Feature-Based SLAM Radio Map Generation for Indoor Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional GPS-based location determination methods are inaccurate in environments with obstructed line of sight, such as indoors or in areas with tall buildings, leading to errors in determining specific locations like floors, rooms, or blocks.
Innovation Solution
A feature-based simultaneous localization and mapping (SLAM) system that generates more accurate radio maps by processing trace data from mobile devices, including wireless access point data and sensor measurements, to determine the best estimate of a mobile device's state and create a posterior probability-based radio map for unsurveyed environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If GPS signals are used for location determination, then outdoor positioning can be achieved, but accuracy deteriorates in environments with obstructed line of sight such as indoors or areas with tall buildings
Solution Approach 1:
The patent introduces wireless access points as intermediary objects to enable location determination in GPS-denied environments. Instead of directly using GPS satellites, the system uses local WiFi access points as mediators to provide positioning information indoors, where GPS signals are blocked by buildings
Solution Approach 2:
The patent replaces the GPS satellite-based electromagnetic signal system with a local WiFi-based electromagnetic signal system for indoor positioning. This substitution allows the system to operate in environments where the original GPS system fails due to signal obstruction
2Ease of operation
If conventional GPS methods are used, then location can be determined with tens of meters error margin, but this error margin is too large for determining specific floors, rooms, or blocks
Solution Approach 1:
The patent applies local quality by using locally-available WiFi access points for positioning instead of distant GPS satellites. The system leverages the fact that WiFi access points are distributed throughout the indoor environment, providing location-specific signal characteristics that enable precise positioning at the level of floors, rooms, or blocks
Solution Approach 2:
The patent transitions from two-dimensional GPS positioning (latitude and longitude) to three-dimensional positioning by incorporating vertical floor information. The system determines not only horizontal position but also the floor level, enabling precise location determination within multi-story buildings
3Measurement precision
If radio maps are generated for unsurveyed environments using trace data from multiple mobile devices, then measurement precision improves, but device complexity increases due to processing trace data and computing posterior probabilities
Solution Approach 1:
The patent merges trace data from multiple mobile devices to collectively build and refine radio maps for unsurveyed environments. By combining data from multiple sources, the system achieves higher measurement precision while distributing the processing burden across multiple devices rather than requiring a single complex system
Data Source
AI summary
Embodiments are disclosed for a feature-based simultaneous localization and mapping (SLAM) system and method that generates radio maps for environments that are not accessible for surveying. More accurate radio maps are generated for an unsurveyed environment by determining a best estimate of a mobile device state from harvested traced data that maximizes a posterior probability of the mobile device state given measurements, landmarks and loop constraints.