XR Hand Chirality Estimation Using Joint Bending Angles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing XR devices face challenges in accurately and efficiently estimating hand chirality due to the variability in hand shapes, sizes, and movements, leading to potential errors in tracking and interpreting user gestures, and introducing computational inefficiencies and latency.
Innovation Solution
XR devices process tracking data to determine multiple bending angles associated with a hand, using a geometrically defined reference vector to estimate chirality without relying on machine learning models, and combine this with a rules-based approach for enhanced accuracy and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning models are used to estimate hand chirality, then accuracy may be improved, but computational complexity and latency increase
Solution Approach 1:
The patent replaces machine learning models (complex computational system) with a rules-based geometric analysis system that calculates bending angles and determines chirality through predefined geometric relationships. This substitution reduces computational complexity while maintaining estimation accuracy by leveraging the inherent geometric properties of hand structures.
Solution Approach 2:
The patent extracts only the essential geometric features (bending angles of finger joints) needed for chirality estimation, discarding the need for complex machine learning models. By focusing solely on the critical geometric parameters, the system achieves accurate chirality determination with significantly reduced computational requirements.
2Measurement precision
If machine learning models are used to estimate hand chirality, then accuracy may be improved, but processing time and latency increase
Solution Approach 1:
The patent replaces computationally intensive machine learning inference with lightweight geometric calculations that compute bending angles and apply simple decision rules. This substitution dramatically reduces processing time and latency while maintaining the accuracy needed for real-time XR applications.
Solution Approach 2:
The patent uses simple, computationally inexpensive geometric calculations instead of heavy machine learning models. These lightweight calculations can be performed rapidly and discarded, enabling real-time chirality estimation without the computational burden of sustained machine learning processing.
3Device complexity
If traditional tracking methods are used, then device complexity is reduced, but reliability of hand chirality estimation deteriorates due to hand variability
Solution Approach 1:
The patent applies localized geometric analysis to specific finger joints, calculating bending angles for each joint individually. This local quality approach allows the system to adapt to variations in individual finger configurations while maintaining overall reliability, as each joint's geometry is analyzed independently according to its specific characteristics.
Solution Approach 2:
The patent changes the approach from using fixed, generic hand models to dynamically calculating bending angles based on actual tracked joint positions. By adapting the geometric parameters to the specific hand configuration being observed, the system maintains high reliability across diverse hand shapes and sizes without increasing overall system complexity.
Data Source
AI summary
Examples in the present disclosure relate to hand chirality estimation. Tracking data captured by one or more sensors associated with an extended reality (XR) device is processed to determine positions of a plurality of joints of a hand of a person. A reference vector is generated based on a first subset of the positions. The first subset of the positions includes positions of at least two metacarpophalangeal joints. A plurality of bending angles is determined based on at least a second subset of the positions. Each bending angle represents an angle between a respective pair of articulating bones that is measured in relation to the reference vector. An estimated chirality of the hand is identified based on the plurality of bending angles. Operation of the XR device is controlled using the estimated chirality of the hand.