Collaborative spatial reasoning for environment mapping using unmanned aerial vehicles

• Autor(a) principal: Sécolo, A. C.
• Data de Publicação: 2022
• Tipo de documento: Tese
• Idioma: eng
• Título da fonte: Biblioteca Digital de Teses e Dissertações da FEI
• Texto Completo: https://repositorio.fei.edu.br/handle/FEI/4437; https://doi.org/10.31414/EE.2022.T.131409
• topic: collaborative spatial reasoning; qualitative spatial reasoning; Allen's interval algebra; environment mapping

The goal of this project is the investigation of existing spatial reasoning formalism for collaborative systems, in order to interpret a scene from multiple viewpoints in the task of environment mapping. Motivated by the increasing need of interaction between humans and robots, Qualitative Spatial Reasoning (QSR) theories are integrated into a single formalism for modeling the perceptions of remotely operated Unmanned Aircraft Vehicles (UAV). Qualitative theories enables the exchange of information between humans and robotic agents, so that they can perform tasks in collaborative missions involving searching and monitoring objectives in agriculture, natural disasters, searching and rescue tasks, among others. The combination of the studied spatial theories led to the development of two formalism: the LH Interval Calculus and the Collaborative Spatial reasoning. LH Interval Calculus consists in the combination of Region Connection Calculus and Allen’s Interval Algebra to describe the relations of two objects from an aerial point of view. Collaborative Spatial Reasoning combines the Cardinal Direction Calculus with LH Interval Calculus to the task of environment mapping where agents have a partial view of the scene. UAVs equipped with cameras are the platform used to test the formalism of this project, capturing images with a partial view of the environment, from different directions of flight. The results obtained showed that the two formalism proposed were successful in the task of mapping the environment