Open AccessA SLAM system based on Hidden Markov Models
Author(s) -
Oscar Fuentes,
Jesús Savage,
Luis Contreras
Publication year - 2021
Publication title -
informatika i avtomatizaciâ/informatika i avtomatizaciâ (print)
Language(s) - English
Resource type - Journals
eISSN - 2713-3206
pISSN - 2713-3192
DOI - 10.15622/ia.2022.21.7
Subject(s) - hidden markov model , computer science , robot , artificial intelligence , simultaneous localization and mapping , cluster analysis , representation (politics) , sensor fusion , set (abstract data type) , markov chain , graph , pattern recognition (psychology) , machine learning , mobile robot , theoretical computer science , programming language , politics , political science , law
We present a graph SLAM system based on Hidden Markov Models (HMM) where the sensor readings are represented with different symbols using a number of clustering techniques; then, the symbols are fused as a single prediction, to improve the accuracy rate, using a Dual HMM. Our system’s versatility allows to work with different types of sensors or fusion of sensors, and to implement, either active or passive, graph SLAM. The Toyota HSR (Human Support Robot) robot was used to generate the data set in both real and simulated competition environments. We tested our system in the kidnapped robot problem by training a representation, improving it online, and, finally, solving the SLAM problem.