Energy Management in Autonomous Vessels Using Restricted Boltzmann Machine
ResumoThe management of energy in autonomous vehicles is an essential part to guarantee their autonomy and longevity, especially in autonomous sailboats. In this work we propose a methodology for the application of the Restricted Boltzmann Machine (RBM) neural network that aims to find a better way to use the distribution of energy consumption with solar panels in an autonomous sailboat equipped with a reserve electrical engine. The RBM receives input data from sensors coupled to the vessel and the output is an estimate of the overall dynamic energy consumption. We carried out an experiment using data from a vessel similar to the F-Boat that navigate and collect data in a region of lagoons in Rio Grande do Norte. The results show that it is possible to increase the level of confidence in the remaining stored energy and potential energy generation in the near future using this approach.
Palavras-chave: Potential energy, Energy consumption, Navigation, Neural networks, Sensors, Solar panels, Vehicle dynamics
CORREA, Wanderson; ARAÚJO, André P. D. de; AGUIAR, Rodrigo B. de; SANTOS, Davi Henrique Dos; DIAS, Daniel; CLUA, Esteban W. G.; GONÇALVES, Luiz M. G.. Energy Management in Autonomous Vessels Using Restricted Boltzmann Machine. In: SIMPÓSIO BRASILEIRO DE ROBÓTICA E SIMPÓSIO LATINO AMERICANO DE ROBÓTICA (SBR/LARS), 13. , 2021, Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2021 . p. 66-71.