Robotic Vacuum Vision-Based Cliff Detection for Advance Path Planning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing robotic vacuum cleaners face challenges in detecting cliffs, such as stairs, which can lead to damage when not detected in time, as they often rely on reflective infrared sensors that only detect obstacles as they are encountered, making it difficult to plan a cleaning path effectively.

Innovation Solution

A method and device that use a light source to illuminate the surface, capture images with a camera, and determine distances to objects, comparing these distances to detect cliffs by identifying a significant increase, allowing for advanced cliff detection and inclusion in navigation planning.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If reflective infrared sensors are used for cliff detection, then the robot can detect cliffs as they are encountered, but it becomes difficult to plan a cleaning path in advance

Engineering Contradiction:
Improvecliff detection reliabilityVSAvoidpath planning time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent applies preliminary action by using a light source and camera to capture images of the surface ahead of the robot, allowing cliff detection before the robot actually encounters the cliff. This enables advance path planning while maintaining reliable cliff detection, as the system processes images captured in advance rather than relying on reactive infrared sensors that only detect cliffs at the moment of encounter

Inventive Principle:
Principle #10Preliminary action

2Device complexity

If the robot detects cliffs only as they are encountered, then the detection system remains simple, but the robot cannot effectively plan its cleaning path

Engineering Contradiction:
Improvedetection system complexityVSAvoidcleaning efficiency
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The system uses a light source and camera to capture images of the surface in advance, enabling the robot to identify cliffs before encountering them. This allows for effective path planning and improves cleaning productivity by allowing the robot to navigate around cliffs efficiently rather than reacting at the last moment, while keeping the detection system relatively simple

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent replaces the mechanical/optical infrared sensing system with a vision-based system using a camera and light source. This substitution enables advance detection and image processing, allowing the robot to plan its path effectively while maintaining a relatively simple detection apparatus

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

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 the robotic cleaning device to detect cliffs before encountering them, allowing for safe navigation and planning of a cleaning path, enabling high-speed approach and effective cleaning around obstacles.

Implementation Method 1

illuminating the surface with at least one light source

Methodology Applied
Scientific EffectLight emission: Light

Implementation Method 2

capturing an image of the surface

Methodology Applied
Scientific EffectImage capture: Photography

Data Source

PatentUS11169533B2Robotic cleaning device and a method at the robotic cleaning device of performing cliff detection
Publication Date: 2021.11.09 AB ELECTROLUX
  • US11169533B2 patent drawing
  • US11169533B2 patent drawing
  • US11169533B2 patent drawing

AI summary

A robotic cleaning device and a method at the robotic cleaning device of performing cliff detection along a surface over which the robotic cleaning device moves. The method includes illuminating the surface with at least one light source, capturing an image of the surface, detecting at least one illuminated section in the captured image, and determining distance to objects in the at least one illuminated section of the captured image. The method further comprises comparing at least two of the determined distances and detecting an object in the captured image as a cliff when cliff when a relation between the at least two compared determined distances complies with a predetermined increase criterion.