Collaborative AR Eyewear With VIO Ego-Motion Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing augmented reality (AR) technologies face challenges in enabling collaborative and shared AR experiences between wearable devices without relying on common image content or markers, which increases computational burden and requires complex global mapping pipelines.
Innovation Solution
The use of six degrees of freedom (6DOF) tracker trajectories, specifically visual inertial odometry (VIO) pose trackers, for ego motion alignment between eyewear devices, allowing local odometry systems to operate independently and share 3D content without the need for global mapping, reducing computational resources and memory usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If global mapping pipelines and common scene alignment are used for collaborative AR, then alignment precision between devices is improved, but device complexity and computational burden increase significantly
Solution Approach 1:
The patent segments the collaborative AR system into independent local coordinate systems for each device, with each device performing local odometry independently. This eliminates the need for a complex global mapping pipeline while maintaining alignment through ego-motion tracking, thereby reducing device complexity while preserving alignment precision.
Solution Approach 2:
The patent introduces a markerless intermediary object that serves as a reference point for alignment between devices. Instead of requiring direct global scene alignment, each device tracks the intermediary object independently to establish relative positions, simplifying the system architecture while maintaining precise alignment.
2Adaptability or versatility
If global mapping pipelines are implemented for shared AR experience, then collaborative functionality is improved, but processing time and computational resources increase
Solution Approach 1:
The patent divides the collaborative AR processing into independent local odometry tasks for each device rather than a centralized global mapping pipeline. Each device processes its own sensor data locally to determine ego-motion, enabling parallel processing that reduces overall processing time while maintaining full collaborative functionality.
Solution Approach 2:
Each device performs self-service local odometry independently without relying on other devices for global mapping computations. This autonomous approach allows simultaneous processing on multiple devices, significantly reducing processing time while enabling collaborative AR experiences through shared tracking of common objects.
3Measurement precision
If image sharing is used for alignment between devices, then alignment accuracy is improved, but security risks and piracy issues increase
Solution Approach 1:
The patent extracts the alignment function from image sharing and implements it through independent local odometry systems that track ego-motion and intermediary objects. This removes the security vulnerability of sharing proprietary image content while maintaining alignment accuracy through mathematical modeling of device motion and relative positioning.
Solution Approach 2:
Instead of sharing actual image content, the patent uses copies or representations of motion data and object positions through local coordinate systems. Each device independently generates its own representation of the shared environment through odometry, achieving alignment without exposing sensitive image data that could be pirated.
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
Enables lightweight and efficient sharing of 3D content between multiple users, allowing simultaneous modification and alignment of virtual objects, while preventing piracy issues by not requiring image sharing, and maintaining alignment without relying on common scene alignment.
Implementation Method 1
The VIO pose tracker may comprise a visual inertial odometry (VIO) pose tracker
Implementation Method 2
An inertial measurement unit (IMU) may also be used to align the eyewear devices
Data Source
AI summary
Eyewear providing an interactive augmented reality experience between two eyewear devices by using alignment between respective 6DOF trajectories, also referred to herein as ego motion alignment. An eyewear device of user A and an eyewear device of user B track the eyewear device of the other user, or an object of the other user, such as on the user's face, to provide the collaborative AR experience. This enables sharing common three-dimensional content between multiple eyewear users without using or aligning the eyewear devices to common image content such as a marker, which is a more lightweight solution with reduced computational burden on a processor. An inertial measurement unit may also be used to align the eyewear devices.