Robot Mower Vision Control for Slope-Aware Boundary Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing intelligent mowers misjudge boundaries and obstacles due to buried underground wires and camera positioning issues, leading to inaccurate navigation and work disruption.
Innovation Solution
A control method that processes captured images to segment sub-regions, uses representative pixel points for boundary and obstacle detection, and adjusts comparison points based on slope angles, combined with machine vision to accurately judge distances and obstacles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If boundaries are set using buried underground wires, then the intelligent mower can sense boundaries, but it costs more manpower and material resources and limits lawn shape flexibility
Solution Approach 1:
The patent replaces the mechanical/electrical boundary wire system with an optical machine vision system. The intelligent mower uses a camera to capture images and process them to detect boundaries and obstacles, eliminating the need for buried wires and their associated installation complexity.
Solution Approach 2:
The patent changes the detection parameter from electrical signals (boundary wire) to optical images (camera capture). By processing image data and analyzing pixel information, the system achieves boundary detection without physical wires, improving ease of manufacture while maintaining reliability.
2Device complexity
If the camera is in a fixed position, then the structure is simple, but the mower may capture distant boundaries or large obstacles and misjudge that it has reached boundaries
Solution Approach 1:
The patent introduces dynamic adjustment of the comparison pixel point position based on the slope angle. As the mower encounters slopes, the system dynamically recalculates where the comparison point should be located in the image, allowing accurate boundary judgment even when the camera captures distant features.
Solution Approach 2:
The patent implements a feedback mechanism where the detected slope angle is used to adjust the comparison pixel point position. The system continuously monitors the terrain, calculates the appropriate comparison point based on the angle, and uses this adjusted reference for boundary detection, improving measurement precision while keeping the camera fixed.
3Device complexity
If the comparison pixel point is fixed, then the processing is simple, but the mower cannot accurately judge boundaries when encountering slopes
Solution Approach 1:
The patent makes the comparison pixel point dynamic rather than fixed. The position of the comparison point is adjusted according to the detected slope angle, allowing the system to adapt to different terrain conditions and maintain reliable boundary judgment on slopes.
Solution Approach 2:
The patent changes the parameter of the comparison pixel point from a fixed coordinate to a dynamically calculated position based on slope angle. This parameter adjustment allows the system to compensate for slope effects and maintain accurate boundary detection across varying terrain.
Data Source
AI summary
A self-working system, a self-walking device, a control method therefor and a computer-readable storage medium are disclosed, wherein the control method may include the following steps: acquiring a captured image; processing the captured image to acquire a processed image; segmenting the processed image into at least one sub-region; respectively acquiring a representative pixel point PLn of each sub-region; calculating, in the processed image, the number of sub-regions of which the representative pixel point PLn is located below a comparison pixel point PC and marking same as the number Nb of special sub-regions, PC being a preset comparison pixel point; if Nb≤1, judging that there is a boundary (2) or obstacle in the distance of the captured image; if Nb>1, judging that there is a boundary (2) or obstacle in the vicinity of the captured image. The subsequent work of the self-walking device is directly judged by means of machine vision, which is more convenient and also makes the control more sensitive and effective. Furthermore, an erroneous judgement caused by recognition of a boundary (2) or obstacle on a slope can be effectively avoided, so that the control is more accurate.