Surface Normal Vector Stability Detection on Sloped Surfaces
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Inertial measurement units in autonomous vehicles provide inaccurate measurements of driving stability, particularly when driving on slopes, as they may indicate instability when the vehicle is actually stable.
Innovation Solution
Identify roll, pitch, and azimuth of an object relative to a surface by using surface normal vectors based on updated normal vectors from various sensors, including cameras and LIDAR, to enhance stability detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If inertial measurement units are used to identify driving stability, then stability measurements can be obtained, but the measurement accuracy deteriorates on sloped surfaces
Solution Approach 1:
The patent introduces surface normal vectors as an intermediary element between the vehicle and the stability assessment system. By calculating the normal vector of the surface the vehicle is traveling on and comparing it with the vehicle's orientation, the system can accurately determine stability relative to the actual surface, not just relative to a flat reference plane. This intermediary calculation resolves the contradiction by providing accurate stability measurements on both flat and sloped surfaces.
2Loss of information
If inertial measurement units are used to detect stability, then stability data is available, but false instability indications occur on slopes
Solution Approach 1:
The system implements feedback by continuously monitoring the relationship between the surface normal vector and the vehicle's orientation vector. When the vehicle is on a slope, the system receives feedback about the surface orientation and adjusts the stability assessment accordingly. This feedback mechanism eliminates false instability indications by comparing the vehicle's orientation relative to the actual surface rather than a fixed reference plane.
Data Source
AI summary
Aspects of the subject technology relate to systems, methods, and computer-readable media for identifying roll, pitch, and azimuth angles for an object based on surface normal vectors. Image data tracking a surface as an object moves relative to the surface can be accessed. A reference normal vector of the surface can be identified. A dynamic normal vector of the surface associated with the object moving over the surface can be identified from the image data. One or a combination of roll, pitch, and azimuth of the object with respect to the surface can be determined based on the reference normal vector and the dynamic normal vector.