Mobile Robot Grid Map Accuracy via Feature Point Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for building grid maps by mobile robots are prone to inaccuracies due to sensor errors, leading to distorted maps and inefficient cell decomposition, which hinders the robot's ability to perform tasks accurately and efficiently in wide areas.
Innovation Solution
The method involves obtaining grid points by sensing distances to obstacles, extracting feature points, using SLAM algorithms to update the robot's pose and transform feature points, and updating the grid map with a transform formula to achieve a more accurate representation, followed by cell decomposition based on these feature points and sweep-line angles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a robot builds a grid map by autonomously traveling and using sensors to recognize surroundings, then the robot can operate without pre-prepared maps, but sensor errors cause uncertainty and inaccuracies in the built map
Solution Approach 1:
The patent introduces feature points as intermediary elements that mediate between sensor data and the final grid map. These feature points serve as reference markers that help correct and align the grid map, reducing the impact of sensor errors while maintaining autonomous operation capability
Solution Approach 2:
The patent implements a feedback mechanism where the robot repeatedly captures images, extracts feature points, and compares them with previously identified feature points. This feedback loop allows the robot to detect discrepancies caused by sensor errors and correct the grid map accordingly, improving map accuracy while maintaining autonomous operation
2Area of stationary object
If the robot uses sensors to build a grid map of a limited area, then the robot can recognize the local surroundings, but the overall structure of the completed map becomes distorted and inaccurate
Solution Approach 1:
The patent segments the map building process into multiple stages: capturing images at different positions, extracting feature points from each image, and progressively constructing the grid map. This segmentation allows the robot to build accurate local maps that can be correctly integrated into the overall map structure, preventing distortion
Solution Approach 2:
Feature points serve as intermediary reference markers that connect different local areas into a coherent overall map. By using these feature points to align and integrate local maps, the patent maintains accurate overall map structure even as the robot expands its recognized area
3Productivity
If conventional cell decomposition methods are used on inaccurate grid maps, then the space can be divided into cells, but the decomposition is inefficient and the robot cannot perform tasks accurately
Solution Approach 1:
The patent performs preliminary correction of the grid map using feature points before conducting cell decomposition. By pre-aligning and correcting the map structure, the subsequent cell decomposition and task execution can proceed accurately, improving both productivity and position/orientation accuracy
Data Source
AI summary
Provided are a method, apparatus, and medium for building a grid map in a mobile robot and a method, apparatus, and medium for cell decomposition using the grid map building method and apparatus. A mobile robot for building a grid map includes a grid map building unit obtaining grid points by sensing a distance to an external space or obstacle, and building a grid map, a feature point extraction unit extracting feature points from the grid points, a feature point update unit estimating the pose of the robot after the robot moves, and obtaining updated feature points by SLAM (Simultaneous Localization And Map building) algorithm, a transform formula calculation unit calculating a transform formula that transforms feature points extracted by the feature point extraction unit into feature points updated by the feature point update unit, and a grid map update unit updating the grid map according to the obtained formula.