Social Robot Action Control for User Interaction Style Matching

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing robots struggle to perform actions that match the interaction style of the user, leading to unnatural communication and reduced user engagement.

Innovation Solution

A robot equipped with an acquisition unit to gather information on user contact and an action control unit to perform actions that induce a favorable response based on the user's interaction style, utilizing a learning device with a state observation unit and learning unit to generate a learning model for robot actions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the robot changes action based on whether contact is comfortable for the robot, then the robot's comfort is improved, but the interaction style matching the user's desire deteriorates

Engineering Contradiction:

Improverobot comfortVSAvoidinteraction style matching

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

Instead of determining whether user contact is comfortable for the robot and changing actions based on that, the invention inverts the approach by determining whether the contact matches the user's desired interaction style, and changes actions to match the user's style rather than robot comfort

Inventive Principle:

Principle #13The other way round (Inversion)

Solution Approach 2:

The invention changes the parameter used for action determination from 'robot comfort assessment' to 'user interaction style assessment', fundamentally altering the control parameter to achieve better user alignment

Inventive Principle:

Principle #35Parameter changes

2Reliability

If the robot performs actions based on its own comfort assessment, then the robot's operational reliability is improved, but the naturalness of communication deteriorates

Engineering Contradiction:

Improveoperational reliabilityVSAvoidcommunication naturalness

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The invention inverts the basis for action selection from robot-centered comfort assessment to user-centered interaction style matching, making communication more natural by aligning with user expectations rather than robot operational comfort

Inventive Principle:

Principle #13The other way round (Inversion)

3Device complexity

If the robot uses simple contact detection, then the device complexity is reduced, but the ability to understand user interaction style deteriorates

Engineering Contradiction:

Improvesystem complexityVSAvoidinteraction style understanding

Core Design Contradiction:

Device complexityVSAdaptability or versatility

Solution Approach 1:

The invention changes the analytical parameter from simple contact detection to interaction style determination, using machine learning to extract meaningful patterns from contact data without requiring complex additional hardware

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentEP4596075A1Robot, learning device, control method, and program

Publication Date: 2025.08.06 NITTO DENKO CORP

Figure 1
Figure 2
Figure 3

AI summary

Actions that do not match an interaction style of a user are reduced. A robot includes an acquisition unit configured to acquire information on contact of a user with respect to the robot; and an action control unit configured to instruct to perform a predetermined action that induces a favorable reaction of the user in accordance with a state of an interaction style of the user based on the information on the contact.