Probabilistic Proximity Detection for Uncertain Vehicle Geometry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing proximity detection methods struggle to accurately measure the distance between uncertain geometric entities such as points and polynomials, which are inherently ambiguous due to sensor uncertainties, leading to inaccurate control in autonomous systems.
Innovation Solution
Employ probabilistic computing techniques to determine probabilistic proximity by transforming the uncertainty of polynomial curves into point uncertainties and calculating statistical distances using Mahalanobis or Bhattacharyya distances, considering the covariance matrices of both entities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional proximity detection methods are used to measure distance between uncertain geometric entities, then the measurement process is simple, but the measurement precision is poor due to sensor uncertainties
Solution Approach 1:
The patent transforms the proximity detection problem by changing the parameter representation from direct distance measurement to probabilistic distance measurement. It uses Mahalanobis distance and Bhattacharyya distance as alternative parameters that account for sensor uncertainties and correlations, thereby improving measurement precision while managing computational complexity through structured covariance matrix operations
Solution Approach 2:
The patent introduces covariance matrices as intermediary elements that mediate between raw sensor measurements and proximity detection. These covariance matrices capture uncertainty and correlation information, serving as a bridge that enables accurate probabilistic distance calculation while systematically handling the complexity of uncertain geometric entities
2Reliability
If sensor uncertainties are ignored in proximity detection, then the computational process is simple, but the reliability of control operations deteriorates in noisy environments
Solution Approach 1:
The patent applies preliminary action by pre-computing and storing covariance matrices that characterize sensor uncertainties and correlations before the actual proximity detection occurs. This preparation work enables reliable probabilistic distance calculation during runtime without requiring complex real-time uncertainty modeling, thus improving reliability while managing computational complexity
Solution Approach 2:
The patent replaces traditional mechanical distance measurement approaches with probabilistic computing methods. Instead of relying on simple geometric distance calculations, it substitutes a computational framework based on Mahalanobis and Bhattacharyya distances that inherently account for uncertainties, thereby improving reliability in noisy environments
Data Source
AI summary
A method includes identifying, using at least one processor, a first point associated with an uncertain location of an object in a space and a polynomial curve associated with an uncertain location of a feature in the space. The method also includes determining, using the at least one processor, a probabilistic proximity of the object and the feature. The probabilistic proximity is determined by identifying a second point on the polynomial curve, transforming an uncertainty associated with the polynomial curve into an uncertainty associated with the second point, and identifying the probabilistic proximity of the object and the feature using the first and second points and the uncertainty associated with the second point.