Robot Doorsill Area Detection for Jam-Prone Floor Transitions

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Cleaning robots often jam at doorsill areas during sweeping, leading to prolonged sweeping time and poor cleaning efficiency due to difficulties in identifying and effectively treating these areas.

Innovation Solution

A method and apparatus for identifying doorsill areas by determining jam-prone areas based on escape information and obstacle height, using a neural network classifier to enhance accuracy and identify doorsill-like areas, thereby improving sweeping efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If cleaning robots perform general sweeping without specific doorsill identification, then the sweeping process is simple, but the robot jams frequently at doorsill areas leading to prolonged sweeping time

Engineering Contradiction:
Improvesweeping efficiencyVSAvoidsweeping time
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary identification of doorsill areas by analyzing escape information and obstacle height data before executing the sweeping operation. This allows the robot to pre-map jam-prone areas and plan appropriate escape actions, preventing repeated jamming and time loss during the actual sweeping process

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system uses escape information (positions where the robot previously jammed and performed escape actions) as feedback to identify and mark doorsill areas. This feedback mechanism allows the robot to learn from past jamming experiences and improve its navigation and cleaning efficiency in subsequent operations

Inventive Principle:
Principle #23Feedback

2Measurement precision

If the system identifies doorsill areas using detailed obstacle analysis and neural network classification, then identification accuracy improves, but computational load increases

Engineering Contradiction:
Improvedoorsill area identification accuracyVSAvoidcomputational load
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The identification process is segmented into multiple stages: first filtering areas with continuous obstacles of preset height, then applying neural network classification only to candidate jam-prone areas. This segmentation reduces the computational load by limiting complex processing to relevant regions rather than the entire mapping area

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system applies neural network classification selectively to candidate doorsill areas identified through preliminary obstacle analysis, rather than processing all areas uniformly. This partial application of complex computation achieves high identification accuracy while minimizing unnecessary computational overhead

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP4621610A1Doorsill area identification method and apparatus, medium, and electronic device
Publication Date: 2025.09.24 BEIJING ROBOROCK INNOVATION TECH CO LTD
  • EP4621610A1 patent drawingFigure 1~2
  • EP4621610A1 patent drawingFigure 3~4
  • EP4621610A1 patent drawingFigure 5A

AI summary

The present disclosure provides a doorsill area identification method, a doorsill area identification apparatus, a computer-readable storage medium, and an electronic device. The method comprises: on the basis of escape information from the cleaning process of a cleaning robot, determining a first area of easy entrapment; determining a first area of easy entrapment having a continuous obstacle of a preset height as a second area of easy entrapment; and according to the second area of easy entrapment and information of a room map in which the second area of easy entrapment is located, determining whether the second area of easy entrapment is a doorsill area. The method may identify a doorsill area in a cleaning area.