Dynamic Occupancy Grid Coordinate System for Autonomous Driving
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional Dynamic Occupancy Grids (DOG) systems face challenges in increasing precision without compromising real-time implementation, particularly in representing obstacles that cannot be bounded by a box, and require efficient obstacle perception in automatic driving systems.
Innovation Solution
The proposed solution involves a new approach to the occupancy grid coordinate system where the grid center moves only with integer multiples of cell sizes, allowing for reduced grid cells and varying sizes to enhance perception resolution, particularly near the vehicle, while maintaining efficient computation and reducing the number of grid cells.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the precision of the occupancy grid is increased, then the measurement precision is improved, but the device complexity increases due to the increased number of particles
Solution Approach 1:
The occupancy grid is segmented into multiple regions with different resolutions. High-resolution grid cells are used only in critical areas (e.g., near the vehicle), while lower-resolution grid cells are used in distant or less critical areas. This segmentation allows the system to maintain high measurement precision where needed while reducing the overall number of particles and computational complexity.
Solution Approach 2:
Different regions of the occupancy grid are assigned different qualities (resolutions). The grid uses variable cell sizes where smaller cells provide higher precision in important local areas, and larger cells provide lower precision in less critical areas. This local quality approach optimizes the balance between measurement precision and device complexity by allocating computational resources selectively.
2Measurement precision
If the number of grid cells is increased to improve precision, then the measurement precision is improved, but the productivity decreases due to increased computation time
Solution Approach 1:
The grid is divided into regions with different resolutions, allowing the system to process fewer high-resolution cells while maintaining overall precision. This segmentation reduces the total computational load and increases perception speed while preserving measurement precision in critical areas.
Solution Approach 2:
By assigning different resolutions to different local regions, the system concentrates computational effort only where high precision is necessary, rather than uniformly processing all grid cells at high resolution. This improves productivity by reducing unnecessary computations in non-critical areas.
3Measurement precision
If the occupancy grid is dynamically updated with high precision, then the measurement precision is improved, but the loss of time increases due to computation requirements
Solution Approach 1:
The dynamic update process segments the grid into regions requiring different update frequencies and resolutions. Critical regions are updated with high precision, while non-critical regions use lower precision updates. This reduces overall computation time while maintaining precision where it matters most.
Solution Approach 2:
The system applies local quality by varying the update precision across different spatial regions. High-precision updates are performed only in areas where occupancy changes are critical, reducing the total computation time required for dynamic updates while preserving measurement precision in important local areas.
Data Source
AI summary
Various aspects of this disclosure provide an area occupancy determining device. The device may include a memory configured to store at least one occupancy grid of a predetermined region, and a processor. The processor may be configured to generate the occupancy grid of the predetermined region. The occupancy grid includes a plurality of grid cells, each grid cell framed by respective grid cell frame lines. At least some of the grid cells have been assigned an information about the occupancy of the region represented by the respective grid cell. The processor may further be configured to dynamically update the occupancy grid, thereby successively generating a plurality of updated occupancy grids. Each updated occupancy grid is moved relative to the previous occupancy grid such that an origin coordinate of the updated occupancy grid is positioned on a contact point of grid cell frame lines of adjacent grid cells.