Towards Automatic Design of Soft Pneumatic Actuators: Inner Structure Design Using CNN Model and Bézier Curve-Based Genetic Algorithm

In this paper, the development of a method for the design of soft pneumatic actuators is described. The focus is given on the interest of using a deep learning model to explore the design space with a genetic algorithm. In particular, we propose to perform the automatic synthesis of the inner struct...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE robotics and automation letters Ročník 8; číslo 10; s. 1 - 8
Hlavní autoři: Mosser, Loic, Barbe, Laurent, Rubbert, Lennart, Renaud, Pierre
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.10.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Accuracy
Actuators
Computational modeling
Computer Science
Convolutional neural networks
Curves
Deep learning
Deep Learning Approach for Soft Robot Design
Design methodology
Genetic algorithms
Hydraulic/Pneumatic Actuators
Machine learning
Mathematical models
Pneumatics
Robotics
Shape
Soft Robot Materials and Design
Soft robotics
Soft Sensors and Actuators
Synthesis
Topology
ISSN:2377-3766, 2377-3766
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this paper, the development of a method for the design of soft pneumatic actuators is described. The focus is given on the interest of using a deep learning model to explore the design space with a genetic algorithm. In particular, we propose to perform the automatic synthesis of the inner structure of pneumatic actuators using Bézier curves and Gaussian Mixture Points, to have a simple representation of the actuator genotype. This makes it possible to represent a wide variety of structures and to take into account the presence of the actuator pneumatic supply. It is shown a CNN model can interestingly be used in conjunction with FEM. FEM is being used to train initially the CNN model and for the control of accuracy, while the CNN model reduces the computational cost, offering a sufficient accuracy during the synthesis thanks to transfer learning. Through two case studies, the capacity of generating geometrically complex designs such as a double-helix network for a twisting actuator is outlined. Its possible extension and further use are also discussed.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2023.3309135