Lidar Occupancy Grid Dynamic Status Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing resolution of LIDAR units in automated vehicles leads to a significant data processing burden, making automotive image-data-processing controllers more expensive and less economical.
Innovation Solution
An object detection system that uses a LIDAR unit to detect cloud-points and a controller to define an occupancy grid, determining the dynamic status of objects by comparing cloud-point counts and registration between consecutive scans, reducing processing complexity and cost.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the resolution of LIDAR units is increased to improve object detection accuracy, then the data processing burden increases, making controllers more expensive
Solution Approach 1:
The patent divides the field of view into multiple columns and processes cloud points column by column. Each column is independently analyzed for occupancy status and dynamic characteristics. This segmentation reduces the overall processing complexity by breaking down the large-scale point cloud data into smaller, manageable units that can be processed more efficiently.
Solution Approach 2:
The patent extracts only the essential features from the point cloud data - specifically, the occupancy status (occupied/unoccupied) and dynamic status (moving/static) of each column. By extracting only these critical attributes rather than processing all raw point cloud data, the system reduces the processing burden while maintaining detection accuracy.
2Measurement precision
If high-resolution LIDAR data is processed in detail, then object detection accuracy improves, but processing time and computational resources increase
Solution Approach 1:
The patent applies partial action by performing processing only on columns that are marked as occupied. Unoccupied columns are skipped entirely, avoiding unnecessary computational work. Additionally, the system performs dynamic status determination only when needed, rather than continuously processing all data at full resolution.
Solution Approach 2:
By segmenting the processing into column-level operations, the system can parallelize processing and reduce the critical path time. Each column can be evaluated independently and simultaneously, significantly reducing overall processing time compared to sequential processing of the entire point cloud.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system effectively determines the dynamic status of objects near an automated vehicle with reduced processing burden, enabling more economical controller configurations and improved object detection accuracy.
Implementation Method 1
a lidar-unit used to detect cloud-points in a field-of-view of the lidar-unit proximate to a host-vehicle
Data Source
AI summary
An object detection system includes a lidar-unit and a controller. The controller defines an occupancy-grid that segregates the field-of-view into columns, determine a first-occupancy-status of a column based on first-cloud-points detected by the lidar-unit in the column by a first-scan, determine a second-occupancy-status of the column based second-cloud-points detected in the column by a second-scan, determine a first-number of the first-cloud-points and a second-number of the second-cloud-points, and determine a dynamic-status of the column only if the column is classified as occupied by either the first-occupancy-status or the second-occupancy-status. The dynamic-status of the column is determined to be moving when a count-difference between the first-number and the second-number is greater than a difference-threshold, and the dynamic-status of the column is determined to be static when the count-difference is not greater than the difference-threshold and a registration-factor that aligns the first-cloud-points to the second-cloud-points is less than a registration-threshold.