Robust and Accurate Localization System for Mobile Manipulators in Cluttered Environments

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2015

Autores

Costa, CM (Autor) Outra; Sobreira, HM (Autor) Outra; Armando Jorge Sousa (Autor) FEUP; Germano Veiga (Autor) FEUP

Ata de Conferência Internacional

Título: Proceedings of the IEEE International Conference on Industrial Technology

Páginas: 3308-3313

2015 IEEE International Conference on Industrial Technology, ICIT 2015

17 March 2015 through 19 March 2015

Indexação

ISI Web of Knowledge - 2 Citações

Scopus - 2 Citações

Outras Informações

ID Authenticus: P-00G-EK5

DOI: 10.1109/icit.2015.7125588

Abstract (EN): Autonomous robots play a pivotal role in improving productivity and reducing operational costs. They excel at both precision and speed in repetitive jobs and can cooperate with humans in complex tasks within dynamic environments. Self-localization is critical to any robot that must navigate or manipulate the environment. To solve this problem, a modular localization system suitable for mobile manipulators was developed. By using LIDAR data the proposed system is capable of achieving less than a centimeter in translation error and less than a degree in rotation error while requiring only 5 to 25 milliseconds of processing time. The system was tested in two different robot platforms at different velocities and in several cluttered and dynamic environments. It demonstrated high accuracy while performing pose tracking and high reliability when estimating the initial pose using feature matching. No artificial landmarks are required and it is able to adjust its operation rate in order to use very few hardware resources when a mobile robot is not moving.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 6