®®®® SIIA Público

Título del libro: Proceedings - 2021 International Conference On Mechatronics, Electronics And Automotive Engineering, Icmeae 2021
Título del capítulo: Optical Flow-Hermite and Fuzzy Q-Learning Based Robotic Navigation Approach

Autores UNAM:
ERNESTO MOYA ALBOR;
Autores externos:

Idioma:

Año de publicación:
2021
Palabras clave:

Air navigation; Biomimetics; MATLAB; Reinforcement; Reinforcement learning; Robots; Visual servoing; Autonomous robotics; Fuzzy-Q-learning; Hermite; Hermite transforms; Reinforcement signal; Robotic navigation; Unknown environments; V-REP; Vision based control; Vision-based control navigation; Optical flows


Resumen:

The present paper presents a bio-inspired optical flow approach to autonomous robotics navigation. It uses a Fuzzy Q-Learning (FQL) method to take decisions in an unknown environment through a reinforcement signal. The proposed method was implemented in a virtual robotics system using the V-REP software and in communication con MATLAB. The preliminary results show that the robot was able to navigate successfully in unknown environments. © 2021 IEEE.


Entidades citadas de la UNAM: