Occupancy Grid Free Space Detection With Tested-Cell Skipping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing free space detection methods for autonomous vehicles are computationally expensive and time-consuming, particularly when determining parkable spaces, due to the need to test every grid cell in a region of interest for occupancy status.
Innovation Solution
Implement a Binarized Occupancy Grid (B-OG) map using sensor inputs to identify free space, where previously tested occupied cells are marked as 'tested' without re-evaluation, allowing for computational improvements by skipping unnecessary cell processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If every grid cell in the region of interest is tested for occupancy status, then the accuracy of free space detection is improved, but the computational time and processing power required increases significantly
Solution Approach 1:
The patent applies preliminary action by marking cells as 'tested' in advance during the scanning process. When a cell is evaluated for occupancy, it is immediately marked with a tested flag, preventing redundant evaluation of the same cell or cells already examined as part of surrounding areas. This preliminary marking action eliminates the need to re-test cells, significantly reducing computational time while preserving detection accuracy.
Solution Approach 2:
The patent implements local quality by applying different processing treatments to different cells based on their occupancy status. Cells determined to be occupied are marked with both occupied and tested flags, while free cells receive only the tested flag. This localized differentiation allows the system to optimize processing by avoiding redundant checks in already-examined areas while maintaining thorough detection in unexamined regions.
2Measurement precision
If every grid cell in the region of interest is tested for occupancy status, then the accuracy of free space detection is improved, but the computational power consumption increases
Solution Approach 1:
The patent applies preliminary action by marking cells as 'tested' in advance during the scanning process. When a cell is evaluated for occupancy, it is immediately marked with a tested flag, preventing redundant evaluation of the same cell or cells already examined as part of surrounding areas. This preliminary marking action eliminates the need to re-test cells, significantly reducing computational time while preserving detection accuracy.
Solution Approach 2:
The patent implements local quality by applying different processing treatments to different cells based on their occupancy status. Cells determined to be occupied are marked with both occupied and tested flags, while free cells receive only the tested flag. This localized differentiation allows the system to optimize processing by avoiding redundant checks in already-examined areas while maintaining thorough detection in unexamined regions.
3Reliability
If redundant cell testing is performed, then comprehensive occupancy verification is achieved, but the detection speed decreases
Solution Approach 1:
The patent applies preliminary action by marking cells as 'tested' in advance during the scanning process. When a cell is evaluated for occupancy, it is immediately marked with a tested flag, preventing redundant evaluation of the same cell or cells already examined as part of surrounding areas. This preliminary marking action eliminates the need to re-test cells, significantly reducing computational time while preserving detection accuracy.
Solution Approach 2:
The patent implements skipping by allowing the detection algorithm to bypass cells that have already been marked with the tested flag. When processing reaches a cell with an existing tested marker, the system skips the occupancy evaluation for that cell and proceeds to the next untested cell. This skipping mechanism maintains verification reliability for untested cells while dramatically improving detection speed by eliminating redundant operations.
Data Source
AI summary
Examples provide for computer executable instructions executable by a processor to configure the processor to determine an occupancy status of cells of a region of interest by, for a first cell of the region of interest, determining whether the first cell is free by setting a free space flag for the first cell to an asserted value and setting a free space tested flag for the first cell to an asserted value responsive to determining that the first cell and each of the surrounding cells in the programmed radius of the first cell are unoccupied, and setting a free space flag for a second cell to a de-asserted value and setting a free space tested flag for the second cell to an asserted value responsive to determining that the second cell is occupied, the second cell being among the surrounding cells in the programmed radius of the first cell.


