AR Voice Control With Device Labels for Unambiguous Selection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing AR systems face challenges in precisely identifying and controlling multiple devices of the same type due to ambiguity in voice commands, requiring additional data like labels or coordinate systems for accurate localization.

Innovation Solution

A system that uses a camera to capture a user's view, detects controllable objects, and overlays disambiguating information such as labels or grids on the display to uniquely identify subsets of objects, allowing precise voice control through AR.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If voice commands are used to control multiple devices of the same type, then ease of operation is improved, but measurement precision deteriorates due to ambiguity in identifying specific devices

Engineering Contradiction:
Improveease of operationVSAvoidmeasurement precision
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The system segments the group of multiple devices by displaying disambiguating information (labels, identifiers, or visual indicators) next to each device in the augmented reality view. This allows the user to mentally segment the group and select a specific device based on its displayed identifier, resolving the ambiguity while maintaining voice command convenience.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system introduces an intermediary element (disambiguating information such as labels, codes, or visual markers) that mediates between the voice command and the target device. This intermediary provides the additional context needed to precisely identify which device among multiple similar devices should be controlled, without requiring the user to abandon voice-based interaction.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If disambiguating information is displayed for multiple controllable objects, then measurement precision is improved, but device complexity increases

Engineering Contradiction:
Improvemeasurement precisionVSAvoiddevice complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system applies local quality by displaying disambiguating information only in the specific location where it is needed—next to or near the detected controllable objects in the augmented reality view. This localized approach provides necessary precision information without globally increasing system complexity or overwhelming the user interface with unnecessary data everywhere.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system employs self-service by automatically detecting controllable objects and generating appropriate disambiguating information without requiring manual configuration or complex user setup. The system autonomously manages the display of identifiers, labels, or visual markers based on its detection capabilities, reducing the operational complexity for the user.

Inventive Principle:
Principle #25Self-service

3Measurement precision

If additional data such as labels or coordinate systems are provided to identify devices, then measurement precision is improved, but loss of information increases due to the need for extra data processing

Engineering Contradiction:
Improvemeasurement precisionVSAvoidloss of information
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The system performs preliminary action by pre-detecting and pre-identifying controllable objects in the environment before the user issues a voice command. The disambiguating information is already prepared and displayed in the augmented reality view, so when the user speaks, the system can immediately match the voice command to the correct pre-identified device without requiring additional real-time data processing or information retrieval.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS12505626B2Augmented Reality method and system enabling commands to control real-world devices
Publication Date: 2025.12.23 INTERDIGITAL CE PATENT HOLDINGS SAS
  • US12505626B2 patent drawing
  • US12505626B2 patent drawing
  • US12505626B2 patent drawing

AI summary

A camera captures part of a surrounding scene to obtain a user view, disambiguating information uniquely identifying at least one controllable device or group of controllable devices in a set of controllable devices of a given type or at least one location or direction for a mobile controllable device is obtained, the user view and the disambiguating information relating to at least one controllable device overlaid on the user view are displayed on a display, a command intended to control at least one controllable device is received, wherein a command including at least part of the disambiguating information and a message based on the command is sent towards a corresponding controllable device.