Learn from model beyond fine-tuning: A survey

H Zheng, L Shen, A Tang, Y Luo, H Hu, B Du… - arXiv preprint arXiv …, 2023 - arxiv.org
Foundation models (FM) have demonstrated remarkable performance across a wide range
of tasks (especially in the fields of natural language processing and computer vision) …

Data-driven methods applied to soft robot modeling and control: A review

Z Chen, F Renda, A Le Gall, L Mocellin… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Soft robots show compliance and have infinite degrees of freedom. Thanks to these
properties, such robots can be leveraged for surgery, rehabilitation, biomimetics …

Optimized Design of a Soft Actuator Considering Force/Torque, Bendability, and Controllability via an Approximated Structure

WT Yang, B Kurkcu… - Journal of …, 2024 - asmedigitalcollection.asme.org
This paper introduces a novel design method that enhances the force/torque, bendability,
and controllability of soft pneumatic actuators (SPAs). The complex structure of the soft …

Nonlinear Parameter-Varying Modeling for Soft Pneumatic Actuators and Data-Driven Parameter Estimation

WT Yang, H Stuart, B Kurkcu, M Tomizuka - arXiv preprint arXiv …, 2023 - arxiv.org
Accurately modeling soft robots remains a challenge due to their inherent nonlinear
behavior and parameter variations. This paper presents a novel approach to modeling soft …

Data-driven Explainable Controller for Soft Robots based on Recurrent Neural Networks

Z Chen, X Ren, G Ciuti, C Stefanini - arXiv preprint arXiv:2406.04094, 2024 - arxiv.org
The nonlinearity and hysteresis of soft robot motions have posed challenges in accurate soft
robot control. Neural networks, especially recurrent neural networks (RNNs), have been …

Torque-Bounded Admittance Control With Implicit Euler Realization of Set-Valued Operators

X Yuan, Y Ding, X Xiong, Y Lou - IEEE/ASME Transactions on …, 2023 - ieeexplore.ieee.org
When a robot collides with environments of unknown stiffness, the resultant torque
saturation can cause the conventional admittance control to exhibit unsafe behaviors such …

[PDF][PDF] Optimized Residual Action for Interaction Control with Learned Environments

V Petrone, L Puricelli, E Ferrentino, A Pozzi… - Authorea …, 2024 - techrxiv.org
In industrial settings, robotic tasks often require interaction with various objects,
necessitating compliant manipulation to prevent damage while accurately tracking reference …