Robot Head and Torso Control via Smartphone Face Orientation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing telexistence technologies are limited to environments where a head-mounted display is used, preventing their utilization with smartphones or other mobile terminal devices.

Innovation Solution

An information processing device that controls a robot's motion by detecting the orientation of a user's face through a mobile terminal device, using a first and second rotating device to mimic the user's head and torso movements, enabling telexistence without a head-mounted display.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If head-mounted display is used for telexistence, then the user can feel present at the robot's location, but the system cannot be used with smartphones or other mobile terminal devices

Engineering Contradiction:
Improvedevice compatibilityVSAvoidsystem configuration
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system is designed to work with multiple types of terminal devices including smartphones, tablets, and computers by providing a universal interface that adapts to different device form factors. The web browser-based access method allows any device with a web browser to connect to the telexistence system without requiring device-specific applications or configurations.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

A web server acts as an intermediary between the robot controller and various terminal devices. The web server provides a standardized interface that translates between different device input methods and the robot control protocol, enabling universal access while maintaining system integrity.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If the robot uses a three-axis rotation mechanism to change head and torso position, then the robot can accurately follow user gaze, but the system requires head-mounted display which limits accessibility

Engineering Contradiction:
Improvegaze tracking accuracyVSAvoiduser accessibility
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces the requirement for head-mounted displays with software-based gaze tracking implemented through web browsers. The system uses the user's device camera or existing browser capabilities to detect eye gaze direction, substituting the mechanical head-mounted display system with a software solution that works on any mobile device.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system creates a virtual representation of the user's gaze direction by analyzing camera images or browser input data. This virtual gaze model is then transmitted to the robot, which replicates the user's viewing direction through its own camera and display system, achieving the same effect without requiring physical head-mounted equipment.

Inventive Principle:
Principle #26Copying

Data Source

PatentUS12472638B2Information processing device, robot, and mobile terminal device
Publication Date: 2025.11.18 SONY INTERACTIVE ENTERTAINMENT LLC
  • US12472638B2 patent drawing
  • US12472638B2 patent drawing
  • US12472638B2 patent drawing

AI summary

Provided is an information processing device that controls a motion of a robot having a torso and a head. The information processing device includes an acquisition section that acquires an image of a face of a user that is captured by a camera of a mobile terminal device, a motion detection section that detects an orientation of the face of the user from the acquired image, a control signal generation section that generates a control signal for rotating the first or the second rotating device of the robot according to the detected orientation of the face of the user, and a transmission section that transmits the generated control signal to the robot.