AR Map Reconciliation via Confidence Score Anchoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Augmented Reality (AR) systems face challenges in accurately mapping and displaying virtual objects in environments, particularly when multiple devices with different perspectives and confidence scores are involved, leading to inconsistencies and inaccuracies in object positioning and visibility.
Innovation Solution
The method involves reconciling environmental maps created by multiple devices by determining confidence scores for object locations and anchoring AR objects in a reconciled map based on these scores, allowing for accurate and consistent display of virtual objects beyond the visible range of individual devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple devices create environmental maps independently, then each device can operate autonomously and capture its own perspective, but inconsistencies and inaccuracies in object positioning occur when maps are combined
Solution Approach 1:
The patent introduces a server as an intermediary that receives environmental maps from multiple devices, reconciles their different perspectives and confidence scores, and generates a unified reconciled map. This mediator coordinates the multi-device data fusion process, allowing autonomous device operation while ensuring accurate object positioning through centralized map reconciliation.
2Productivity
If a single device creates an environmental map, then the mapping process is simple and fast, but the coverage and comprehensiveness of the environment representation is limited
Solution Approach 1:
The patent merges environmental maps from multiple devices by combining their respective data on the server. Each device continues to map quickly from its own perspective, and the server consolidates these individual maps into a comprehensive reconciled map that covers the entire environment, eliminating information loss while maintaining individual device productivity.
3Measurement precision
If confidence scores are used to select object locations from multiple maps, then positioning accuracy improves, but the complexity of reconciling multiple maps increases
Solution Approach 1:
The patent implements a feedback mechanism where confidence scores from multiple devices are continuously evaluated and used to select the most reliable object locations for the reconciled map. The server compares confidence scores, selects optimal positions, and updates the reconciled map accordingly, creating a feedback loop that improves positioning accuracy while managing reconciliation complexity through systematic score-based decision making.
Data Source
AI summary
Embodiments provide for reconciling a first map of an environment created by a first device with a second map of the environment created by a second device by determining a first confidence score for a first location of a given object in the first map; determining a second confidence score for a second location of the given object in the second map; inserting the given object into a reconciled map at a position based on the first confidence score and the second confidence score; anchoring an Augmented Reality object in the reconciled map at coordinates based on the position of the given object; and outputting the reconciled map to an Augmented Reality device.