journal article·2024-05Open access

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

Seyed Mo Mirvakili, Ehsan Haghighat, Douglas Sim

Advanced Materials Technologies· Volume 9· Issue 9

Abstract

Abstract 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.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Advanced Sensor and Energy Harvesting Materials · Advanced Materials and Mechanics · Dielectric materials and actuators

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Massachusetts Institute of Technology Cambridge MA 02139 USA

Seron Electronics Vancouver BC Canada

References (24)

Show source-provided references
1. 10.1002/adma.20170440710.1002/adma.201704407 ↗
2. 10.1002/adma.20190409310.1002/adma.201904093 ↗
3. Haines C. S. · Appl. Phys. Sci. · 2016 · 113
4. 10.1002/admt.20220210110.1002/admt.202202101 ↗
5. 10.1126/science.124690610.1126/science.1246906 ↗
6. 10.1002/adma.20160473410.1002/adma.201604734 ↗
7. Haines C. S. · 2018 · 6980
8. Arakawa T. · 97982W
9. 10.1109/TRO.2017.266488510.1109/TRO.2017.2664885 ↗
10. Abbas A. · 2017 · 482
11. 10.1063/1.492331510.1063/1.4923315 ↗
12. 10.1038/nature1453910.1038/nature14539 ↗
13. Goodfellow I. · 2016
14. 10.1017/978100908951710.1017/9781009089517 ↗
15. 10.1016/j.cma.2016.02.00110.1016/j.cma.2016.02.001 ↗
16. 10.1016/j.cma.2021.11374110.1016/j.cma.2021.113741 ↗
17. 10.1115/1.405054210.1115/1.4050542 ↗
18. 10.1016/j.cma.2021.11395910.1016/j.cma.2021.113959 ↗
19. 10.1017/jfm.2016.80310.1017/jfm.2016.803 ↗
20. 10.1073/pnas.210178411810.1073/pnas.2101784118 ↗
21. 10.1109/TIE.2022.322265510.1109/TIE.2022.3222655 ↗
22. 10.3389/frobt.2022.88826110.3389/frobt.2022.888261 ↗
23. 10.1016/j.engappai.2022.10515110.1016/j.engappai.2022.105151 ↗
24. D. P.Kingma J. A.Ba Adam: A Method for Stochastic Optimization arxiv San Diego California USA 2014.