Wearable Armband Hand Tracking via Electrical Impedance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing gesture recognition systems for hand tracking are cumbersome, uncomfortable, and limited in customization, often requiring the entire hand to be in view and are unsuitable for head-mounted displays due to high costs and limited gesture recognition capabilities.

Innovation Solution

A wearable device using electrical impedance measurement sensors on the arm to track hand positions, combined with inertial measurement units and machine learning models, allowing for accurate hand pose detection without the need for the entire hand to be in view and enabling more types of data extraction than traditional systems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If camera-based gesture tracking systems are used to detect hand area from captured images, then hand position can be detected, but the entire hand must be in camera view range and the system fails when there is object occlusion

Engineering Contradiction:
Improvehand position detection accuracyVSAvoidhand tracking reliability under occlusion
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent replaces camera-based optical detection with electrical impedance sensing. Sensors equipped with electrodes measure impedance changes in the arm and hand tissues, which correspond to hand gestures and positions. This electrical measurement approach works independently of visual occlusion, allowing reliable hand tracking even when the hand is not visible to cameras or when objects block the view.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If glove-like devices with mechanical signals are used to track hand motion, then hand position can be tracked, but the device disturbs the haptic sense of the hand and is difficult to customize to different users

Engineering Contradiction:
Improvehand motion tracking accuracyVSAvoiduser comfort and haptic perception
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces mechanical signal tracking with electrical impedance measurement. Instead of using mechanical components that contact and constrain the hand, the system uses electrical sensors that measure impedance changes through the skin and tissues. This approach maintains natural hand haptics while accurately tracking hand motion and position through electrical properties of the tissues.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent measures changes in electrical impedance parameters of the arm and hand tissues to detect hand gestures. By monitoring how impedance values change with different hand positions and movements, the system can track hand motion without mechanical contact. The system can be customized to different users by calibrating baseline impedance values for each individual's anatomy.

Inventive Principle:
Principle #35Parameter changes

3Adaptability or versatility

If traditional gesture recognition systems are used, then predefined gestures can be recognized, but the system is limited to a small set of gestures and has high cost

Engineering Contradiction:
Improvegesture recognition capabilityVSAvoidsystem cost and customization
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent creates a universal hand tracking system based on electrical impedance measurement that can recognize any hand gesture, not just predefined ones. The sensor array with multiple electrodes can detect impedance patterns corresponding to various hand positions, finger configurations, and gestures. The system is highly adaptable to different users and gesture sets through software calibration without requiring expensive specialized hardware for each gesture type.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The solution provides a comfortable, cost-effective, and versatile hand tracking system suitable for head-mounted displays, enabling accurate detection of hand positions and gestures with improved user experience and expanded data extraction capabilities.

Implementation Method 1

Sensors located on the wearable device receive electrical signals from the user's wrist or arm corresponding to a hand position of the user. Each sensor includes an electrode and a conductive agent located between the electrode and the wrist or arm of the user.

Methodology Applied
Scientific EffectElectrical Impedance: Electrical Resistance

Implementation Method 2

Each sensor can transmit an alternative current (AC) signal, a direct current (DC) signal, or a wide-bandwidth AC signal including multiple frequencies, preferably into the wrist or arm of the user.

Methodology Applied
Scientific EffectElectrical Conduction: Conduction (electrical)

Implementation Method 3

The position computation circuit computes, using information derived from the electrical signals with a machine learning model, an output that describes a hand position of a hand of the wrist or arm of the user.

Methodology Applied
Scientific EffectMachine Learning:

Implementation Method 4

In some embodiments, the wearable device includes an inertial measurement unit (IMU) that measures motion of the user's arm, and provides inertial signals to the position computation circuit as an input for determination of the hand position.

Methodology Applied
Scientific EffectInertial Measurement:

Data Source

PatentEP3659016B1Armband for tracking hand motion using electrical impedance measurement
Publication Date: 2022.10.12 META PLATFORMS TECHNOLOGIES LLC
  • EP3659016B1 patent drawingFigure 1
  • EP3659016B1 patent drawingFigure 2A
  • EP3659016B1 patent drawingFigure 2B

AI summary

A system includes a wearable device including sensors arranged at different locations on the wearable device. Each sensor measures electrical signals transmitted from a wrist or arm of a user. A position computation circuit is coupled to the sensors. The position computation circuit computes, using information derived from the electrical signals with a machine learning model, an output that describes a hand position of a hand of the wrist or arm of the user.