Visual-Inertial Mapping With Stereo Pose Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies for providing fast, accurate, and reliable positional awareness to autonomous robots and wearable devices, such as VR/AR headsets, face challenges including high costs, power consumption, and interference issues with existing methods like RFID, WiFi, and depth sensors, while visual approaches are slow and suffer from scale ambiguity.
Innovation Solution
The implementation of a visual-inertial sensor system that combines low-cost grayscale and RGB cameras with a low-power control unit to process image and inertial data efficiently, offloading computational tasks from the main processor, using stereo imaging capabilities and inertial data to correct pose estimates and reduce energy consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If RFID/WiFi approaches are used for positional awareness, then coverage area is improved, but cost increases and accuracy is limited
Solution Approach 1:
The patent combines multiple sensing modalities (visual sensors, inertial sensors, RFID, WiFi) into a unified positioning system. The visual-inertial system provides accurate short-range positioning while RFID and WiFi provide broader coverage, with the system dynamically selecting and fusing data from appropriate sources to achieve both accuracy and extensive coverage area.
2Measurement precision
If depth sensors are used for positional awareness, then accuracy is improved, but power consumption increases and cost increases
Solution Approach 1:
The system dynamically adjusts sensor activation and processing intensity based on operational context. Visual sensors operate at variable frame rates and resolution levels, while depth sensors are activated only when necessary. The inertial sensor continuously operates at low power to provide baseline tracking, reducing overall power consumption while maintaining accuracy requirements.
Solution Approach 2:
The positioning system is divided into multiple independent sensing modules (visual, inertial, RFID, WiFi) that can operate semi-independently. This segmentation allows the system to activate only the necessary subsystems for each specific task, reducing overall power consumption while maintaining accuracy when needed.
3Measurement precision
If marker based approaches are used for positional awareness, then accuracy is improved, but the useful operating area is limited
Solution Approach 1:
The system creates virtual markers through visual feature detection and reconstruction of environmental features, eliminating the need for physical markers. The visual-inertial system detects and tracks natural features in the environment, generating virtual marker representations that provide accurate positioning without requiring physical marker placement, thereby expanding the useful operating area to any visually detectable environment.
4Ease of manufacture
If visual approaches are used for positional awareness, then cost is reduced, but speed decreases and scale ambiguity occurs
Solution Approach 1:
The inertial sensor acts as an intermediary that provides high-speed preliminary tracking data to guide visual processing. The inertial data predicts device position and orientation, allowing the visual system to process only relevant image regions at reduced resolution, thereby maintaining low cost while improving processing speed and eliminating scale ambiguity through sensor fusion.
Data Source
AI summary
The described positional awareness techniques employing visual-inertial sensory data gathering and analysis hardware with reference to specific example implementations implement improvements in the use of sensors, techniques and hardware design that can enable specific embodiments to provide positional awareness to machines with improved speed and accuracy.