Reinforcement Learning in Navigation and Cooperative Mapping

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2020

Autores

José Aleixo Cruz (Autor) Outra; Henrique Lopes Cardoso (Autor) FEUP; Luís Paulo Reis (Autor) FEUP; Armando Jorge Sousa (Autor) FEUP

Ata de Conferência Internacional

Título: 2020 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2020, Ponta Delgada, Portugal, April 15-17, 2020

Páginas: 200-205

2020 IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2020

15 April 2020 through 16 April 2020

Indexação

ISI Web of Knowledge - 1 Citação

ISI Web of Science

Scopus - 1 Citação

INSPEC

Outras Informações

ID Authenticus: P-00S-6PC

DOI: 10.1109/icarsc49921.2020.9096136

Abstract (EN): Reinforcement learning is becoming a more relevant area of research, as it allows robotic agents to learn complex tasks with evaluative feedback. One of the most critical challenges in robotics is the simultaneous localization and mapping problem. We have built a reinforcement learning environment where we trained an agent to control a team of two robots, with the task of cooperatively mapping a common area. Our training process takes the robots' sensors data as input and outputs the control action for each robot. We verified that our agent performed well in a small test environment, with little training, indicating that our approach could be a good starting point for end-to-end reinforcement learning for cooperative mapping. © 2020 IEEE.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 6