Fast Signals of Opportunity Fingerprint Database Maintenance with Autonomous Unmanned Ground Vehicle for Indoor Positioning

Indoor positioning technology based on Received Signal Strength Indicator (RSSI) fingerprints is a potential navigation solution, which has the advantages of simple implementation, low cost and high precision. However, as the radio frequency signals can be easily affected by the environmental change during its transmission, it is quite necessary to build location fingerprint database in advance and update it frequently, thereby guaranteeing the positioning accuracy. At present, the fingerprint database building methods mainly include point collection and line acquisition, both of which are usually labor-intensive and time consuming, especially in a large map area. This paper proposes a fast and efficient location fingerprint database construction and updating method based on a self-developed Unmanned Ground Vehicle (UGV) platform NAVIS, called Automatic Robot Line Collection. A smartphone was installed on NAVIS for collecting indoor Received Signal Strength Indicator (RSSI) fingerprints of Signals of Opportunity (SOP), such as Bluetooth and Wi-Fi. Meanwhile, indoor map was created by 2D LiDAR-based Simultaneous Localization and Mapping (SLAM) technology. The UGV automatically traverse the unknown indoor environment due to a pre-designed full-coverage path planning algorithm. Then, SOP sensors collect location fingerprints and generates grid map during the process of environment-traversing. Finally, location fingerprint database is built or updated by Kriging interpolation. Field tests were carried out to verify the effectiveness and efficiency of our proposed method. The results showed that, compared with the traditional point collection and line collection schemes, the root mean square error of the fingerprinting-based positioning results were reduced by 35.9% and 25.0% in static tests and 30.0% and 21.3% respectively in dynamic tests. Moreover, our UGV can traverse the indoor environment autonomously without human-labor on data acquisition, the efficiency of the automatic robot line collection scheme is 2.65 times and 1.72 times that of the traditional point collection and the traditional line acquisition, respectively.

[1]  Yunhao Liu,et al.  Locating in fingerprint space: wireless indoor localization with little human intervention , 2012, Mobicom '12.

[2]  Yuwei Chen,et al.  Fast Fingerprint Database Maintenance for Indoor Positioning Based on UGV SLAM , 2015, Sensors.

[3]  Simo Ali-Löytty,et al.  A comparative survey of WLAN location fingerprinting methods , 2009, 2009 6th Workshop on Positioning, Navigation and Communication.

[4]  Yuwei Chen,et al.  NAVIS-An UGV Indoor Positioning System Using Laser Scan Matching for Large-Area Real-Time Applications , 2014, Sensors.

[5]  Marc Langheinrich,et al.  Improving Location Fingerprinting through Motion Detection and Asynchronous Interval Labeling , 2009, LoCA.

[6]  Songtao Guo,et al.  A novel radio map construction method to reduce collection effort for indoor localization , 2016 .

[7]  A.E.F. Ryerson,et al.  Vehicle Path Planning for Complete Field Coverage Using Genetic Algorithms , 2007 .

[8]  Komwut Wipusitwarakun,et al.  Indoor localization improvement via adaptive RSS fingerprinting database , 2013, The International Conference on Information Networking 2013 (ICOIN).

[9]  Peter Brida,et al.  Wi-Fi Fingerprint Radio Map Creation by Using Interpolation , 2017 .

[10]  Cyrill Stachniss,et al.  Simultaneous Localization and Mapping , 2016, Springer Handbook of Robotics, 2nd Ed..

[11]  Yuwei Chen,et al.  Bayesian Fusion for Indoor Positioning Using Bluetooth Fingerprints , 2013, Wirel. Pers. Commun..

[12]  Ralph L. Hollis,et al.  Contact sensor-based coverage of rectilinear environments , 1999, Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014).

[13]  Naser El-Sheimy,et al.  PDR/INS/WiFi Integration Based on Handheld Devices for Indoor Pedestrian Navigation , 2015, Micromachines.

[14]  Philipp Scholl,et al.  Fast indoor radio-map building for RSSI-based localization systems , 2012, 2012 Ninth International Conference on Networked Sensing (INSS).

[15]  Andrew G. Dempster,et al.  A new method to generate and maintain a WiFi fingerprinting database automatically by using RFID , 2012, 2012 International Conference on Indoor Positioning and Indoor Navigation (IPIN).

[16]  Yi Liu,et al.  Indoor Fingerprint Positioning Based on Wi-Fi: An Overview , 2017, ISPRS Int. J. Geo Inf..

[17]  Yi Zhang,et al.  Unsupervised Indoor Localization Based on Smartphone Sensors, iBeacon and Wi-Fi , 2018, 2018 Ubiquitous Positioning, Indoor Navigation and Location-Based Services (UPINLBS).

[18]  Jing Liu,et al.  Survey of Wireless Indoor Positioning Techniques and Systems , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[19]  Robert Harle,et al.  SmartSLAM - An Efficient Smartphone Indoor Positioning System Exploiting Machine Learning and Opportunistic Sensing , 2013 .

[20]  Shau-Shiun Jan,et al.  Received Signal Strength Database Interpolation by Kriging for a Wi-Fi Indoor Positioning System , 2015, Sensors.

[21]  Robert Harle,et al.  Location Fingerprinting With Bluetooth Low Energy Beacons , 2015, IEEE Journal on Selected Areas in Communications.

[22]  Mingming Lu,et al.  Reducing fingerprint collection for indoor localization , 2016, Comput. Commun..

[23]  S.X. Yang,et al.  A neural network approach to complete coverage path planning , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[24]  Santiago Mazuelas,et al.  Robust Indoor Positioning Provided by Real-Time RSSI Values in Unmodified WLAN Networks , 2009, IEEE Journal of Selected Topics in Signal Processing.