RT Conference Proceedings
T1 Towards a Semantic Gas Source Localization under Uncertainty
A1 González-Monroy, Javier
A1 Ruiz-Sarmiento, José Raúl
A1 Moreno-Dueñas, Francisco Ángel
A1 Galindo-Andrades, Cipriano
A1 González-Jiménez, Antonio Javier
K1 Robótica
AB This work addresses the problem of efficiently and coherentlylocating a gas source in a domestic environment with a mobilerobot, meaning efficiently the coverage of the shortest distance as possibleand coherently the consideration of different gas sources explainingthe gas presence. The main contribution is the exploitation, for thefirst time, of semantic relationships between the gases detected and theobjects present in the environment to face this challenging issue. Ourproposal also takes into account both the uncertainty inherent in thegas classification and object recognition processes. These uncertaintiesare combined through a probabilistic Bayesian framework to provide apriority-ordered list of (previously observed) objects to check. Moreoverthe proximity of the different candidates to the current robot locationis also considered by a cost function, which output is used for planningthe robot inspection path. We have conducted an initial demonstrationof the suitability of our gas source localization approach by simulatingthis task within domestic environments for a variable number of objects,and comparing it with an greedy approach.
YR 2018
FD 2018-06-28
LK https://hdl.handle.net/10630/16047
UL https://hdl.handle.net/10630/16047
LA eng
NO Towards a Semantic Gas Source Localization under Uncertainty.Communications in Computer and Information Science book series (CCIS, volume 855), doi:10.1007/978-3-319-91479-4_42
NO Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech.
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 22 ene 2026