Vector Map Line Merging for Accurate Robotic Warehouse Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current robotic mapping systems using occupancy grids face memory inefficiencies and accuracy limitations as environment size increases, due to the need for larger memory storage and the inability to capture precise location data with cell sizes larger than sensor accuracy.
Innovation Solution
Generating vector maps using range sensors that outline object boundaries with line segments, allowing for compact memory storage and accurate navigation by employing iterative closest vector analysis to account for internal navigation errors and merge line segments into cohesive vectors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If occupancy grid cell size is increased to cover larger environments, then memory requirements are reduced, but location accuracy deteriorates
Solution Approach 1:
The patent segments the environment representation into multiple levels: occupancy grids for general spatial layout and vector maps with line segments for precise object boundaries. This hierarchical segmentation allows each representation to serve its optimal function - occupancy grids for memory-efficient large-scale coverage and vector maps for high-precision location data, thereby resolving the contradiction between memory requirements and location accuracy.
2Measurement precision
If occupancy grid cell size is decreased to improve location accuracy, then measurement precision is improved, but memory requirements increase
Solution Approach 1:
The system divides the mapping task into two segments: using occupancy grids for coarse-grained spatial partitioning that requires minimal memory, and overlaying vector maps with line segments for fine-grained boundary representation that provides high location accuracy without proportionally increasing memory usage.
Solution Approach 2:
The patent transitions from a two-dimensional occupancy grid representation to a multi-dimensional hierarchical structure that includes vector maps with line segments, covariance matrices for uncertainty quantification, and object-level semantics. This dimensional expansion allows the system to capture precise location information without the linear memory growth associated with finer occupancy grid cells.
3Measurement precision
If vector maps are used to outline object boundaries with line segments, then location accuracy is improved, but device complexity increases
Solution Approach 1:
The patent segments the complexity management by separating the processing of occupancy grid data from vector map generation and maintenance. The system independently processes sensor data to update occupancy grids, separately extracts line segments for vector maps, and independently handles the merging of line segments from different robot poses, thereby managing system complexity through functional segmentation.
4Measurement precision
If iterative closest vector analysis is used to merge line segments from different robot poses, then mapping accuracy is improved, but computation time increases
Solution Approach 1:
The patent performs preliminary actions by pre-processing sensor data to extract line segments and pre-computing covariance matrices for each line segment before the merging process. This preliminary preparation organizes the data in a structured format that facilitates efficient matching and merging during the iterative closest vector analysis, reducing the computational burden during the actual merging operation.
Data Source
AI summary
Embodiments herein describe a robotic system that uses range sensors to identify a vector map of an environment. The vector map includes lines that outline the shape of objects in the environment (e.g., shelves on the floor of a warehouse). The system identifies one or more line segments representing the boundary or outline of the objects in the environment using range data acquired by the range sensors. The robotic system can repeat this process at different locations as it moves in the environment. Because of errors and inaccuracies, line segments formed at different locations may not clearly align even when these line segments correspond to the same object. To account for this error, the robotic system match line segments identified at a first location with line segments identified at a second location. The matched line segments can be merged into a line that is stored in the vector map.