AI Cleaner Zone-Based Route Planning to Reduce Repeated Coverage

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Robot cleaners inefficiently clean spaces due to inadequate route planning, often getting stuck or repeating areas, as they consider only a limited radius and not the entire cleaning area, leading to uneven cleaning times and potential movement restrictions.

Innovation Solution

An artificial intelligence cleaner that divides the cleaning space into areas based on cleaning logs, sets a cleaning route, and adjusts cleaning modes and priorities for each area type, using machine learning algorithms to optimize cleaning efficiency and reduce the likelihood of failure.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If the robot cleaner performs cleaning while avoiding obstacles in a predetermined radius around the cleaner, then the cleaner can navigate locally, but it wanders in previously visited areas and repeats cleaning the same areas

Engineering Contradiction:
Improvelocal navigation capabilityVSAvoidcleaning efficiency
Core Design Contradiction:
Ease of operationVSProductivity

Solution Approach 1:

The patent divides the cleaning space into multiple zones (first cleaning zone, second cleaning zone, third cleaning zone) based on obstacle density and cleaning status. The cleaner selectively operates in different zones according to predetermined criteria, preventing it from repeatedly cleaning the same areas while maintaining local navigation capabilities.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements dynamic zone classification where cleaning zones are updated in real-time based on the cleaner's position, obstacle detection, and cleaning progress. The cleaner dynamically transitions between zones (e.g., from first to second cleaning zone when obstacles are detected), enabling adaptive route planning that improves cleaning efficiency while maintaining local avoidance capabilities.

Inventive Principle:
Principle #15Dynamics

2Area of stationary object

If the robot cleaner operates in areas with many obstacles, then it can cover more ground, but cleaning takes a long time and movement is restricted

Engineering Contradiction:
Improvecleaning coverage areaVSAvoidcleaning time
Core Design Contradiction:
Area of stationary objectVSLoss of time

Solution Approach 1:

The patent applies different cleaning strategies to different zones based on their characteristics. In the first cleaning zone (low obstacle density), the cleaner performs thorough cleaning. In the second cleaning zone (high obstacle density), the cleaner adjusts its path to minimize time loss while still covering the area. This localized adaptation allows the cleaner to cover more ground without excessive time penalty.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent pre-classifies the cleaning space into zones with different obstacle densities before cleaning begins. This preliminary classification allows the cleaner to plan its route in advance, knowing which areas will require more time and which can be covered quickly, thereby optimizing the overall cleaning time while maintaining extensive coverage.

Inventive Principle:
Principle #10Preliminary action

3Device complexity

If the robot cleaner uses a fixed cleaning route, then the cleaning process is simple to control, but certain areas are cleaned more than others and efficiency is reduced

Engineering Contradiction:
Improvecontrol simplicityVSAvoidcleaning efficiency
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The patent implements a dynamic zone-based cleaning system where the cleaner transitions between different cleaning zones (first, second, third zones) based on real-time conditions such as obstacle detection and cleaning progress. This dynamic approach allows the cleaning route to adapt to the environment, ensuring uniform cleaning coverage across all areas while maintaining relatively simple control logic through predetermined zone transition rules.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3949817B1Artificial intelligence cleaner and operation method thereof
Publication Date: 2024.05.01 LG ELECTRONICS INC
  • EP3949817B1 patent drawingFigure 1
  • EP3949817B1 patent drawingFigure 2
  • EP3949817B1 patent drawingFigure 3

AI summary

Disclosed herein is an artificial intelligence cleaner. The artificial intelligence cleaner includes a memory configured to store a simultaneous localization and mapping (SLAM) map for a cleaning space; a driving unit configured to drive the artificial intelligence cleaner; and a processor configured to collect a plurality of cleaning logs for the cleaning space, divide the cleaning space into a plurality of cleaning areas using the SLAM map and the collected plurality of cleaning logs, determine a cleaning route of the artificial intelligence cleaner in consideration of the divided cleaning areas, and control the driving unit according to the determined cleaning route.