Landmark-Based Localization Calibration for AR Glasses

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing navigation technologies, such as GPS and IMUs, lack precision and accuracy in localized areas due to drift and other issues, making it difficult to determine user position and orientation within small areas.

Innovation Solution

Utilizing physically-identifiable landmarks to calibrate localization parameters through sensor data, enabling precise determination of orientation and position using head-wearable devices like augmented-reality headsets.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If GPS and IMU are used for navigation, then coverage area is large, but localization precision deteriorates in small localized areas

Engineering Contradiction:
Improvelocalization precisionVSAvoidcoverage area
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent segments the localization system into two distinct modes: a global localization mode using GPS/IMU for large-area coverage, and a local high-precision mode using visual landmarks for small-area precision. The system dynamically switches between these segmented approaches based on the operational context, allowing both large coverage and high precision to be achieved in their respective domains.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces visual landmarks as an intermediary element that bridges the gap between global GPS/IMU localization and local precise positioning. By detecting and matching physical landmarks in the environment, the system obtains absolute position and orientation data that corrects and calibrates the drift-affected IMU measurements, thereby achieving high precision without sacrificing coverage area.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If IMU is used for localization, then it provides continuous positioning, but accuracy deteriorates due to drift

Engineering Contradiction:
Improvelocalization accuracyVSAvoiddrift resistance
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent implements a feedback mechanism where visual landmark detection provides periodic absolute position and orientation references that feed back to correct IMU drift. The system continuously monitors landmark features and uses the obtained ground-truth data to recalibrate and reset the IMU's accumulated errors, thereby maintaining high accuracy over time while preserving continuous positioning capability.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent performs preliminary calibration of the IMU system by detecting physical landmarks and establishing absolute position and orientation references before beginning precise tracking. This preliminary action sets the initial accurate state for the IMU, preventing drift from accumulating significantly, and creates a reference framework against which subsequent measurements can be validated and corrected.

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If visual landmarks are used for calibration, then localization accuracy improves, but system complexity increases

Engineering Contradiction:
Improvelocalization accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent makes the head-wearable device's imaging sensors serve multiple functions: they are used both for augmented reality display content and for detecting physical landmarks for localization calibration. This multi-functionality allows the system to achieve high localization accuracy without adding dedicated hardware, as the existing camera system performs dual roles, thereby minimizing the increase in system complexity.

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

Solution Approach 2:

The system uses its own imaging sensors and processing capabilities to perform self-calibration by detecting and matching visual landmarks in the environment. Rather than requiring external calibration equipment or additional specialized sensors, the system serves itself by utilizing its existing resources to obtain and process landmark data, thereby achieving high accuracy without proportionally increasing system complexity.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS20260010226A1Techniques for calibrating localization parameters based on physically-identifiable landmarks, and systems, devices and methods of using such techniques
Publication Date: 2026.01.08 META PLATFORMS TECHNOLOGIES LLC
  • US20260010226A1 patent drawing
  • US20260010226A1 patent drawing
  • US20260010226A1 patent drawing

AI summary

A method of interacting with extended-reality glasses is provided. The method includes determining, based on the sensor data, that a landmark-based-localization condition is satisfied. The method further includes, in accordance with determining that the landmark-based-localization condition is satisfied, obtaining data about a physically-identifiable feature of a physical landmark detectable from the localized physical area. And the method includes, based on (i) the data about the physically-identifiable feature of the physical landmark, and (ii) other data indicating a time when the data about the physically-identifiable feature of the physical landmark was obtained, determining an orientation and/or and a position of the head-wearable device within the localized physical area.