Autonomous Vehicle Chassis Frame Estimation via CAD Distortion Minimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in calibrating sensors without structured facilities and excessive human intervention, leading to sensor positioning and orientation discrepancies that distort chassis frame estimation, which can impair safety.
Innovation Solution
The autonomous vehicle minimizes distortion between measured sensor values and CAD model values using methods like least-squares regression, convex hull generation, and symmetry constraints to estimate a chassis point and frame accurately.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If sensor calibration is performed without structured facilities and human intervention, then calibration time and cost are reduced, but sensor positioning precision and chassis frame estimation accuracy deteriorate
Solution Approach 1:
The autonomous vehicle performs self-calibration by automatically minimizing distortion between measured sensor values and CAD model values using computational methods (least-squares regression, convex hull generation, symmetry constraints), eliminating the need for structured facilities and human intervention while maintaining calibration accuracy
Solution Approach 2:
The patent replaces physical calibration facilities and manual mechanical adjustment with computational algorithms that process sensor data and minimize distortion mathematically, substituting mechanical calibration processes with information-processing methods
2Ease of operation
If sensor calibration is performed without structured facilities and human intervention, then operational ease is improved, but chassis frame estimation accuracy deteriorates
Solution Approach 1:
The system enables autonomous self-calibration where the vehicle independently minimizes distortion between measured and CAD model sensor values using computational methods, making calibration easy to perform while maintaining high estimation accuracy through algorithmic optimization
Solution Approach 2:
The patent implements a feedback mechanism where the system continuously minimizes distortion between measured sensor values and CAD model values, using the distortion minimization as feedback to iteratively improve chassis frame estimation accuracy until convergence is achieved
3Measurement precision
If distortion minimization methods are applied to align sensor positions with CAD models, then chassis frame estimation accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent segments the distortion minimization problem into distinct computational steps: generating convex hulls for sensor constellations, applying symmetry constraints, performing least-squares regression, and iteratively minimizing distortion between measured and CAD model values, making the complex computational task more manageable and systematic
Data Source
AI summary
The subject disclosure relates to estimating a chassis frame of an autonomous vehicle. A process of the disclosed technology can include receiving a position for each of a plurality of sensors on an autonomous vehicle, determining an ideal chassis point in relation to a constellation of model sensors in a CAD model associated with the autonomous vehicle, generating a constellation of the plurality of sensors based on the positions of the plurality of sensors in relation to the ideal chassis point, minimizing distortion between measured values associated with the constellation of the plurality of sensors and ideal values associated with the constellation of model sensors, determining an estimated real chassis point based on the minimized distortion between the measured values and the ideal values, and calibrating at least one of the plurality of sensors based on the estimated real chassis point.