Grid Map Preprocessing for Faster Distance Transformation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The calculation amount for distance transformation in autonomous vehicle path planning is excessively large, particularly in complex environments, due to the need for high-precision grid maps that include unnecessary information, which affects real-time feasibility and safety.
Innovation Solution
A preprocessing method that adjusts the grid map precision based on the vehicle model, reducing the number of cells requiring processing by determining state values and identifying cells that need no processing, thereby reducing the calculation load for distance transformation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If high-precision grid map is used for distance transformation, then path planning accuracy is improved, but calculation amount increases excessively
Solution Approach 1:
The patent applies local quality by differentiating grid precision based on spatial location. Cells near obstacles maintain high precision for accurate path planning, while cells in open regions use lower precision. This is achieved by classifying cells into different types (first type cells near obstacles, second type cells in open regions) and applying different processing strategies to each type, thereby reducing overall calculation amount while preserving necessary accuracy.
2Reliability
If entire grid map is processed with high precision, then path planning reliability is improved, but processing time increases
Solution Approach 1:
The patent segments the grid map into different cell types based on their relationship with obstacles. First type cells (near obstacles) require high-precision processing for reliable path planning, while second type cells (in open regions) can use simplified processing. This segmentation allows the system to maintain reliability where needed while reducing processing time overall by avoiding unnecessary high-precision calculations in regions where they are not critical.
Solution Approach 2:
The patent applies partial action by performing distance transformation only on necessary cells (first type cells near obstacles) rather than the entire grid map. Cells that do not require precise distance calculations (second type cells in open regions) are excluded from intensive processing. This partial processing approach maintains path planning reliability for critical areas while significantly reducing overall processing time.
3Productivity
If grid precision is reduced to decrease calculation amount, then processing speed is improved, but pose estimation accuracy deteriorates
Solution Approach 1:
The patent applies local quality by maintaining high grid precision for first type cells near obstacles where accurate pose estimation is critical for safety, while using lower precision for second type cells in open regions. This localized precision strategy ensures that pose estimation accuracy is preserved where it matters most (near obstacles) while achieving improved processing speed overall through reduced calculation in less critical areas.
Data Source
AI summary
Disclosed are a preprocessing method and device for distance transformation. The method includes: acquiring a first grid map; calculating a second parameter of a vehicle model; calculating a precision of a second grid map according to the second parameter of the vehicle model and a precision of the first grid map; calculating the numbers of rows and columns of the second grid map according to information on the first grid map, the precision of the second grid map and the second parameter of the vehicle model; determining for each cell of the second grid map a state value according to the numbers of obstacle cells within said each cell; and determining in the first grid map at least one cell requiring no processing, according to the state value. Therefore, during the distance transformation, the processing speed for determining the distance value of each cell is increased.