artificial intelligence to recognize the stimulus-response pairs. 
     
     
         35 . The non-transitory computer-readable medium of  claim 32 , wherein the deriving instructions further comprise instructions for using artificial intelligence to correlate the stimulus-response pairs to the quantitative personality trait values. 
     
     
         36 . The non-transitory computer-readable medium of  claim 32 , wherein the deriving instructions further comprise instructions for including a data object for determining a social response for responding to combinations of stimuli. 
     
     
         37 . The non-transitory computer-readable medium of  claim 32 , wherein the personality profile comprises multiple personality modes each correlated to one of distinct behavior patterns to be emulated by the social robot. 
     
     
         38 . The non-transitory computer-readable medium of  claim 37 , wherein each of the distinct behavior modes comprises a distinct set of personality trait values in a memory coupled to the at least one processor. 
     
     
         39 . The non-transitory computer-readable medium of  claim 38 , further comprising instructions for configuring the distinct behavior patterns by grouping the behavioral data over different continuous time periods of the prior character portrayal. 
     
     
         40 . The non-transitory computer-readable medium of  claim 39 , wherein the instructions further define that the different time periods are selected to model moods of the prior character portrayal. 
     
     
         41 . The non-transitory computer-readable medium of  claim 32 , wherein the deriving instructions further comprise instructions for determining whether ones of the stimulus-response pairs are in range of a social response profile for the social robot.