Warped Occupancy Grid for Curved-Road Object Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle sensor data processing systems face inefficiencies in storage and processing due to the need to handle large amounts of data, particularly when dealing with curved roadways, leading to potential delays in object detection and untimely safety measure deployment.
Innovation Solution
The implementation of a warped occupancy grid system, which allocates memory based on the vehicle's trajectory, allowing only relevant sensor data points to be stored and processed, using transformations like conformal mobius transformations to fit the grid to the trajectory, reducing unnecessary data storage and processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If a larger area of sensor data is stored to encapsulate the curvature of the roadway, then the coverage area is improved, but storage space is wasted and processing time increases
Solution Approach 1:
The patent divides the sensor data processing into two distinct segments: a reduced occupancy grid that covers only the relevant roadway area for efficient processing, and a separate curved roadway map that stores the complete environmental information. This segmentation allows the system to process only essential data for collision detection while maintaining comprehensive spatial awareness, thereby reducing processing time without sacrificing coverage capability.
Solution Approach 2:
The patent extracts and separates the curved roadway geometry information from the standard occupancy grid data. By taking out the roadway curvature information and storing it independently in a specialized map structure, the system eliminates the need to process redundant data points in the occupancy grid that would otherwise be required to represent curved roadways, thus reducing processing time while preserving complete spatial coverage.
2Area of stationary object
If a larger area of sensor data is stored to encapsulate the curvature of the roadway, then the coverage area is improved, but storage space is wasted
Solution Approach 1:
The patent segments sensor data storage into two specialized structures: a reduced occupancy grid that consumes minimal storage space for real-time processing, and a separate curved roadway map that efficiently stores comprehensive environmental geometry. This segmentation enables the system to maintain complete coverage area information without requiring the occupancy grid to expand proportionally, thus optimizing storage space utilization.
Solution Approach 2:
The patent extracts curved roadway information from the occupancy grid and stores it in a dedicated map structure optimized for geometric data. This extraction eliminates redundant storage of roadway curvature information within the occupancy grid, allowing the system to achieve comprehensive coverage area representation with significantly reduced total storage requirements.
3Area of stationary object
If processing is performed on a large chunk of sensor data associated with an area outside of the roadway, then the coverage area is improved, but processing power is wasted
Solution Approach 1:
The patent segments the processing workload into two distinct operations: processing a small reduced occupancy grid that requires minimal computational power for collision detection, and separately managing curved roadway map data that provides comprehensive coverage information without requiring intensive processing. This segmentation eliminates the waste of processing power on irrelevant data while maintaining complete area coverage.
Solution Approach 2:
The patent extracts and separates roadway-specific geometric information from the general occupancy grid data. By taking out the curved roadway representation and handling it through specialized mapping operations, the system avoids applying computationally intensive grid processing algorithms to data that would otherwise be processed unnecessarily, thus optimizing processing power utilization while preserving complete coverage.
Data Source
AI summary
Techniques for determining a warped occupancy grid fit to a vehicle trajectory are discussed herein. In some examples, a portion of memory may be allocated to an occupancy grid. Further, a warped occupancy grid can be warped and associated with an environment that an autonomous vehicle is traversing according to a trajectory and/or throughway. A transformation maybe be determined between the warped occupancy grid and the memory allocated to the occupancy grid. Sensor data can be received from a sensor associated with the autonomous vehicle and may be associated with the warped occupancy grid and stored in the occupancy grid. The autonomous vehicle may be controlled according to the warped occupancy grid by identifying sensor data returns in cells of the warped occupancy grid that may indicate a detection of an object in a path of travel of the vehicle.