Robot Cleaner Sound Source Detection for Ambient Noise Monitoring

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current robot cleaners lack the ability to accurately detect the direction and position of sound sources and recognize specific event sounds amidst ambient noise, limiting their effectiveness in monitoring situations and responding to abnormal events.

Innovation Solution

A robot cleaner equipped with a sound input unit using multiple microphones to differentiate between event and environmental sounds, a control unit to determine the sound source's direction and position, and a communication unit to transmit information, allowing for precise sound recognition and automated response.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If multiple microphones are used to detect sound source direction and position, then sound recognition precision is improved, but device complexity increases

Engineering Contradiction:
Improvesound source direction and position detection precisionVSAvoidmicrophone array complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent divides the sound detection function into multiple independent microphones positioned at different locations. Each microphone independently captures sound signals, and the control unit processes signals from multiple microphones to determine sound source direction and position through signal comparison and time difference analysis, thereby improving measurement precision without requiring a single complex detection device

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent combines multiple microphones and their signal processing functions into an integrated sound recognition system. The control unit merges signals from multiple microphones, performs correlation analysis, and determines sound source characteristics, achieving improved precision while managing system complexity through unified control

Inventive Principle:
Principle #5Merging (Combining)

2Reliability

If sound recognition function is updated using ambient sound, then sound recognition reliability is improved, but loss of time for updating occurs

Engineering Contradiction:
Improvesound recognition reliabilityVSAvoidsound recognition function update time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent performs preliminary sound recognition function updates by collecting and analyzing ambient sounds during normal operation periods. The control unit accumulates sound data and updates recognition models in advance, so that when actual sound detection is needed, the system already has refined recognition capabilities, reducing the time loss associated with updates

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements continuous sound recognition function updates by continuously collecting ambient sound data during robot operation. The control unit continuously refines the sound recognition model based on accumulated data, making the update process ongoing rather than periodic, thereby maintaining reliability improvement without significant time interruption to the robot's useful functions

Inventive Principle:
Principle #20Continuity of useful action

3Loss of information

If robot cleaner moves to detected sound source position, then monitoring capability is improved, but productivity for cleaning tasks decreases

Engineering Contradiction:
Improvemonitoring capabilityVSAvoidcleaning task completion rate
Core Design Contradiction:
Loss of informationVSProductivity

Solution Approach 1:

The patent implements partial movement to sound source positions rather than complete relocation. When a sound source is detected, the robot cleaner moves partially toward the sound source to capture image information or verify the situation, then returns to its cleaning task. This partial action provides sufficient monitoring capability while minimizing disruption to cleaning productivity

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The patent employs periodic sound detection and selective movement rather than continuous movement. The control unit periodically checks for sound sources during cleaning operations and only triggers movement when abnormal sounds are detected. This periodic approach maintains monitoring capability while ensuring that cleaning tasks proceed uninterrupted during normal periods

Inventive Principle:
Principle #19Periodic 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

Enables robust and precise sound recognition, enabling the robot cleaner to move towards detected sound sources, capture image information, and provide alerts via a communication network, enhancing monitoring capabilities and preventing blind spots, with potential applications in security and safety services.

Implementation Method 1

a sound input unit having one or more microphones, and configured to receive an ambient sound

Methodology Applied
Scientific EffectAcoustic signal detection: Sound

Data Source

PatentEP2637073B1Robot cleaner and method for controlling the same
Publication Date: 2019.12.18 LG ELECTRONICS INC
  • EP2637073B1 patent drawingFigure 1~2
  • EP2637073B1 patent drawingFigure 3~4
  • EP2637073B1 patent drawingFigure 5~6

AI summary

Disclosed are a robot cleaner, and a method for controlling the same. Firstly, a sound source direction and a sound source position may be detected by one or more microphones, e,g., three microphones, and a specific event sound may be recognized. Then, the recognized specific event sound may be output to a cleaner body in the form of a message, or may be provided via a communication network. This can allow the circumstances to be easily monitored. Secondly, a sound recognition function may be updated using an ambient sound, for sound recognition from background noise and environmental noise, in a robust and precise manner. This can enhance a sound recognition rate, and improve stability and efficiency. Thirdly, the robot cleaner may be moved to a detected direction or position of a sound source with respect to an event sound. Then, image information may be detected, or whether an abnormal situation has occurred or not may be determined. Such information may be provided via a communication network.