Mobile Augmented Reality Task Scheduling via Context Profiling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile Augmented Reality (MAR) technologies face performance issues due to time-consuming rendering and image processing tasks on mobile devices with limited resources, leading to poor application performance and user experience, as existing scheduling methods fail to effectively utilize resources and improve performance significantly.
Innovation Solution
A task scheduling system for MAR that includes a mobile device with a CPU and GPU, featuring a Network Profiling Component, Device Profiling Component, Application Profiling Component, and a Scheduling Component to gather and utilize context data for optimal task scheduling between the CPU, GPU, and a workspace, employing co-scheduling methods and conflict management to balance workload and minimize time delays.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If rendering and image processing tasks are performed on mobile devices, then real-time MAR interaction is achieved, but mobile device resources are overwhelmed leading to poor performance
Solution Approach 1:
The patent segments MAR tasks into different types (rendering, image processing, tracking, registration) and distributes them across multiple processing units (CPU, GPU, and external workspace), preventing any single mobile device resource from being overwhelmed while maintaining real-time processing capabilities
Solution Approach 2:
The patent introduces an external workspace dimension beyond the mobile device itself, creating a distributed processing architecture where tasks can be offloaded to additional computational resources, thereby expanding the system's overall processing capacity without compromising real-time performance
2Productivity
If more computational resources are allocated to mobile devices, then processing capability is improved, but device complexity and resource limitations are exacerbated
Solution Approach 1:
The patent creates a universal scheduling system that can dynamically allocate tasks across diverse processing resources (CPU, GPU, external workspace) based on task requirements and resource availability, providing enhanced computational capability without requiring every mobile device to possess all necessary resources
Solution Approach 2:
The scheduling component acts as an intermediary that manages task distribution between mobile devices and external workspace, abstracting the complexity of resource management from individual devices while coordinating computational efforts across the entire system to achieve improved processing capability
3Ease of operation
If traditional scheduling methods are used, then task execution is simplified, but resource utilization is insufficient leading to poor performance
Solution Approach 1:
The patent implements dynamic scheduling that adapts to changing resource availability and task requirements in real-time, continuously optimizing task allocation between CPU, GPU, and external workspace based on current system state, thereby achieving high resource utilization without sacrificing operational simplicity
Data Source
AI summary
A system for scheduling mobile augmented reality tasks performed on at least one mobile device and a workspace includes: a mobile device, comprising a central processing unit (CPU) and a graphics processing unit (GPU); a Network Profiling Component, configured to gather network related context data; a Device Profiling Component, configured to gather hardware related context data; an Application Profiling Component, configured to gather application related context data; and a Scheduling Component, configured to receive the network related context data, the hardware related context data, and the application related context data, and to schedule tasks between the CPU, the GPU and the workspace.