Robot Relocalization Using Laser Subgraph Template Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current robot relocalization methods, such as AMCL, face challenges in maintaining high accuracy and efficiency, especially in dynamic environments, leading to potential navigation errors and safety risks due to changing scenes.
Innovation Solution
A robot relocalization method that involves obtaining a level feature in a laser map, calculating pose lists, matching laser subgraph point clouds using the iterative closest point algorithm, and performing multi-target template matching to improve localization accuracy and precision, especially in complex and dynamic environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the AMCL relocation method is used, then the computing resource requirements are low and the localization accuracy is high in constant environments, but the accuracy decreases and error rate increases in changing environments
Solution Approach 1:
The patent divides the relocation process into multiple stages: coarse relocation using grid-based methods to identify candidate regions, followed by fine relocation using AMCL within those regions. This segmentation allows the system to benefit from both the robustness of grid methods in dynamic environments and the precision of AMCL in constant environments, resolving the contradiction between accuracy and reliability.
Solution Approach 2:
The patent introduces an intermediate step of generating candidate position lists through grid-based coarse relocation before applying AMCL. This intermediary process filters out unlikely positions and provides a restricted search space, allowing AMCL to operate more reliably in dynamic environments while maintaining its computational efficiency and precision advantages.
2Ease of operation
If the user specification method is used for local relocation, then the operation is simple, but the efficiency is low and there are many constraints
Solution Approach 1:
The patent implements automatic relocation algorithms (grid-based coarse relocation combined with AMCL fine relocation) that enable the robot to determine its position autonomously without user intervention. The system processes sensor data, generates candidate positions, and executes relocation automatically, eliminating the need for users to manually control the robot to fixed positions while achieving high relocation efficiency.
3Productivity
If the software algorithm processing method is used for local relocation, then the efficiency is high and cost is low, but the algorithm complexity is high
Solution Approach 1:
The patent segments the complex relocation algorithm into two distinct phases: a grid-based coarse relocation phase that handles environmental adaptability, and an AMCL fine relocation phase that handles precision positioning. This segmentation reduces the complexity burden on each individual algorithm while maintaining high overall efficiency through the coordinated operation of both phases.
Data Source
AI summary
The present disclosure provides a robot relocalization method including: obtaining a level feature of an object in a laser map and calculating a first pose list; matching a laser subgraph point cloud collected by the robot with the first pose list to obtain a second pose list, if a distance between the level feature of the object and an initial position of a relocation of the robot is smaller than a threshold; splicing the laser subgraph point cloud into subgraphs, and performing a multi-target template matching to obtain a first matching candidate result; filtering the first matching candidate result based on the second pose list to obtain a second matching candidate result; determining a overlapping area of the second matching candidate result and the subgraph, and matching boundary points in the overlapping area with the laser subgraph point cloud to obtain the result of the relocation of the robot.