Laser Plane Detection With Material-Aware SLAM Data Refinement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Laser sensors face challenges in accurately mapping and positioning due to varying reflections from different materials and surfaces, leading to inaccuracies in SLAM, particularly with special materials and shapes.
Innovation Solution
A plane detection method and device using a laser sensor that employs a machine learning model to recognize the medium type of a wall and optimize laser data based on the recognized medium type, employing techniques like median filtering, interpolation, and nearest neighbor resampling to refine the data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If laser sensor is used for positioning and mapping, then positioning speed and distance are improved, but positioning accuracy deteriorates when dealing with special materials and surfaces
Solution Approach 1:
The patent changes the parameter of laser transmission by adjusting transmission power dynamically. When the laser sensor detects that a special material or surface is encountered (through characteristics like diffuse reflection or signal fluctuation), the system increases the transmission power to compensate for the poor reflection characteristics, thereby improving positioning accuracy without sacrificing the speed advantage
2Productivity
If laser sensor transmits laser continuously, then detection speed is improved, but measurement accuracy deteriorates due to diffuse reflection and angle problems
Solution Approach 1:
The patent implements a feedback mechanism where the laser sensor continuously monitors the characteristics of the returned laser signal. When diffuse reflection or angle problems are detected (indicated by signal fluctuation or lack of expected reflection pattern), the system adjusts transmission power in real-time based on this feedback, allowing continuous detection to maintain both speed and accuracy
Solution Approach 2:
The patent makes the laser transmission power dynamic rather than fixed. The transmission power is adjusted in real-time based on the detected characteristics of the target surface and material, allowing the system to adapt to varying conditions while maintaining both fast detection and accurate measurement
3Ease of manufacture
If laser sensor detects flat surfaces, then mapping is simplified, but special materials and surfaces cause uneven laser data even on originally flat surfaces
Solution Approach 1:
The patent changes the transmission power parameter dynamically when special materials or surfaces are detected. By increasing the transmission power in response to detected reflection characteristics (such as diffuse reflection from special materials), the system compensates for the uneven laser data and maintains accurate detection of originally flat surfaces
Solution Approach 2:
The patent replaces simple geometric processing with machine learning-based material recognition. Instead of relying solely on the shape and geometry of surfaces to identify flatness, the system uses a machine learning model to recognize material types and their reflection characteristics, substituting a more sophisticated computational approach to handle complex material properties
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
Enhances the accuracy of mapping and positioning by classifying and optimizing laser data according to the characteristics of different materials, resulting in a more refined map and improved SLAM performance.
Implementation Method 1
by calculating the time difference between transmitting and receiving laser, the distance of the obstacle in the angle can be obtained
Implementation Method 2
the distance measured by some will fluctuate due to the diffuse reflection of light
Data Source
AI summary
A plane detection method and device based on a laser sensor are disclosed. The method includes: acquiring data of the laser sensor after starting detection; inputting the data into a detection model trained in advance, wherein the detection model is obtained by training with data corresponding to a medium type selected in advance and is capable of recognizing the medium type selected; judging whether an object to which the data belongs is a plane, and if the object is a plane, determining the medium type of the plane; and setting corresponding optimization methods for different medium types, and optimizing the data according to the medium type. The laser sensor recognizes the medium type by the machine learning model, and optimizes the two-dimensional laser data according to the recognition results, and thus forms a more refined map and performs more accurate positioning based on the two-dimensional laser data.