Automatic Boundary Generation for XR Environments
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing artificial reality (XR) systems lack an efficient method to automatically define and manage boundaries within real-world environments, leading to potential user safety issues and suboptimal XR experiences.
Innovation Solution
The system determines a floor plane and generates a height map of the real-world environment, then automatically calculates a consecutive floor area by excluding areas with heights above or below thresholds, thereby defining a boundary for the XR environment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual boundary setup is used in XR systems, then users can define custom boundaries, but it increases setup time and complexity
Solution Approach 1:
The system performs automatic environment mapping and boundary generation without requiring manual user input. The XR system independently captures spatial data, processes it through machine learning models, and generates boundaries autonomously, eliminating the need for manual setup procedures.
Solution Approach 2:
The system pre-processes environment data by capturing spatial information and generating boundaries before the user begins the XR experience. This preliminary automatic setup occurs in the background, so boundaries are ready when the user starts using the system.
2Productivity
If automatic boundary generation is implemented, then setup time is reduced, but system complexity increases
Solution Approach 1:
The patent replaces manual mechanical boundary setup with an automated computational system using machine learning models and computer vision algorithms. The system uses sensors and cameras to capture environment data, processes it through neural networks, and automatically generates boundaries without manual intervention.
Solution Approach 2:
The system introduces an intermediate processing layer between environment capture and boundary definition. Machine learning models and spatial processing algorithms act as intermediaries that automatically transform raw sensor data into structured boundary definitions, reducing the need for complex manual configuration.
3Measurement precision
If detailed environment scanning is performed, then boundary accuracy is improved, but processing time increases
Solution Approach 1:
The system performs scanning and processing to a sufficient level of detail rather than exhaustive detail. It captures environment data with appropriate resolution and processes only the necessary features needed for accurate boundary definition, avoiding unnecessary processing of excessive data.
Solution Approach 2:
The system pre-processes and filters environment data during capture, identifying and prioritizing key spatial features before full boundary generation. This preliminary processing reduces the computational burden of subsequent detailed analysis while maintaining boundary accuracy.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
For artificial reality (XR) applications that need a guardian, aspects of the present disclosure can automatically determine where boundaries should be set in the real-world environment. Using a machine learning model, the automatic boundary system can detect the floor plane, then generate a height map of the real-world environment with the floor at zero. The height map can include positive heights (e.g., objects on the floor) and negative heights (e.g., downward leading stairs). The automatic boundary system can then generate a boundary for the area based on the detected heights by: applying thresholds to disregard objects at certain heights, applying thresholds to disregard open areas at certain widths, excluding oddly shaped areas that would constantly trigger the boundary if the user were nearby, etc. The user can further manually adjust the generated boundary in both directions (e.g., bringing it closer or further from the user).