IMU-EMG XR Input for Reliable Hands-Free Gesture Control

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing extended reality input methods, such as camera-based gesture input and EMG-based interfaces, suffer from limitations like reduced recognition rates due to environmental factors and limited gesture flexibility, respectively.

Innovation Solution

An IMU- and EMG-based extended reality input device that utilizes inertial measurement unit (IMU) signals for 3D pointing and electromyography (EMG) signals for command transfer, enabling a fully hands-free input system with expanded gesture recognition capabilities through artificial intelligence.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If camera-based gesture input technology is used, then hands-free input is achieved, but recognition rate is reduced due to environmental factors

Engineering Contradiction:

Improvehands-free inputVSAvoidrecognition rate

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The patent combines IMU sensor-based pointing (for spatial position and orientation) with EMG sensor-based gesture recognition (for hand movements) into a hybrid input system. This merging allows the system to maintain hands-free operation while improving recognition reliability by cross-validating signals from multiple sensor types, thereby resolving the contradiction between ease of operation and recognition reliability.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces an intermediary processing layer that receives signals from both IMU and EMG sensors, processes them through neural networks, and integrates the results. This intermediary system acts as a mediator that compensates for environmental limitations by using multiple signal sources, thereby maintaining high recognition rates while preserving hands-free operation.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Ease of operation

If EMG-based interfaces are used, then gesture recognition is achieved, but only registered gestures and pre-mapped commands can be performed

Engineering Contradiction:

Improvegesture recognitionVSAvoidgesture flexibility

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent employs dynamic neural network models that can adapt to new gestures and commands in real-time, rather than relying on static pre-mapped gestures. The system continuously learns from user interactions and updates its gesture recognition capabilities, enabling flexible adaptation to novel gestures while maintaining ease of operation through intuitive hand movements.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent creates a universal gesture recognition system that can handle both registered and unregistered gestures through a single integrated neural network architecture. This multi-functional system processes various hand gestures, pointing motions, and combinations thereof, providing versatile input capabilities while maintaining ease of operation through a unified interface.

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Area of stationary object

If multiple camera sensors are positioned in various directions, then hand position coverage is improved, but device complexity increases

Engineering Contradiction:

Improvehand position coverageVSAvoidnumber of camera sensors

Core Design Contradiction:

Area of stationary objectVSDevice complexity

Solution Approach 1:

The patent extracts the essential functionality of multi-camera spatial coverage by using a single IMU sensor that measures orientation and position through inertial data. This extraction eliminates the need for multiple camera sensors while maintaining the ability to track hand position and orientation across various directions, thereby reducing device complexity while preserving spatial coverage capability.

Inventive Principle:

Principle #2Taking out (Extraction)

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

Provides high interface expandability and flexibility by combining IMU-based ray-casting with EMG-based gesture input, allowing for various commands and gestures without environmental limitations.

Implementation Method 1

an inertial measurement unit (IMU) sensor and an electromyography (EMG) sensor, wherein the first wearable device is configured to detect, based on a movement of a body part of a user, at least one IMU signal

Methodology Applied

Scientific EffectInertial measurement: Inertia

Implementation Method 2

Methodology Applied

Scientific EffectElectromyography:

Data Source

PatentUS20260037072A1IMU- and EMG-Based Extended Reality Input Device and Method

Publication Date: 2026.02.05 HYUNDAI MOTOR CO LTD

AI summary

An IMU- and EMG-based extended reality input device is provided to be connected to an arm band worn on an arm of a user and provided with an inertial measurement unit (IMU) sensor and an electromyography (EMG) sensor and an extended reality module worn on a face of the user and providing a virtual extended reality, through a network, and configured to dispose a virtual cursor on the extended reality, the virtual cursor moving corresponding to a change of an angle and position change of the arm of the user detected by an IMU sensor and providing an input corresponding to a gesture of the arm of the user recognized through an EMG sensor.