Landmark2Vec: An Unsupervised Neural Network-Based Landmark Positioning Method

A Neural Network-based method for unsupervised landmarks map estimation from measurements taken from landmarks is introduced. The measurements needed for training the network are the signals observed/received from landmarks by an agent. The definition of landmarks, agent, and the measurements taken by agent from landmarks is rather broad here: landmarks can be visual objects, e.g., poles along a road, with measurements being the size of landmark in a visual sensor mounted on a vehicle (agent), or they can be radio transmitters, e.g., WiFi access points inside a building, with measurements being the Received Signal Strength (RSS) heard from them by a mobile device carried by a person (agent). The goal of the map estimation is then to find the positions of landmarks up to a scale, rotation, and shift (i.e., the topological map of the landmarks). Assuming that there are $L$ landmarks, the measurements will be $L \times 1$ vectors collected over the area. A shallow network then will be trained to learn the map without any ground truth information.

[1]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[2]  Gabriele Bitelli Introduction to Photogrammetry , 2013 .

[3]  I. D. Coope,et al.  Reliable computation of the points of intersection of $n$ spheres in $R^n$ , 2000 .

[4]  Yuxing Han,et al.  Weighted Centroid Localization Algorithm: Theoretical Analysis and Distributed Implementation , 2011, IEEE Transactions on Wireless Communications.

[5]  Markku Renfors,et al.  Statistical path loss parameter estimation and positioning using RSS measurements in indoor wireless networks , 2012, 2012 International Conference on Indoor Positioning and Indoor Navigation (IPIN).

[6]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[7]  Federico Thomas,et al.  Revisiting trilateration for robot localization , 2005, IEEE Transactions on Robotics.

[8]  Baoqi Huang,et al.  On the Reliable Localization of WiFi Access Points , 2019, IEEE Access.

[9]  Philip S. Yu,et al.  A Comprehensive Survey on Graph Neural Networks , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[10]  Mikko Valkama,et al.  K-Means Fingerprint Clustering for Low-Complexity Floor Estimation in Indoor Mobile Localization , 2015, 2015 IEEE Globecom Workshops (GC Wkshps).

[11]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[12]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[13]  Theodore S. Rappaport,et al.  Wireless communications - principles and practice , 1996 .

[14]  F. Golatowski,et al.  Weighted Centroid Localization in Zigbee-based Sensor Networks , 2007, 2007 IEEE International Symposium on Intelligent Signal Processing.

[15]  Naser El-Sheimy,et al.  Fast WiFi access point localization and autonomous crowdsourcing , 2014, 2014 Ubiquitous Positioning Indoor Navigation and Location Based Service (UPINLBS).

[16]  A. El-Rabbany Introduction to GPS: The Global Positioning System , 2002 .

[17]  T. Schenk,et al.  Introduction to Photogrammetry , 2022 .

[18]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[19]  Bertrand T. Fang,et al.  Trilateration and extension to Global Positioning System navigation , 1986 .