Indoor Localization Quality Control Using Survey Data Consistency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing indoor navigation systems face challenges in providing reliable localization within buildings due to inaccurate data collection and errors in floor plans, especially when GPS signals are weak, leading to incorrect location estimations and low-quality data.
Innovation Solution
A method and device that flag survey data by receiving time-indexed logs from client devices, identifying paths, determining consistency scores, and adjusting constraints to generate an adjusted map for improved localization, using data from user inputs, orientation devices, and wireless network access points.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If data is collected by having an individual walk a collection device through various locations in the building, then coverage of the indoor space is improved, but the time required for data collection increases and measurement precision may deteriorate due to human error
Solution Approach 1:
The system segments the data collection process by distributing multiple client devices throughout the building simultaneously, rather than using a single device sequentially. Each device independently collects data in its respective location, dividing the overall task into parallel segments that reduce total collection time while maintaining comprehensive coverage.
Solution Approach 2:
Client devices automatically collect and transmit survey data without requiring manual intervention at each location. The devices self-manage the data collection process by recording wireless network signals, generating paths, and submitting data to the server, eliminating the time-consuming manual walking and data entry process.
2Loss of time
If existing floor plans and pre-generated databases are used for indoor navigation, then setup time is reduced, but measurement precision deteriorates due to errors in existing floor plans or recent building changes
Solution Approach 1:
The system implements feedback by comparing survey data collected from multiple client devices against the existing floor plan and constraints. The server analyzes consistency scores and identifies discrepancies between collected data and the stored map, flagging areas where the existing floor plan may be inaccurate or outdated, thereby improving location estimation accuracy.
Solution Approach 2:
The system performs preliminary validation by comparing collected survey data against existing floor plans before finalizing the indoor navigation database. This preliminary check identifies and flags potential errors in the existing floor plan, allowing for corrections to be made before the data is used for navigation, thus improving measurement precision.
3Productivity
If multiple client devices are used to collect survey data simultaneously, then data collection time is reduced, but device complexity increases due to the need to process and validate data from multiple sources
Solution Approach 1:
The server acts as an intermediary that receives, processes, and validates survey data from multiple client devices. It implements consistency checks by comparing data against existing floor plans and constraints, manages path identification, and handles flagging of inconsistent data. This centralizes the complex processing tasks, keeping client devices simple while maintaining high data collection productivity.
Data Source
AI summary
Aspects of the disclosure relate to quality control of survey data used to generate and or supplement map information. A device may be walked through an indoor space in order to collect survey data (accelerometer, gyroscope, wireless network identifiers, etc.). The survey data is then transmitted to a server for further processing to identify the path (or the various locations) of the device in the indoor space. The path may be determined by referring to a map of the indoor location and a localization algorithm, for example, a particle filter or least squares optimizer. The path may be compared to other survey data and paths from the same indoor space as well as the map in order to provide an estimate of the quality of the localization produced for the survey data. Low quality survey data may be flagged for further review or used to make changes to the map.


