Simultaneous localization and mapping using spatial and temporal coherence for indoor location
AssigneeIntel Corporation
InventorsShao-Wen Yang, Xue Yang, Lei Yang
Life of this patent
Estimating the term…
Abstract
This document discloses one or more systems, apparatuses, methods, etc. for detecting precise indoor location of a portable wireless device based on a WiFi simultaneous localization and mapping (SLAM) algorithm that implements spatial and temporal coherence. In an implementation, a SLAM algorithm includes WiFi similarities and inertial navigational system (INS) measurements data as location estimates (i.e., references) for the spatial and temporal coherences implementations to constitute the WiFi SLAM algorithm.
Claims29
A device comprising:
- a WLAN similarity component that implements an algorithm to obtain a first level coarse indicator on a revisit point based from similarities of received radio signal that includes at least a received signal strength indicator (RSSI), signal time-of-flight, or channel fading profiles of the radio signal at different time steps;
- an inertial navigation system (INS) dead reckoning estimator component that estimates motion trajectory of the device at different time steps;
- a spatial coherence component that implements a spatial coherence algorithm to obtain a spatial confidence level on the revisit point by analyzing trajectory structure similarity that is based from the estimated motion trajectory;
- a temporal coherence component that utilizes a fuzzy matching algorithm to detect similarity at multiple time steps on the analyzed trajectory structure similarity and the first level coarse indicator;
- and
- a loop closing detector that performs a threshold measurement on the detected similarity to determine occurrence of the revisit point.
A method of implementing a WLAN simultaneous localization and mapping (SLAM) algorithm comprising:
- increasing a time step by one to obtain a current time step;
- updating inertial sensor sample at the current time step;
- estimating inertial dead reckoning position based on the updated inertial sensor sample to obtain estimated trajectory;
- determining spatial coherence of the estimated trajectory, wherein the spatial coherence uses similarity measures that include mean difference, Euclidean distance, or correlation coefficient between coherence features to obtain spatial confidence level;
- updating a WLAN signal sample at the current time step;
- determining WLAN similarity at a revisit point based on the updated WLAN signal sample at the current time step;
- performing sequence alignment on the WLAN similarity and the spatial coherence level at multiple time steps to provide a matching sequence length;
- comparing the matching sequence length with a threshold to detect the revisit point;
- and
- outputting optimized location estimates and a WLAN fingerprint map using revisit point constraints based on the sequence alignment for temporal coherence detection.
At least non-transitory one computer accessible medium that performs a method of implementing a WLAN simultaneous localization and mapping (SLAM) algorithm comprising:
- estimating inertial dead reckoning position based on an inertial sensor sample to obtain estimated motion trajectory;
- determining spatial coherence level of an estimated motion trajectory obtained by an updated sensor sample, wherein the spatial coherence uses an algorithm to determine similarity of trajectory local structure among different trajectory segments to obtain spatial coherence level;
- updating a radio signal sample at a time step;
- determining WLAN similarity along traversed trajectory to determine a revisit point based on the updated radio signal;
- performing sequence alignment on the WLAN similarity and the spatial coherence level at multiple time steps to obtain a matching sequence length;
- and
- comparing the matching sequence length with a threshold to detect occurrence of the revisit point.
Dependencies are inferred from the claim text.