Abstract: A system includes a computing platform having a hardware processor and a memory storing software code, a memory data structure storing memory features for an artificial intelligence interactive character (AIIC), and a trained machine learning (ML) model. The hardware processor executes the software code to receive interaction data describing a communication by a user with the AIIC, predict, using the trained ML model and the interaction data, at least one user memory feature(s) of the communication, and identify, using the memory data structure, one or more of the memory features for the AIIC as corresponding to the user memory feature(s). The software code also determines, using the user memory feature(s) and the corresponding one or more of the memory features for the AIIC, an interactive communication for execution by the AIIC in response to the communication by the user; and outputs the interactive communication to the AIIC.

Abstract: A system includes a computing platform having a hardware processor and a memory storing software code, a memory data structure storing memory features for an artificial intelligence interactive character (AIIC), and a trained machine learning (ML) model. The software code is executed to elicit, using the AIIC, a reminiscence from a user, predict, using the trained ML model and the reminiscence, one or more user memory feature(s) of the reminiscence, identify, using the memory data structure, one or more of the memory features for the AIIC as corresponding to the user memory feature(s), and determine, using the user memory feature(s), a mood modifier for a creative composition. The software code is further executed to produce, based on the mood modifier and the corresponding one or more of the plurality of memory features for the AIIC, the creative composition, and provide the creative composition to the AIIC.

Abstract: A system for monitoring and improving social agent interaction quality includes a computing platform having processing hardware and a system memory storing a software code. The processing hardware is configured to execute the software code to receive, from a social agent, interaction data describing an interaction of the social agent with a user, and to perform an assessment of the interaction, using the interaction data, as one of successful or including a flaw. When the assessment indicates that the interaction includes the flaw, the processing hardware is further configured to execute the software code to identify an interaction strategy for correcting the flaw, and to deliver, to the social agent, one or both of the assessment and the interaction strategy to correct the flaw in the interaction.

Abstract: A system for performing automated multi-persona response generation includes processing hardware, a display, and a memory storing a software code. The processing hardware executes the software code to receive input data describing an action and identifying a multiple interaction profiles corresponding respectively to multiple participants in the action, obtain the interaction profiles, and simulate execution of the action with respect to each of the participants. The processing hardware is further configured to execute the software code to generate, using the interaction profiles, a respective response to the action for each of the participants to provide multiple responses. In various implementations, one or more of those multiple responses may be used to train additional artificial intelligence (AI) systems, or may be rendered to an output device in the form of one or more of a display, an audio output device, or a robot, for example.

Abstract: Systems and methods are presented for immersive and simultaneous animation in a mixed reality environment. Techniques disclosed represent a physical object, present at a scene, in a 3D space of a virtual environment associated with the scene. A virtual element is posed relative to the representation of the physical object in the virtual environment. The virtual element is displayed to users from a perspective of each user in the virtual environment. Responsive to an interaction of one user with the virtual element, an edit command is generated and the pose of the virtual element is adjusted in the virtual environment according to the edit command. The display of the virtual element to the users is then updated according to the adjusted pose. When simultaneous and conflicting edit commands are generated by collaborating users, policies to reconcile the conflicting edit commands are disclosed.

Abstract: A system for providing a situationally aware social agent includes processing hardware and a memory storing a software code. The processing hardware executes the software code to receive radar data and audio data, process the radar data and the audio data to obtain radar-based location data and audio-based location data each corresponding to a location of one or more user(s), and process the radar data and the audio data to obtain radar-based venue data and audio-based venue data each corresponding to an environment surrounding the user(s). The software code further determines, using the radar-based location data and the audio-based location data, the location of the user(s), determines, using the radar-based venue data and the microphone-based venue data, the environment surrounding the user(s), and identifies, based on the location and the environment, an interactive expression for use by the situationally aware social agent to interact with the user(s).

Abstract: A system for monitoring and improving social agent interaction quality includes a computing platform having processing hardware and a system memory storing a software code. The processing hardware is configured to execute the software code to receive, from a social agent, interaction data describing an interaction of the social agent with a user, and to perform an assessment of the interaction, using the interaction data, as one of successful or including a flaw. When the assessment indicates that the interaction includes the flaw, the processing hardware is further configured to execute the software code to identify an interaction strategy for correcting the flaw, and to deliver, to the social agent, one or both of the assessment and the interaction strategy to correct the flaw in the interaction.

Abstract: A system providing an interactive social agent can include a computing platform having a hardware processor and a memory storing a training content standardization software code configured to receive content depicting human expressions and including annotation data describing the human expressions from multiple content annotation sources, generate a corresponding content descriptor for each content annotation source to translate the annotation data into a standardized data format, and transform the annotation data into the standardized data format using the corresponding content descriptor. The content and the annotation data in the to standardized format are stored as training data for use in training expressions for the interactive social agent.

Abstract: A multi-party conversational agent includes a computing platform having a hardware processor and a memory storing a software code. The hardware processor is configured to execute the software code to identify a first predetermined expression for conversing with a group of people, and to have a group conversation, using the first predetermined expression, with at least some members of the group. The hardware processor is configured to further execute the software code to identify, while having the group conversation, a second predetermined expression for having a dialogue with at least one member of the group, and to interrupt the group conversation to have the dialogue, using the second predetermined expression, with the at least one member of the group.

Abstract: A system for incremental natural language understanding includes a media module, a memory storing a software code, and a hardware processor communicatively coupled to the media module. The hardware processor is configured to execute the software code to receive an audio stream including a first utterance, and generate a first and second incremental speech recognition outputs based on first and second portions of the first utterance. In addition, the hardware processor is configured to execute the software code to determine, prior to generating the second incremental speech recognition output, a first intent of the first utterance based on the first incremental speech recognition output. The hardware processor is further configured to execute the software code to retrieve a first resource based on the determined first intent, and incorporate the first resource in the media content to be played by the media module.

Abstract: A multi-party conversational agent includes a computing platform having a hardware processor and a memory storing a software code. The hardware processor is configured to execute the software code to identify a first predetermined expression for conversing with a group of people, and to have a group conversation, using the first predetermined expression, with at least some members of the group. The hardware processor is configured to further execute the software code to identify, while having the group conversation, a second predetermined expression for having a dialogue with at least one member of the group, and to interrupt the group conversation to have the dialogue, using the second predetermined expression, with the at least one member of the group.

Abstract: A system for incremental natural language understanding includes a media module, a memory storing a software code, and a hardware processor communicatively coupled to the media module. The hardware processor is configured to execute the software code to receive an audio stream including a first utterance, and generate a first and second incremental speech recognition outputs based on first and second portions of the first utterance. In addition, the hardware processor is configured to execute the software code to determine, prior to generating the second incremental speech recognition output, a first intent of the first utterance based on the first incremental speech recognition output. The hardware processor is further configured to execute the software code to retrieve a first resource based on the determined first intent, and incorporate the first resource in the media content to be played by the media module.

Abstract: A system for sensing and controlling eye contact for a robot. The system includes a robotic figure with a movable eye. The system includes a light source positioned in the robotic figure to output light through a light outlet of the eye. A light sensor is included that senses light striking surfaces in a physical space in which the robotic figure is positioned including the output light from the light source. The system includes an image processor processing output of the light sensor to identify a location of a target formed by the output light striking surfaces in the physical space and to identify a location of a face of a human. Further, the system includes a robot controller generating eye movement control signals based on the location of the target and the location of the face to position the eye to provide eye contact with the human observer.

Abstract: A system for sensing and controlling eye contact for a robot. The system includes a robotic figure with a movable eye. The system includes a light source positioned in the robotic figure to output light through a light outlet of the eye. A light sensor is included that senses light striking surfaces in a physical space in which the robotic figure is positioned including the output light from the light source. The system includes an image processor processing output of the light sensor to identify a location of a target formed by the output light striking surfaces in the physical space and to identify a location of a face of a human. Further, the system includes a robot controller generating eye movement control signals based on the location of the target and the location of the face to position the eye to provide eye contact with the human observer.

Abstract: According to one implementation, an affect-driven dialog generation system includes a computing platform having a hardware processor and a system memory storing a software code including a sequence-to-sequence (seq2seq) architecture trained using a loss function having an affective regularizer term based on a difference in emotional content between a target dialog response and a dialog sequence determined by the seq2seq architecture during training. The hardware processor executes the software code to receive an input dialog sequence, and to use the seq2seq architecture to generate emotionally diverse dialog responses based on the input dialog sequence and a predetermined target emotion. The hardware processor further executes the software code to determine, using the seq2seq architecture, a final dialog sequence responsive to the input dialog sequence based on an emotional relevance of each of the emotionally diverse dialog responses, and to provide the final dialog sequence as an output.

Abstract: A system providing an interactive social agent can include a computing platform having a hardware processor and a memory storing a training content standardization software code configured to receive content depicting human expressions and including annotation data describing the human expressions from multiple content annotation sources, generate a corresponding content descriptor for each content annotation source to translate the annotation data into a standardized data format, and transform the annotation data into the standardized data format using the corresponding content descriptor. The content and the annotation data in the to standardized format are stored as training data for use in training expressions for the interactive social agent.

Abstract: According to one implementation, an affect-driven dialog generation system includes a computing platform having a hardware processor and a system memory storing a software code including a sequence-to-sequence (seq2seq) architecture trained using a loss function having an affective regularizer term based on a difference in emotional content between a target dialog response and a dialog sequence determined by the seq2seq architecture during training. The hardware processor executes the software code to receive an input dialog sequence, and to use the seq2seq architecture to generate emotionally diverse dialog responses based on the input dialog sequence and a predetermined target emotion. The hardware processor further executes the software code to determine, using the seq2seq architecture, a final dialog sequence responsive to the input dialog sequence based on an emotional relevance of each of the emotionally diverse dialog responses, and to provide the final dialog sequence as an output.

Abstract: According to the present disclosure, a method for securing a threaded fastener in a threaded hole includes directly applying a locking compound to at least a portion of threads to be mated on either the threaded fastener or the threaded hole. The locking compound includes a substantially pure, non-chromated aluminum pigmented compound suspended in a water-based inorganic binder with temperature resistance in excess of 900 degrees Fahrenheit (about 482 degrees Celsius). The threaded fastener is threaded into the threaded hole after applying the locking compound on the threads to be mated.

Abstract: According to the present disclosure, a method for securing a threaded fastener in a threaded hole includes directly applying a locking compound to at least a portion of threads to be mated on either the threaded fastener or the threaded hole. The locking compound includes a substantially pure, non-chromated aluminum pigmented compound suspended in a water-based inorganic binder with temperature resistance in excess of 900 degrees Fahrenheit (about 482 degrees Celsius). The threaded fastener is threaded into the threaded hole after applying the locking compound on the threads to be mated.

Abstract: An assembly includes a threaded hole, a threaded fastener, and a locking compound. The threaded fastener is positioned in the threaded hole with a portion of fastener threads mated with a corresponding portion of hole threads. The locking compound is between the mated fastener threads and hole threads. The locking compound includes an aluminum pigmented compound suspended in a water-based inorganic binder.