A Machine Learning Empowered Shape Memory Alloy Gripper With Displacement-Force-Stiffness Self-Sensing

Pei, Yong-Chen; Wang, Baohua; Wu, Ji-Tuo; Wang, Chenyang; Guan, Jing-Han; Pisani, Luigi

doi:10.1109/tie.2022.3222655

Cited by 8 publications

(2 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, for the SMA-actuated gripper presented in [78], ML models permitted one to successfully predict displacement and force through regression. Moreover, the stiffness of the grasped object was estimated through regression and classification.…”

Section: Machine Learning Techniquesmentioning

confidence: 99%

Control Methodologies for Robotic Grippers: A Review

Cortinovis,

Vitrani,

Maggiali

et al. 2023

Actuators

View full text Add to dashboard Cite

As automation is spreading in all the industry domains, the presence of robots is becoming unavoidable inside factories, warehouses and manufacturing facilities. Although a great number of companies and research institutions have concentrated their efforts on developing new robotic systems and advanced algorithms, much work is necessary to provide robotic grippers, especially industrial ones, with reliable, powerful control strategies. Therefore, this article aims at delivering an up-to-date point of view on the state of the art of robotic gripper control. The principal control methodologies employed so far, as well as a thorough selection of the existing contributions to the field, will be reported and discussed. Finally, the authors’ opinion about future directions will be expressed.

show abstract

Section: Machine Learning Techniquesmentioning

confidence: 99%

Control Methodologies for Robotic Grippers: A Review

Cortinovis,

Vitrani,

Maggiali

et al. 2023

Actuators

View full text Add to dashboard Cite

show abstract

“…Their ability to identify complex patterns and make accurate predictions has been employed in the field of sensors and actuators. [21,22] For accurate positioning of artificial muscles, we propose an ensemble encoder-style neural controller [23] that not only maps the desired displacement trajectory to the required power but also is capable of capturing the hysteresis.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning‐Enabled Precision Position Control and Thermal Regulation in Advanced Thermal Actuators

Mirvakili,

Haghighat,

Sim

2024

Adv Materials Technologies

View full text Add to dashboard Cite

With their unique combination of characteristics – an energy density almost 100 times that of human muscle, and a power density of 5.3 kW kg−1, similar to a jet engine's output – Nylon artificial muscles stand out as particularly apt for robotics applications. However, the necessity of integrating sensors and controllers poses a limitation to their practical usage. Here, a constant power open‐loop controller is reported based on machine learning. It shows that the position of a nylon artificial muscle without external sensors can be controlled. To this end, a mapping is constructed from a desired displacement trajectory to a required power using an ensemble encoder‐style feed‐forward neural network. The neural controller is carefully trained on a physics‐based denoised dataset and can be fine‐tuned to accommodate various types of thermal artificial muscles, irrespective of the presence or absence of hysteresis. This neural network effectively endows the artificial muscles with “muscle memory”, allowing them to replicate complex movements reliably.

show abstract