Robot Head Direction Detection Using Thermal Grid

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing robots face challenges in detecting a person's face, especially when the person is facing away, in low-light conditions, or has a low posture, leading to uncomfortable or forced communication scenarios.

Innovation Solution

A robot equipped with a temperature distribution detection unit using a grid of photo-detectors to identify the direction of a person's head, allowing the face unit to be directed accordingly, enhancing natural communication by detecting temperature patterns and differentiating between individuals and objects.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a robot detects a person's face from an image of the surroundings, then communication can be initiated, but the robot fails to detect the person when the person directs away from the robot or in dark places

Engineering Contradiction:
Improveface detection reliabilityVSAvoiddetection capability in various conditions
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent combines multiple detection methods (image-based face detection, temperature distribution detection, and body detection) into a unified detection system. The robot uses the temperature distribution detection unit to detect the person's presence and direction, then uses the image capturing unit to capture the person's face, merging the advantages of both methods to overcome their individual limitations.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces temperature distribution detection as an intermediary method between direct face detection and body detection. The temperature distribution detection unit detects the person's body heat pattern, which serves as an intermediary step to locate the person before capturing their face image, enabling detection in conditions where direct face detection fails.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If the robot uses a predetermined height to differentiate a person from other objects, then differentiation is possible, but persons with low posture cannot be detected

Engineering Contradiction:
Improveobject differentiation precisionVSAvoiddetection of persons with various postures
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent changes the detection parameter from height-based differentiation to temperature distribution-based differentiation. Instead of using a predetermined height threshold to distinguish persons from objects, the system uses the characteristic temperature distribution pattern of the human body, which remains detectable regardless of the person's posture or height.

Inventive Principle:
Principle #35Parameter changes

3Ease of operation

If the robot directs the face unit toward the detected head direction, then natural communication is enhanced, but the robot may wrongly detect faces in pictures as real persons

Engineering Contradiction:
Improvenatural communicationVSAvoidperson detection accuracy
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent performs preliminary temperature distribution detection and body detection before attempting face detection. By first confirming the presence of a living person through temperature detection and then locating their head direction, the system reduces the likelihood of mistakenly detecting faces in pictures, as the preliminary detection steps verify the target is a living person.

Inventive Principle:
Principle #10Preliminary action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The solution enables more reliable and natural communication by accurately detecting a person's head direction, reducing discomfort and increasing the likelihood of voluntary interaction, even in challenging environments.

Implementation Method 1

a temperature distribution detection unit that detects a temperature distribution of a detection region by using a plurality of photo-detectors disposed in a grid form

Methodology Applied
Scientific EffectThermal radiation: Thermal Radiation

Data Source

PatentUS9919429B2Robot, control method, and program
Publication Date: 2018.03.20 NEC CORP
  • US9919429B2 patent drawing
  • US9919429B2 patent drawing
  • US9919429B2 patent drawing

AI summary

A robot (2000) includes a face unit (2020), a temperature distribution detection unit (2040), a head direction calculation unit (2060), and a first face direction change unit (2080). The temperature distribution detection unit (2040) includes a plurality of photo-detectors disposed in a grid form. The temperature distribution detection unit (2040) detects a temperature distribution of a detection region by using the plurality of photo-detectors. The head direction calculation unit (2060) calculates a direction in which a person's head is located, on the basis of the temperature distribution detected by the temperature distribution detection unit (2040). The first face direction change unit (2080) directs the face unit (2020) in the direction calculated by the head direction calculation unit (2060).