Method for detecting obstacle, self-moving robot, and non-transitory computer readable storage medium
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cleaning robots, such as sweeping robots, can only identify certain types of obstacles and fail to detect low-height obstacles due to the limitations of their laser devices, leading to poor user experience.
Innovation Solution
A method for detecting obstacles using image acquisition apparatuses to transform obstacle information into depth information, convert it into a point cloud map, and analyze a valid height range to determine the presence and size of obstacles, allowing for accurate obstacle detection and navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a laser device is disposed on the top surface of the sweeping robot to detect obstacles, then the robot can identify obstacles around it, but it cannot detect low-height obstacles because the laser device can only detect obstacles higher than the robot itself
Solution Approach 1:
The patent transitions from horizontal laser detection to vertical image-based depth detection. By capturing images from the front and back of the robot and processing them into depth maps, the system can detect obstacles in the vertical dimension (including low-height obstacles) that were previously undetectable by horizontal laser scanning.
Solution Approach 2:
The patent introduces an image processing system as an intermediary between the robot's sensors and obstacle detection. The image acquisition apparatus captures visual information, which is then processed through depth map generation and point cloud analysis to detect obstacles, serving as a mediator that overcomes the limitations of direct laser detection.
2Reliability
If the laser device emits and receives signals in the horizontal direction, then it can identify obstacles around the sweeping robot, but it fails to detect low-height obstacles resulting in poor user experience
Solution Approach 1:
The image acquisition apparatus serves multiple functions: it captures images for depth mapping, identifies obstacle locations, determines obstacle heights, and enables detection across various detection angles. This multi-functional approach replaces the single-function horizontal laser detection, improving both reliability and user experience.
3Loss of information
If the sweeping robot uses image matching with a database to identify obstacles, then it can recognize specific obstacle types, but it can only identify limited types of obstacles and misses low-height obstacles
Solution Approach 1:
The patent merges image-based depth information with point cloud mapping technology to create a comprehensive obstacle detection system. By combining front and back images, generating depth maps, and creating point cloud representations, the system achieves both obstacle type recognition and complete detection including low-height obstacles that were previously missed.
Data Source
AI summary
A method for detecting an obstacle, applied to a self-moving robot, including: transforming obstacle information into depth information; converting the depth information into a point cloud map, and determining coordinate data of a reference point on the obstacle; determining a valid analysis range in a height direction in the point cloud map; and determining, based on the coordinate data of the reference point, whether an obstacle is present within the valid analysis range.