Publications

Publications by Luís Paulo Reis

2020

Robot 2019: Fourth Iberian Robotics Conference

Authors
Silva, MF; Luís Lima, J; Reis, LP; Sanfeliu, A; Tardioli, D;

Publication
Advances in Intelligent Systems and Computing

Abstract

2020

Robot 2019: Fourth Iberian Robotics Conference - Advances in Robotics, Volume 1, Porto, Portugal, 20-22 November, 2019

Authors
Silva, MF; Lima, JL; Reis, LP; Sanfeliu, A; Tardioli, D;

Publication
ROBOT (1)

Abstract

2020

Correction to: Robot 2019: Fourth Iberian Robotics Conference

Authors
Silva, MF; Luís Lima, J; Reis, LP; Sanfeliu, A; Tardioli, D;

Publication
Advances in Intelligent Systems and Computing

Abstract
The original version of the book was inadvertently published with incomplete information in the Organization page of the front matter, which has now been included. The book has been updated with the change. © 2020, Springer Nature Switzerland AG.

CloseRead Abstract

2020

Robot 2019: Fourth Iberian Robotics Conference - Advances in Robotics, Volume 2, Porto, Portugal, 20-22 November, 2019

Authors
Silva, MF; Lima, JL; Reis, LP; Sanfeliu, A; Tardioli, D;

Publication
ROBOT (2)

Abstract

2014

Consolidação e fortalecimento dos estudos qualitativos nas diversas vertentes da área de saúde.

Authors
Souza, DNd; Costa, AP; Souza, FNd; Reis, LP;

Publication
Revista da Escola de Enfermagem da USP

Abstract

2020

Reinforcement Learning in Navigation and Cooperative Mapping

Authors
Cruz, JA; Cardoso, HL; Reis, LP; Sousa, A;

Publication
2020 IEEE INTERNATIONAL CONFERENCE ON AUTONOMOUS ROBOT SYSTEMS AND COMPETITIONS (ICARSC 2020)

Abstract
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.

CloseRead Abstract