Use this link to cite:
http://hdl.handle.net/2183/31407 Identificación de articulación blanda para brazo robótico mediante redes neuronales
Loading...
Identifiers
Publication date
Authors
Toribio, Andrea
Relaño, Carlos
Monje, C.A.
Martínez de la Casa, Santiago
Balaguer, Carlos
Advisors
Other responsabilities
Journal Title
Bibliographic citation
Toribio, A., Relaño, C., Monje, C. A., Martínez de la Casa, S., Balaguer, C. (2022) Identificación de articulación blanda para brazo robótico mediante redes neuronales. XLIII Jornadas de Automática: libro de actas, pp. 843-850. https://doi.org/10.17979/spudc.9788497498418.0843
Type of academic work
Academic degree
Abstract
[Resumen] La robótica blanda es una rama con gran potencial en el campo de la robótica actual. Presenta grandes ventajas frente a la antigua perspectiva rígida. Sin embargo, su desarrollo se ve limitado por la complejidad del modelado, identificación y control de estos sistemas, debido entre otros factores a su no linealidad. Es en este contexto, donde el uso de redes neuronales, capaces de adaptarse al comportamiento de sistemas muy variados independientemente del conocimiento disponible de los mismos, adquiere relevancia. En el presente trabajo se analiza la identificación de una articulación robótica blanda mediante redes neuronales, comparando los resultados frente a los obtenidos a través de la identificación mediante funciones de transferencia.
[Abstract] Soft robotics is a branch with great potential in the field of robotics today. It has great advantages over the old rigid perspective. However, its development is limited by the complexity of modelling, identification and control of these systems, due, among other factors, to their non-linearity. It is in this context that the use of neural networks, capable of adapting to a wide variety of systems, regardless of the knowledge available about them, is relevant. This paper analyses the identification of a soft robotic joint by means of neural networks, comparing the results with those obtained by means of transfer function identification.
[Abstract] Soft robotics is a branch with great potential in the field of robotics today. It has great advantages over the old rigid perspective. However, its development is limited by the complexity of modelling, identification and control of these systems, due, among other factors, to their non-linearity. It is in this context that the use of neural networks, capable of adapting to a wide variety of systems, regardless of the knowledge available about them, is relevant. This paper analyses the identification of a soft robotic joint by means of neural networks, comparing the results with those obtained by means of transfer function identification.
Description
Editor version
Rights
Atribución-NoComercial-CompartirIgual 4.0 Internacional (CC BY-NC-SA 4.0)
https://creativecommons.org/licenses/by-nc-sa/4.0/deed.es


