Robot Doorsill Area Detection for Jam-Prone Floor Transitions
Find Innovative SolutionsGenerate 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
Engineering 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
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
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
2Measurement precision
If the system identifies doorsill areas using detailed obstacle analysis and neural network classification, then identification accuracy improves, but computational load increases
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
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
Data Source
Figure 1~2
Figure 3~4
Figure 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.