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 13 publications

(3 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[25] shows the use of LSTM for position estimation purposes, [16] also makes use of LSTM for their physics-inspired neural network architecture, which is estimating actuator position. [26] also makes use of LSTM for SMA-based gripper displacement, force, and stiffness prediction.…”

Section: Related Workmentioning

confidence: 99%

A comparative analysis between deep neural network-based 1D-CNN and LSTM models to harness the self-sensing property of the shape memory alloy wire actuator for position estimation

Singh,

Bhargaw,

Jadhav

et al. 2024

Smart Mater. Struct.

View full text Add to dashboard Cite

The article presents a performance based comparative analysis of popular deep neu-ral network(DNN) models such as 1D-CNN and LSTM for Shape Memory alloy(SMA)-based wire actuator position estimation. These DNN models utilize the self-sensingproperty(SSP) for position prediction of the SMA actuator. The phase dependent elec-trical resistivity of SMA wire act as SSP, where the electrical resistivity is in the formof resistance acts as inputs to the proposed models for precise estimation of currentposition of the SMA actuator. For effective position control of the actuator, an ac-curate sensor feedback is required, utilizing SSP results in the elimination of externalposition sensor. This will improve the overall system in terms of more compactness andreduced interface complexity. Coming to DNN models, 1-D CNN has been meagerlyexplored in the current literature landscape for self-sensing prediction of SMA actua-tors, these 1-D CNN models are becoming quite popular for time series prediction forvarious applications and are emerging as an alternative to LSTM models. In this paper,a novel implementation of a 1D-CNN model for SMA actuator position estimation hasbeen done. A comparative analysis between 1D-CNN and LSTM has been done forprediction capability and inference speed based on performance measures such as MeanSquare Error(MSE), Mean Absolute Error(MAE), sMAPE(symmetric Mean AbsolutePercentage Error), data distribution and average inference speed. This comparisonshows that 1D-CNN has matching performance with the LSTM model with respect tothe prediction capability, however 1D-CNN offers faster inference speed. This analy-sis can be useful for choosing suitable DNN model for deployment in low computingplatform such as micro-controller for SMA actuator based real time applications wheretime latency is a critical parameter.

show abstract

Section: Related Workmentioning

confidence: 99%

A comparative analysis between deep neural network-based 1D-CNN and LSTM models to harness the self-sensing property of the shape memory alloy wire actuator for position estimation

Singh,

Bhargaw,

Jadhav

et al. 2024

Smart Mater. Struct.

View full text Add to dashboard Cite

show abstract

“…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

“…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

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

Cited by 13 publications

References 43 publications

A comparative analysis between deep neural network-based 1D-CNN and LSTM models to harness the self-sensing property of the shape memory alloy wire actuator for position estimation

A comparative analysis between deep neural network-based 1D-CNN and LSTM models to harness the self-sensing property of the shape memory alloy wire actuator for position estimation

Control Methodologies for Robotic Grippers: A Review

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

Contact Info

Product

Resources

About