Drivable Space Representation from Occupancy Grid Transition Markers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Occupancy grids used in autonomous vehicles require significant memory and are inefficient for memory-limited systems, hindering fast and reliable data transfer between vehicle subsystems and external systems.
Innovation Solution
A method is implemented using a control system that generates a representation of drivable space by processing occupancy grids with a reference tool, identifying transition markers, and computing drivable and non-drivable regions, providing real-time guidance based on localization data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If occupancy grids are used to represent the environment with sufficient resolution, then measurement precision is improved, but device complexity increases due to large memory footprint
Solution Approach 1:
The patent segments the occupancy grid data by identifying and extracting only the critical transition markers (boundaries between occupied and unoccupied zones) along rays from the vehicle, rather than processing or storing the entire high-resolution grid. This segmentation reduces memory requirements while preserving essential environmental representation for navigation decisions.
2Measurement precision
If occupancy grids are used with high resolution, then measurement precision is improved, but loss of time increases due to slow data transfer between subsystems
Solution Approach 1:
The patent extracts only the essential information from the occupancy grid by identifying transition markers along rays from the vehicle's location. This extraction process creates a simplified representation that contains the critical boundary information needed for navigation while eliminating redundant data, thereby reducing data transfer time between subsystems while maintaining measurement precision for environment representation.
3Measurement precision
If occupancy grids are used for environment representation, then measurement precision is improved, but reliability decreases due to inability to ensure fast and reliable data transfer
Solution Approach 1:
The patent extracts critical transition marker information from the occupancy grid to create a simplified representation. This extraction ensures that only essential boundary data between occupied and unoccupied zones is retained, enabling fast and reliable data transfer between vehicle subsystems and external systems while maintaining the precision needed for safe navigation decisions.
Solution Approach 2:
The patent changes the data representation parameters by transforming the full occupancy grid into a simplified format based on transition markers along rays. This parameter change reduces data size and complexity while preserving the critical information needed for reliable environment representation and navigation, thereby improving data transfer reliability.
Data Source
AI summary
A method includes obtaining an occupancy grid. The method includes generating a reference, such as a ray, on the occupancy grid. The ray originates from a location of a vehicle and extends in a direction that corresponds to a driving direction of the vehicle. The method includes identifying markers along the ray. The markers include transition markers, which indicate a first type of transition or a second type of transition. The first type of transition is from an unoccupied zone to an occupied zone. The second type of transition is from the occupied zone to the unoccupied zone. The method includes generating a representation of drivable space in real-time based on computations involving sections that are associated with the first type of transition and the second type of transition. The method includes providing guidance to the vehicle based on the representation of drivable space.