Radar Resolution Function Derivation for False Negative Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Radar systems in autonomous vehicles face challenges in detecting objects due to interference from reflections, leading to false negatives, which can compromise safety and efficiency in navigating complex environments.
Innovation Solution
The techniques involve determining a resolution function based on radar data analysis, which includes correlating data points, distributing offset data onto a spatial grid, and generating a frequency distribution to set a detection threshold, thereby improving the likelihood of detecting obscured objects and reducing false negatives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If radar systems use conventional detection methods, then the system complexity remains manageable, but the detection precision deteriorates due to reflections interfering with captured data
Solution Approach 1:
The patent segments the captured radar data into multiple data points and distributes them onto a spatial grid. By dividing the detection space into discrete cells and assigning data points to specific cells based on their spatial coordinates, the system can analyze each cell independently to determine occupancy probability, thereby improving detection precision while maintaining manageable system complexity through modular processing
Solution Approach 2:
The patent transitions from conventional radar detection to a spatial grid-based approach, adding a dimensional structure to the data processing. By mapping data points onto a two-dimensional spatial grid with cells representing specific geographic locations, the system creates a new dimensional framework that enables more precise detection of obscured objects without proportionally increasing system complexity
2Measurement precision
If radar systems increase detection sensitivity to identify obscured objects, then the detection precision improves, but the reliability deteriorates due to increased false negatives
Solution Approach 1:
The patent implements a feedback mechanism by calculating occupancy probability for each cell based on the distribution of data points. The system uses this probability information to make informed detection decisions, where the detected occupancy status feeds back into the overall scene understanding. This probabilistic feedback approach allows the system to maintain high detection sensitivity while reducing false negatives by considering the statistical likelihood of object presence in each cell
Solution Approach 2:
The patent changes the detection parameter from binary detection to probabilistic occupancy measurement. By representing object presence as a probability value derived from data point distribution rather than a simple detected/not-detected binary state, the system can adjust its detection threshold and confidence levels to balance precision and reliability according to operational requirements
3Measurement precision
If radar systems process more data points to improve object detection, then the detection precision improves, but the productivity deteriorates due to increased processing requirements
Solution Approach 1:
The patent segments the large volume of radar data points into smaller units assigned to specific spatial grid cells. By processing each cell independently and only analyzing data points within or relevant to each cell, the system reduces the computational burden compared to processing all data points globally. This segmented approach maintains detection precision by preserving all data points while improving processing efficiency through localized analysis
Solution Approach 2:
The patent applies partial action by focusing computational resources on specific cells that are likely to contain objects of interest, rather than uniformly processing all spatial locations. The system can prioritize cells with higher data point density or those in critical detection zones, performing more detailed analysis where needed and simpler analysis elsewhere, thereby maintaining high detection precision while optimizing processing efficiency
Data Source
AI summary
Techniques for determining a probability of a false negative associated with a location of an environment are discussed herein. Data from a sensor, such as a radar sensor, can be received that includes point cloud data, which includes first and second data points. The first data point has a first attribute and the second data point has a second attribute. A difference between the first and second attributes is determined such that a frequency distribution may be determined. The frequency distribution may then be used to determine a distribution function, which allows for the determination of a resolution function that is associated with the sensor. The resolution function may then be used to determine a probability of a false negative at a location in an environment. The probability can be used to control a vehicle in a safe and reliable manner.