Distributed Indoor Localization Without Fingerprint Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Indoor localization systems face challenges in achieving a balanced trade-off between energy-efficiency and accuracy, particularly in environments with significant multipath interference, such as hospitals, where existing technologies consume excessive energy and struggle with localization errors due to frequent recalculations of fingerprint maps and electromagnetic interference.
Innovation Solution
A distributed signal processing system that employs local signal processing using eigen structure algorithms and cloud-based signal processing with Sequential Monte Carlo algorithms and machine learning, eliminating the need for fingerprint maps, and utilizing RF tags that switch between active and inactive states only when necessary, along with deep FEC code techniques for energy-efficient data transmission.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If RF tags remain in an active state continuously to update locations frequently, then localization accuracy is improved, but energy consumption increases
Solution Approach 1:
The patent implements periodic action by having RF tags switch between active and inactive states. Tags remain inactive most of the time and only activate periodically when location updates are needed, rather than remaining continuously active. This periodic activation maintains localization accuracy while significantly reducing energy consumption compared to continuous active states.
Solution Approach 2:
The patent applies dynamics by making the tag state flexible and adaptive. RF tags can dynamically transition between inactive and active states based on system needs, and the system can adjust the frequency and timing of these transitions. This dynamic state management allows the system to optimize between accuracy and energy efficiency in real-time.
2Measurement precision
If fingerprint maps are recalculated frequently to maintain accuracy in dynamic environments, then localization accuracy is improved, but energy consumption increases
Solution Approach 1:
The patent applies periodic action to fingerprint map updates by recalculating maps only at scheduled intervals rather than continuously or frequently. This periodic recalibration maintains sufficient accuracy for dynamic environments while dramatically reducing the energy consumption associated with frequent map updates.
Solution Approach 2:
The patent utilizes parameter changes by adjusting the update frequency and timing of fingerprint map recalculations based on environmental conditions and system requirements. This allows the system to optimize between accuracy and energy efficiency by changing temporal parameters of map updates rather than using fixed frequent updates.
3Reliability
If RF tags are kept active after receiving wakeup signals to maintain network readiness, then system reliability is improved, but energy efficiency deteriorates
Solution Approach 1:
The patent implements periodic action by having RF tags return to inactive state immediately after receiving wakeup signals and only activating again when the next scheduled update time approaches. This eliminates the need for tags to remain continuously active after wakeup, maintaining system reliability through coordinated periodic activation while significantly improving energy efficiency.
Solution Approach 2:
The patent applies feedback mechanisms where receiving a wakeup signal triggers a specific response protocol. Tags use this feedback to synchronize their activation timing with the wakeup signal, allowing them to remain inactive between signals while maintaining network readiness through coordinated feedback-based synchronization.
4Loss of energy
If deep FEC code techniques are used for data transmission, then energy efficiency is improved, but transmission speed decreases
Solution Approach 1:
The patent applies parameter changes by adjusting transmission parameters such as coding rate, modulation scheme, and data rate based on the specific requirements of each transmission. The system can switch between different FEC code depths and transmission modes to optimize between energy efficiency and transmission speed for different communication scenarios.
Data Source
AI summary
Aspects of the present invention provide systems and methods for distributed signal processing of indoor localization signals wherein statistical algorithms and machine learning are used in place of a fingerprint map. The disclosure relates to calculation of angle and distance based on measurements of an indoor localization signal, followed by energy-efficient distribution of signal processing. Local signal processing is performed using any of multiple eigen structure algorithms or a linear probabilistic inference, before cloud-based signal processing is performed using a nonlinear probabilistic inference and machine learning that's been trained with historical data transmitted by the base stations and time-of-day location patterns. Without having to generate and constantly update an energy-exorbitant fingerprint map, the disclosed system reduces localization error to merely 50 cm with 95% probability without compromising energy-efficiency to rival the accuracy of indoor localization systems that utilize fingerprinting.