Indoor Robot Exploration Using Reduced Voronoi Topological Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous robotic exploration methods face challenges such as excessive candidate frontier generation, high calculation time, and collision risks due to inefficient path planning on grid maps, particularly in indoor environments.
Innovation Solution
The method constructs a reduced approximated generalized Voronoi topological map using morphological methods, including threshold extraction, small-gap filling, center line extraction, and topologization, to reduce candidate frontiers and optimize path planning, utilizing a visual force field algorithm for navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If frontier-based method is used to perform feature calculation and comparison for candidate frontiers, then exploration accuracy is improved, but calculation time increases significantly
Solution Approach 1:
The patent segments the continuous space into discrete topological nodes and edges, transforming the problem from evaluating continuous frontier points to evaluating discrete topological structures. This segmentation reduces the search space and enables more efficient calculation while maintaining exploration accuracy through topological relationships.
Solution Approach 2:
The patent changes the representation parameter from grid-based coordinates to topological graph structures. By transforming the environmental map into a topological map with nodes and edges, the system reduces the dimensionality of the problem and enables faster feature calculation and comparison operations.
2Reliability
If path planning is performed on grid map, then path finding is achieved, but real-time requirement cannot be satisfied and collision risk increases
Solution Approach 1:
The patent extracts the essential topological relationships from the detailed grid map, removing unnecessary geometric details while preserving connectivity information. This extraction creates a simplified topological map that enables faster path planning while maintaining the ability to find valid paths and avoid collisions.
Solution Approach 2:
The patent transitions from two-dimensional grid coordinates to an abstract topological dimension represented by graph nodes and edges. This dimensional transformation allows path planning to operate in a simplified space while still mapping back to the physical environment for collision-free navigation.
3Speed
If topological map is used for environmental modeling, then path planning speed is accelerated, but environmental information becomes severely insufficient
Solution Approach 1:
The patent creates a topological map that serves multiple functions simultaneously: it enables fast path planning, preserves essential environmental connectivity information, and supports frontier-based exploration. The topological structure universally represents both geometric relationships and navigational constraints.
Solution Approach 2:
The patent performs preliminary processing to construct the topological map from the grid map before path planning. This preliminary action pre-computes the topological relationships and connectivity information, making subsequent path planning operations faster while retaining essential environmental information in the topological structure.
Data Source
AI summary
An autonomous robotic exploration method based on a reduced approximated generalized Voronoi graph, the method including: 1) constructing a reduced approximated generalized Voronoi topological map based on a morphological method; 2) obtaining an Next-Best-View and planning a global path from the robot to the Next-Best-View; and 3) navigating to the Next-Best-View along the global path R={r0, r1, r2, . . . , pNBV} based on a visual force field (VFF) algorithm.