SignalSLAM: Simultaneous localization and mapping with mixed WiFi, Bluetooth, LTE and magnetic signals

摘要: Indoor localization typically relies on measuring a collection of RF signals, such as Received Signal Strength (RSS) from WiFi, in conjunction with spatial maps signal fingerprints. A new technology for could arise the use 4G LTE telephony small cells, limited range but rich strength information, namely Reference Power (RSRP). In this paper, we propose to combine an ensemble available sources signals build multi-modal that can be used or network deployment optimization. We primarily rely Simultaneous Localization and Mapping (SLAM), which provides solution challenge building map observations without knowing location observer. SLAM has recently been extended incorporate WiFi so-called WiFi-SLAM. parallel WiFi-SLAM, other algorithms have developed exploit inertial motion sensors known either RSS magnetic field magnitude. our study, all measurements acquired by off-the-shelf smartphone crowd-source data several experimenters walking freely through building, collecting time-stamped Bluetooth RSS, RSRP, magnitude, GPS reference points when outdoors, Near-Field Communication (NFC) readings at specific landmarks pedestrian dead reckoning based data. resolve users using modified version Graph-SLAM optimization poses absolute pairwise constraints incorporates similarity. demonstrate recover user positions thus simultaneously generate dense each access point cell, “from pocket”. Finally, performance selected single modalities, only generated.