Cleaning Robot Camera-to-Floorplan Transformation for User Interaction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current cleaning robot maps are optimized for robotic navigation and not suitable for human interaction, limiting user control and customization.

Innovation Solution

A bird's eye view planar map is generated by transforming robot camera images into a planar view, corrected for distortion, and displayed on user interfaces like smartphones, allowing users to input modifications such as no-go areas and cleaning intensity adjustments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If robot camera images are used to create maps, then the robot can navigate and clean effectively, but the maps are not suitable for human interaction and user control

Engineering Contradiction:
Improveuser interaction with mapVSAvoidgeometric accuracy for navigation
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The system separates map processing into two distinct segments: a navigation-optimized map for robot movement and a user-optimized floorplan for human interaction. Each segment serves its specific purpose without compromising the other, allowing geometric accuracy to be preserved in the navigation map while creating a simplified, user-friendly representation for the floorplan.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system creates a simplified copy of the navigation map tailored for human users. This floorplan copy transforms complex camera-based navigation data into an intuitive bird's-eye view that preserves essential spatial relationships while removing unnecessary geometric complexity, making it suitable for user interaction without losing critical layout information.

Inventive Principle:
Principle #26Copying

2Area of stationary object

If a camera is mounted high in the robot housing to provide an angled downward view, then a broader floor area can be captured, but the images contain distortion that requires correction

Engineering Contradiction:
Improvefloor area capturedVSAvoidimage geometric accuracy
Core Design Contradiction:
Area of stationary objectVSManufacturing precision

Solution Approach 1:

The system applies distortion correction algorithms as a preliminary step before creating the floorplan. By pre-correcting the geometric distortion in captured images based on the known camera mounting position and angle, the system ensures that subsequent map generation processes work with accurate geometric data, eliminating the need for complex real-time corrections during navigation.

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If images are captured at high resolution to provide detailed floorplan information, then user interaction precision improves, but processing power and storage requirements increase

Engineering Contradiction:
Improvefloorplan detail resolutionVSAvoidprocessing power consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system applies different resolution qualities to different regions of the floorplan based on user interaction needs. High-detail areas are captured and processed only where necessary for user decision-making, while other areas use lower resolution. This localized quality adjustment maintains measurement precision where needed while significantly reducing overall processing power consumption and storage requirements.

Inventive Principle:
Principle #3Local quality

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 effective human interaction with cleaning robots by providing a user-friendly interface for controlling navigation and cleaning operations, enhancing user experience and robot efficiency.

Implementation Method 1

The camera can capture images of an area to be cleaned, and show objects in that area

Methodology Applied
Scientific EffectPhotography: Photography

Implementation Method 2

The camera's field of view is captured as an image

Methodology Applied
Scientific EffectPhotoelectric Effect: Photoelectric Effect

Implementation Method 3

a lens (e.g., fish-eye lens) is used in front of the camera

Methodology Applied
Scientific EffectRefraction: Refraction

Implementation Method 4

a lens (e.g., fish-eye lens) is used in front of the camera. Before (or after) transforming from the robot perspective view to the planar view, a distortion algorithm is applied to correct the image distortion due to the lens

Methodology Applied
Scientific EffectLens: Lens

Data Source

PatentUS10638906B2Conversion of cleaning robot camera images to floorplan for user interaction
Publication Date: 2020.05.05 VORWERK & CO INTERHOLDING GMBH
  • US10638906B2 patent drawing
  • US10638906B2 patent drawing
  • US10638906B2 patent drawing

AI summary

In one embodiment, a method is disclosed for a robot (e.g., cleaning robot) to produce a bird's eye view (planar) map by transforming from a robot camera view and stitching together images tagged by location. The planar map can then be presented on a user interface as a floorplan, showing the location of objects (such as rugs). A camera is mounted in the cleaning robot sufficiently high in the cleaning robot housing to provide an angled view downward at a floor. The camera's field of view is captured as an image, and a portion or segment of that image is cropped. The cropped segment is transformed from the camera perspective to a planar view (before or after cropping), and is combined with other images to form a map of a floorplan.