Autonomous Vehicle Positioning Using Multi-Resolution Histogram Filters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicle positioning systems face challenges in efficiently utilizing limited computing resources, as multiple modules compete for resources, and existing methods like position probability grids and probabilistic maps do not effectively reduce computing resource occupancy.
Innovation Solution
The method involves matching a current point cloud projected image with a map to generate a histogram filter, determining response areas based on probability values, and calculating a weighted average of probability values to determine the vehicle's positioning, thereby reducing computing resource consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional positioning methods (position probability grids or probabilistic maps) are used, then positioning accuracy is maintained, but computing resource occupancy remains high
Solution Approach 1:
The patent divides the positioning computation into two separate histogram filters: a first histogram filter for coarse positioning and a second histogram filter for fine positioning. This segmentation allows the system to process positioning data in stages, reducing the overall computing resource occupancy while maintaining positioning accuracy by combining results from both filters.
Solution Approach 2:
The patent applies partial action by using the first histogram filter to process only the most probable response areas (top K areas) rather than the entire map. This partial processing significantly reduces computing resource consumption while still achieving accurate positioning by focusing computational effort on the most relevant regions.
2Measurement precision
If high-resolution positioning is performed directly, then positioning accuracy is improved, but computing resource consumption increases significantly
Solution Approach 1:
The patent implements a two-stage resolution strategy where the first histogram filter operates at lower resolution to identify candidate regions, and the second histogram filter operates at higher resolution within those candidate regions. This segmentation of resolution levels achieves high positioning accuracy while maintaining computing efficiency by applying high-resolution processing only where necessary.
Solution Approach 2:
The patent applies local quality by using high-resolution processing only in the response areas identified by the first histogram filter, rather than applying high-resolution processing uniformly across the entire map. This localized high-resolution approach maintains positioning accuracy in critical areas while reducing overall computing resource consumption.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Embodiments of the present disclosure disclose a method and apparatus for positioning an autonomous vehicle. A specific embodiment of the method includes: matching a current point cloud projected image of a first resolution with a map of the first resolution to generate a first histogram filter based on the matching result; determining at least two first response areas in the first histogram filter based on a probability value of an element in the first histogram filter, the probability value of the element corresponding to the first response area being greater than a probability value of another element in the first histogram filter; generating a second histogram filter based on a result of matching a current point cloud projected image of a second resolution with a map of the second resolution and the at least two first response areas, the first resolution being less than the second resolution; and calculating a weighted average of probability values of target elements in the second histogram filter to determine a positioning result of the autonomous vehicle in the map of the second resolution. This embodiment reduces computing resources consumed for positioning an autonomous vehicle.