Abstract: A system for behaviour mapping and categorization of objects and users in an 3D environment for creating and learning user behaviour map is provided. The system includes a robot 102, a network 104 and a central AI system 106. The robot 102 is embedded with an array of acoustic sensors 108 and visual sensors 110 for behaviour mapping and categorization the objects and users in the 3D environment and generates an auditory behaviour map and a visual behaviour map based on sensory inputs from the acoustic sensors 108 and visual sensors 110. The robot 102 transmits the acoustic source sensory input and the visual source sensory input to the central AI system 106 over the network 104 for generating a global behaviour map. The central AI system 106 tunes the global behaviour map to a specific user by tuning the detection and classification model to data obtained from a specific 3D environment that corresponds to the specific user.

Abstract: A system for user initiated generic conversation with an artificially intelligent machine is provided. The system includes a conversational server (CS) that executes a conversational architecture across multiple devices, a communication network and a remote device. The conversational architecture includes one or more conversational nodes connected by edges which encapsulates flow and logic and transport data between the one or more conversational nodes. The conversational server (CS) receives input, at an input node, from a user through an input modality and performs computation logic that generates output data to pass to an output node.

Abstract: A system for behaviour mapping and categorization of objects and users in an 3D environment for creating and learning user behaviour map is provided. The system includes a robot 102, a network 104 and a central AI system 106. The robot 102 is embedded with an array of acoustic sensors 108 and visual sensors 110 for behaviour mapping and categorization the objects and users in the 3D environment and generates an auditory behaviour map and a visual behaviour map based on sensory inputs from the acoustic sensors 108 and visual sensors 110. The robot 102 transmits the acoustic source sensory input and the visual source sensory input to the central AI system 106 over the network 104 for generating a global behaviour map. The central AI system 106 tunes the global behaviour map to a specific user by tuning the detection and classification model to data obtained from a specific 3D environment that corresponds to the specific user.

Abstract: A system for user initiated generic conversation with an artificially intelligent machine is provided. The system includes a conversational server (CS) that executes a conversational architecture across multiple devices, a communication network and a remote device. The conversational architecture includes one or more conversational nodes connected by edges which encapsulates flow and logic and transport data between the one or more conversational nodes. The conversational server (CS) receives input, at an input node, from a user through an input modality and performs computation logic that generates output data to pass to an output node.

Abstract: A robotic companion device (10) configured for capturing and analysing affective information and semantic information and elicit response accordingly is disclosed herein. It comprises a processor (20) for managing emotional processing and responses configured for capturing and analysing semantic and affective information from sensory devices and communicating with users as well as external world using multitude of actuators and communication devices; a facial arrangement (11) configured for capturing visual information and displaying emotions; a locomotor arrangement (13) enabling movement of the robotic companion device; and microphone/speaker arrangement (15) configured for receiving auditory signal and emitting vocal response. The facial arrangement (11), the locomotor arrangement (13) and the microphone/speaker arrangement (15) are all in communication with the processor (20).

Abstract: A robotic companion device (10) configured for capturing and analysing affective information and semantic information and elicit response accordingly is disclosed herein. It comprises a processor (20) for managing emotional processing and responses configured for capturing and analysing semantic and affective information from sensory devices and communicating with users as well as external world using multitude of actuators and communication devices; a facial arrangement (11) configured for capturing visual information and displaying emotions; a locomotor arrangement (13) enabling movement of the robotic companion device; and microphone/speaker arrangement (15) configured for receiving auditory signal and emitting vocal response. The facial arrangement (11), the locomotor arrangement (13) and the microphone/speaker arrangement (15) are all in communication with the processor (20).