Physics-informed recurrent neural networks for soft pneumatic actuators
Replacing sensors with indirect sensing techniques contributes to retaining the flexibility of
soft robots. By combining physical models with recurrent neural networks (which we term a …
soft robots. By combining physical models with recurrent neural networks (which we term a …
Durable pneumatic artificial muscles with electric conductivity for reliable physical reservoir computing
R Sakurai, M Nishida, T Jo, Y Wakao… - Journal of Robotics and …, 2022 - jstage.jst.go.jp
A McKibben-type pneumatic artificial muscle (PAM) is a soft actuator that is widely used in
soft robotics, and it generally exhibits complex material dynamics with nonlinearity and …
soft robotics, and it generally exhibits complex material dynamics with nonlinearity and …
Embedding bifurcations into pneumatic artificial muscle
Harnessing complex body dynamics has long been a challenge in robotics, particularly
when dealing with soft dynamics, which exhibit high complexity in interacting with the …
when dealing with soft dynamics, which exhibit high complexity in interacting with the …
Self-organization of physics-informed mechanisms in recurrent neural networks: A case study in pneumatic artificial muscles
Complex nonlinear dynamics limit the indirect sensing accuracy of the pneumatic artificial
muscle (PAM). We implemented an echo state network, which is a type of recurrent neural …
muscle (PAM). We implemented an echo state network, which is a type of recurrent neural …
PINN-Ray: A Physics-Informed Neural Network to Model Soft Robotic Fin Ray Fingers
Modelling complex deformation for soft robotics provides a guideline to understand their
behaviour, leading to safe interaction with the environment. However, building a surrogate …
behaviour, leading to safe interaction with the environment. However, building a surrogate …
Information Processing Using Soft Body Dynamics
In this chapter, we address how the introduction of softness into robots will enable
unprecedented information-processing functionalities. In Sect. 15.1, we show how softening …
unprecedented information-processing functionalities. In Sect. 15.1, we show how softening …
A Pneumatically Driven Arm Motion Teaching System Using Visual and Torque Feedback
Y Tomita, T Miyazaki, M Sogabe… - … on Robotics and …, 2023 - ieeexplore.ieee.org
Machine-human interaction systems have been proposed to improve motion learning
efficiency by providing feedback on motion misalignment between a learner and an …
efficiency by providing feedback on motion misalignment between a learner and an …
Pre-training on physical dynamics enhances indirect sensing in recurrent neural networks
M Nishida, R Sakurai, Y Wakao… - … Symposium on Micro …, 2022 - ieeexplore.ieee.org
A McKibben-type pneumatic artificial muscle (PAM), which can achieve a large contraction
force, is a promising candidate for the actuation of soft robots. Currently, to control PAMs …
force, is a promising candidate for the actuation of soft robots. Currently, to control PAMs …
ソフトロボット学での研究とその宿題
中嶋浩** - 日本ロボット学会誌, 2024 - jstage.jst.go.jp
やわらかい身体を持つロボットと硬いロボットは何が違うのか? 我々は, この問いに対して,
一貫してダイナミクスに着目して研究を進めてきた. やわらかいロボットの身体は …
一貫してダイナミクスに着目して研究を進めてきた. やわらかいロボットの身体は …
空気圧人工筋肉のスケール可能なデータ収集システムとモデル学習
池田悠也， 松嶋達也， 岩澤有祐， 新山龍馬… - … 学会全国大会論文集 第 …, 2023 - jstage.jst.go.jp
抄録 ゴムやエラストマーなどの柔らかい素材でできたロボットはソフトロボットと呼ばれ,
その物理的な柔らかさから, 従来のロボットの課題の一つである安全性を保証できるとして注目が …
その物理的な柔らかさから, 従来のロボットの課題の一つである安全性を保証できるとして注目が …