Motion Mode Classification for Portable Inertial Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current navigation systems face challenges in accurately determining the mode of motion or conveyance of a device within a platform, especially when the device is not strapped and has unconstrained mobility, and in environments where clear line of sight to satellite signals is not guaranteed, such as indoors, due to high noise and random drift rates from MEMS sensors.
Innovation Solution
A method and system that utilize measurements from sensors like accelerometers, gyroscopes, and barometers to build a classifier model for determining the mode of motion or conveyance, which can function with or without GNSS information, using feature extraction and classification techniques, and can handle various device orientations and usage scenarios.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If MEMS sensors are used for navigation in portable devices, then device portability and versatility are improved, but measurement precision and reliability deteriorate due to high noise and random drift rates
Solution Approach 1:
The patent introduces an intermediary classification system that processes raw sensor data through feature extraction and mode classification before navigation computation. This intermediary layer separates the noisy raw measurements from the navigation algorithm, allowing the use of portable MEMS sensors while maintaining navigation accuracy by operating on classified motion modes rather than raw sensor data
Solution Approach 2:
The patent replaces direct reliance on precise mechanical sensor measurements with a computational approach using machine learning classifiers. Instead of depending on the physical precision of MEMS sensors, the system uses data-driven classification to determine motion modes, substituting mechanical precision requirements with computational processing
2Ease of operation
If the device is allowed to move freely within the platform for portability, then ease of operation is improved, but measurement precision deteriorates due to changing orientations and positions
Solution Approach 1:
The patent embraces the dynamic nature of free-moving devices by implementing a classification system that adapts to changing device orientations and positions. The system continuously classifies motion modes based on current sensor readings, allowing the navigation system to remain accurate regardless of device mobility or orientation changes within the platform
Solution Approach 2:
The patent changes the parameter space from raw sensor measurements to classified motion modes. By transforming the problem from direct sensor data usage to classification-based mode determination, the system becomes insensitive to device orientation and position changes, enabling free mobility without compromising navigation precision
3Measurement precision
If inertial sensors are fixed and aligned with the platform for accurate navigation, then measurement precision is improved, but ease of operation deteriorates due to mounting constraints
Solution Approach 1:
The patent inverts the traditional approach by not trying to align sensors with the platform, but rather aligning the navigation solution with the device's local coordinate system. The classification-based approach determines motion modes in the device's reference frame, eliminating the need for precise mechanical alignment between sensors and platform
4Adaptability or versatility
If AGPS and cell tower methods are used for positioning, then absolute position can be determined without line of sight to satellites, but measurement precision deteriorates in indoor environments and heading information is incomplete
Solution Approach 1:
The patent merges inertial sensor data with classification-based motion mode determination to create a hybrid navigation system. This combination provides both absolute positioning capability (when available) and precise relative navigation (through motion classification), achieving complete heading information and improved indoor localization precision by supplementing AGPS/cell tower methods with inertial classification data
Data Source
AI summary
A method and system for determining the mode of motion or conveyance of a device, the device being within a platform (e.g., a person, vehicle, or vessel of any type). The device can be strapped or non-strapped to the platform, and where non-strapped, the mobility of the device may be constrained or unconstrained within the platform and the device may be moved or tilted to any orientation within the platform, without degradation in performance of determining the mode of motion. This method can utilize measurements (readings) from sensors in the device (such as for example, accelerometers, gyroscopes, etc.) whether in the presence or in the absence of navigational information updates (such as, for example, Global Navigation Satellite System (GNSS) or WiFi positioning). The present method and system may be used in any one or both of two different phases, a model building phase or a model utilization phase.