Português English
Contato

Tese de Doutorado de Mathias Fassini Mantelli


Detalhes do Evento


Aluno: Mathias Fassini Mantelli
Orientadora: Profa. Dra. Mariana Luderitz Kolberg Fernandes
Coorientador: Prof. Dr. Renan de Queiroz Maffei

Título: Exploiting organisational semantic information in indoor environments for the object search problem
Linha de Pesquisa: Planejamento, Sistemas Multiagentes e Robótica

Data: 27/05/2022
Horário: 14h
Esta banca ocorrerá excepcionalmente de forma totalmente remota. Interessados em assistir a defesa poderão acessar a sala virtual através do link: https://meet.google.com/qdm-tkpx-vjt

Banca Examinadora:
– Prof. Dr. Roseli Aparecida Francelin Romero (USP)
– Prof. Dr. Edison Pignaton de Freitas (UFRGS)
– Prof. Dr. Vitor Augusto Machado Jorge (UFABC)

Presidente da Banca: Profa. Dra. Mariana Luderitz Kolberg Fernandes

Abstract: Nowadays, the mobile robotics research community deals with different high-level tasks that require the robot to manipulate or interact with objects that may not be in the robot’s field of view. To find an object in unknown environments, the robot needs to look for it while gaining information about the environment and making decisions in real-time, known as the object search (OS) problem. The research community has proposed different approaches for dealing with the OS problem, relying on the objects’ color or 3D shape as visual cues to guide the search. However, this geometric information (i.e., color or size) limits the robot’s perception and, consequently, the robot’s performance during the search. Therefore, we propose two OS systems that exploit the advantages of semantic information inferred from the organisation of both the environment and objects. The first one relies on semantic information inferred from numbers in text signs found in the environment. The goal is to find a target door label. The use of organisational semantic information in this scenario allows the robot to reduce the search costs by avoiding not promising corridors to contain the target door label. The detected numbers are used to estimate either the search continues towards unknown parts of the environment, or carefully search in the already known parts. The second proposed OS system is based on the changes in the organisation and arrangement of objects over time in the environment. It observes the environment and gathers data from the objects’ placement through the time by executing its recording mode. This recorded data is later used when the robot executes the requesting mode to search for the target object. Both systems were evaluated in different environments and compared against other OS approaches in simulated and real scenarios. The results support our systems’ efficiency and demonstrate the improvement in the searching performance with the aid of organisational semantic information.

Keywords: Mobile robotics. Object search. Organisational semantic information. Robotics perception. Indoor environments.