6 papers
Reconstructing Backpropagation from Forward Fluctuations in Noise-modulated Neural Networks
Shuhei Ikemoto
A Noise-modulated Neural Network (NNN) learns and infers only in the presence of noise, treating noise as a computational resource rather than a disturbance. The noise lets it lear…
Multimodal Learning of Soft Robot Dynamics using Differentiable Filters
Xiao Liu, Yifan Zhou, Shuhei Ikemoto +1
Differentiable Filters, as recursive Bayesian estimators, possess the ability to learn complex dynamics by deriving state transition and measurement models exclusively from data. T…
Learning Soft Robot Dynamics using Differentiable Kalman Filters and Spatio-Temporal Embeddings
Xiao Liu, Shuhei Ikemoto, Yuhei Yoshimitsu +1
This paper introduces a novel approach for modeling the dynamics of soft robots, utilizing a differentiable filter architecture. The proposed approach enables end-to-end training t…
Goal-Conditioned Variational Autoencoder Trajectory Primitives with Continuous and Discrete Latent Codes
Takayuki Osa, Shuhei Ikemoto
Imitation learning is an intuitive approach for teaching motion to robotic systems. Although previous studies have proposed various methods to model demonstrated movement primitive…
Learning Interactive Behaviors for Musculoskeletal Robots Using Bayesian Interaction Primitives
Joseph Campbell, Arne Hitzmann, Simon Stepputtis +3
Musculoskeletal robots that are based on pneumatic actuation have a variety of properties, such as compliance and back-drivability, that render them particularly appealing for huma…
Local Online Motor Babbling: Learning Motor Abundance of A Musculoskeletal Robot Arm
Zinan Liu, Arne Hitzmann, Shuhei Ikemoto +3
Motor babbling and goal babbling has been used for sensorimotor learning of highly redundant systems in soft robotics. Recent works in goal babbling has demonstrated successful lea…