Outubro 2023 vol. 10 num. 5 - IX Simpósio Internacional de Inovação e Tecnologia

Full article - Open Access.

Idioma principal | Segundo idioma

CONTROL OF INDUSTRIAL MANIPULATORS THROUGH REINFORCEMENT LEARNING: A STUDY OF THE PANDA MANIPULATOR IN A SIMULATED ENVIRONMENT

CONTROL OF INDUSTRIAL MANIPULATORS THROUGH REINFORCEMENT LEARNING: A STUDY OF THE PANDA MANIPULATOR IN A SIMULATED ENVIRONMENT

FERREIRA, MARCELO ALBERGARIA PAULINO FERNANDES ; FRANKLIN, TANIEL SILVA ; PINHEIRO, OBERDAN ROCHA ;

Full article:

The wide variety of scenarios in industrial environments requires intelligent robotics capable of directly interacting with the environment for problem-solving. Through reinforcement learning, robots can quickly adapt to new situations and learn from direct interaction with the environment. This work proposes a simulation environment based on Robotics Toolbox for Python to solve a classic problem of the inverse kinematics of manipulators, ensuring that the robot reaches the desired position without colliding with the obstacles present in the scene. The potential of this reinforcement learning method is illustrated through simulation using the Franka-Emika Panda manipulator trained by the Deep Deterministic Policy Gradient algorithm.

Full article:

The wide variety of scenarios in industrial environments requires intelligent robotics capable of directly interacting with the environment for problem-solving. Through reinforcement learning, robots can quickly adapt to new situations and learn from direct interaction with the environment. This work proposes a simulation environment based on Robotics Toolbox for Python to solve a classic problem of the inverse kinematics of manipulators, ensuring that the robot reaches the desired position without colliding with the obstacles present in the scene. The potential of this reinforcement learning method is illustrated through simulation using the Franka-Emika Panda manipulator trained by the Deep Deterministic Policy Gradient algorithm.

Download (PDF)

Palavras-chave: deep reinforcement learning; robot; manipulator; machine learning; artificial intelligence,

Palavras-chave: deep reinforcement learning; robot; manipulator; machine learning; artificial intelligence,

DOI: 10.5151/siintec2023-306030

Referências bibliográficas
  • [1] "KROEMER, Oliver; NIEKUM, Scott; KONIDARIS, George. A review of robot learning
  • [2] for manipulation: Challenges, representations, and algorithms. The Journal of
  • [3] Machine Learning Research, 2021.
  • [4] Liu, R., Nageotte, F., Zanne, P., de Mathelin, M., Dresp-Langley, B., 2021. Deep
  • [5] reinforcement learning for the control of robotic manipulation: A focussed
  • [6] mini-review. Robotics 10, 22. doi:10.3390/robotics10010022.
  • [7] Data Science Academy. Deep Learning Book, 2022. Disponivel em: <
  • [8] https://www.deeplearningbook.com.br/?s=65 > Acesso em: 5 abril. 2023.
  • [9] P.Corke And J.Haviland. Not your grandmother’s toolbox- The Robotic’s Toolbox
  • [10] reinvented for Python. Proc. ICRA,2021.
  • [11] Timothy P. Lillicrap and Jonathan J. Hunt and Alexander Pritzel and Nicolas Heess
  • [12] and Tom Erez and Yuval Tassa and David Silver and Daan Wierstra. Continuous
  • [13] control with deep reinforcement learning. Machine Learning.
  • [14] https://doi.org/10.48550/arXiv.1509.02971
  • [15] Malik, A.; Lischuk, Y.; Henderson, T.; Prazenica, R. A Deep ReinforcementLearning Approach for Inverse Kinematics Solution of a High Degree of Freedom
  • [16] Robotic Manipulator. Robotics 2022, 11, 44.
  • [17] https://doi.org/10.3390/robotics11020044"
Como citar:

FERREIRA, MARCELO ALBERGARIA PAULINO FERNANDES ; FRANKLIN, TANIEL SILVA; PINHEIRO, OBERDAN ROCHA ; "CONTROL OF INDUSTRIAL MANIPULATORS THROUGH REINFORCEMENT LEARNING: A STUDY OF THE PANDA MANIPULATOR IN A SIMULATED ENVIRONMENT", p. 318-325 . In: . São Paulo: Blucher, 2023.
ISSN 2357-7592, DOI 10.5151/siintec2023-306030

últimos 30 dias | último ano | desde a publicação


downloads


visualizações


indexações