Companion Robot Digital Twin for Personalized Interaction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing intelligent robots cannot meet the higher accompanying requirements of parents for their children or elderly individuals, as they lack the ability to effectively mimic the behavior and interaction patterns of a companion person when the companion is not present.
Innovation Solution
A robot control method and device that collects interaction information from a companion target and uses machine learning algorithms to generate interaction content and manner, mimicking the behavior of a companion person by utilizing digital person information, including personal and behavioral data, to engage with the companion target.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the robot uses basic communication functions to interact with the companion target, then the robot can communicate with the child, but the robot cannot meet the higher accompanying requirement of parents for personalization and emotional connection
Solution Approach 1:
The patent creates a digital twin (virtual image) of the companion person that copies their behavioral patterns, communication styles, and interaction preferences. This digital twin enables the robot to mimic the companion's way of interacting with the child, providing personalized accompaniment without requiring the actual companion person to be physically present. The copying principle resolves the contradiction by capturing essential characteristics of the companion person in a simplified digital form that the robot can execute.
Solution Approach 2:
The system performs preliminary data collection and analysis to build the digital twin of the companion person before the robot needs to interact with the child. By pre-processing the companion person's communication patterns, behavioral data, and interaction history, the system prepares the digital model in advance, enabling the robot to immediately replicate authentic companion-like interactions without real-time complexity.
2Reliability
If the robot collects and processes interaction information to imitate the companion person, then the robot can meet personal accompaniment requirements, but the data processing and machine learning operations increase computational complexity
Solution Approach 1:
The patent extracts only the essential and relevant features from the companion person's interaction data to build the digital twin. Instead of processing all possible data, the system identifies and extracts key behavioral patterns, communication styles, and interaction preferences that are most important for authentic accompaniment. This extraction principle reduces computational complexity while maintaining high reliability in the robot's accompaniment quality.
Solution Approach 2:
The digital twin focuses on capturing local qualities or specific aspects of the companion person's behavior rather than attempting to replicate every detail. The system concentrates computational resources on modeling the most salient interaction patterns and communication characteristics that matter for the child-companion interaction, rather than uniformly processing all possible behavioral data.
3Adaptability or versatility
If the robot uses simple interaction patterns, then the robot can respond to the companion target, but the interaction lacks the depth and personalization that parents expect from intelligent robots
Solution Approach 1:
The robot copies the companion person's interaction patterns, communication style, and behavioral preferences into a digital twin model. This copying approach enables the robot to automatically replicate personalized interactions without requiring complex real-time decision-making or deep machine learning algorithms during actual interaction. The personalization is pre-captured in the digital twin, resolving the contradiction between personalization quality and automation complexity.
Data Source
AI summary
The present invention provides a robot control method, and the method includes: collecting interaction information of a companion target, and obtaining digital person information of a companion person (101), where the interaction information includes interaction information of a sound or an action of the companion target toward the robot, and the digital person information includes a set of digitized information of the companion person; and determining, by using the interaction information and the digital person information, a manner of interacting with the companion target (103); generating, based on the digital person information of the companion person and by using a machine learning algorithm, an interaction content corresponding to the interaction manner (105); and generating a response action toward the companion target based on the interaction manner and the interaction content (107).