Embedding Bifurcations into Pneumatic Artificial Muscle
Source abstract
Abstract
Abstract Harnessing complex body dynamics has long been a challenge in robotics, particularly when dealing with soft dynamics, which exhibit high complexity in interacting with the environment. Recent studies indicate that these dynamics can be used as a computational resource, exemplified by the McKibben pneumatic artificial muscle, a common soft actuator. This study demonstrates that bifurcations, including periodic and chaotic dynamics, can be embedded into the pneumatic artificial muscle, with the entire bifurcation structure using the framework of physical reservoir computing. These results suggest that dynamics not present in training data can be embedded through bifurcation embedment, implying the capability to incorporate various qualitatively different patterns into pneumatic artificial muscle without the need to design and learn all required patterns explicitly. Thus, this study introduces a novel approach to simplify robotic devices and control training by reducing reliance on external pattern generators and the amount and types of training data needed for control.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Neural Networks and Reservoir Computing · Model Reduction and Neural Networks · Neural Networks and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Graduation School of Informatics Kyoto University Yoshida‐honmachi Sakyo‐ku Kyoto 606‐8501 Japan
Graduate School of Information Science and Technology The University of Tokyo 7‐3‐1 Hongo Bunkyo‐ku Tokyo 113‐8654 Japan
GX Innovation Technology Development Bridgestone Corporation 3‐1‐1 Kyobashi Chuo‐ku Tokyo 104‐8340 Japan
Funding
Japan Society for the Promotion of Science · Core Research for Evolutional Science and Technology
References (69)
Show source-provided references
1. 10.1177/02783649900090020610.1177/027836499000900206 ↗
2. 10.1088/1367-2630/ac45ca10.1088/1367-2630/ac45ca ↗
3. 10.1371/journal.pone.008669610.1371/journal.pone.0086696 ↗
4. 10.1126/scirobotics.abq727810.1126/scirobotics.abq7278 ↗
5. 10.1109/ICRA.2013.663077010.1109/ICRA.2013.6630770 ↗
6. 10.3389/fncom.2013.0009110.3389/fncom.2013.00091 ↗
7. 10.1038/srep1048710.1038/srep10487 ↗
8. 10.1089/soro.2017.007510.1089/soro.2017.0075 ↗
9. 10.1016/B978-0-08-102260-3.00008-110.1016/B978-0-08-102260-3.00008-1 ↗
10. 10.1162/08997660276040795510.1162/089976602760407955 ↗
11. 10.1126/science.109127710.1126/science.1091277 ↗
12. 10.1007/978-981-13-1687-610.1007/978-981-13-1687-6 ↗
13. 10.35848/1347-4065/ab8d4f10.35848/1347-4065/ab8d4f ↗
14. 10.1007/s00422-012-0471-010.1007/s00422-012-0471-0 ↗
15. 10.1162/ARTL_a_0008010.1162/ARTL_a_00080 ↗
16. 10.1109/LRA.2021.313908310.1109/LRA.2021.3139083 ↗
17. Q.Zhao K.Nakajima H.Sumioka H.Hauser R.Pfeifer presented at2013 IEEE/RSJ International Conference on Intelligent Robots and Systems Tokyo Japan November2013.
18. Y.Horii K.Inoue S.Nishikawa K.Nakajima R.Niiyama Y.Kuniyoshi ALIFE 2021: The 2021 Conference on Artificial Life MIT Press Cambridge MA2021.10.1299/jsmermd.2021.2P2-G16 ↗
19. Schulte H. · 1961 · 94
20. 10.1007/BF0247467210.1007/BF02474672 ↗
21. Daerden F. · Eur. J. Mech. Environ. Eng. · 2002 · 47 · 11
22. 10.1080/1176232080255786510.1080/11762320802557865 ↗
23. 10.1109/ICORR.2015.728126010.1109/ICORR.2015.7281260 ↗
24. 10.1115/1.294330010.1115/1.2943300 ↗
25. 10.20965/jrm.2022.p024010.20965/jrm.2022.p0240 ↗
26. 10.1109/ICRA46639.2022.981237710.1109/ICRA46639.2022.9812377 ↗
27. 10.1080/01691864.2017.140270310.1080/01691864.2017.1402703 ↗
28. 10.1109/ICRA48891.2023.1016131510.1109/ICRA48891.2023.10161315 ↗
29. 10.1007/s10514-009-9176-110.1007/s10514-009-9176-1 ↗
30. 10.1038/nphys150810.1038/nphys1508 ↗
31. 10.5772/6279610.5772/62796 ↗
32. 10.1016/S0167-2789(05)80014-410.1016/S0167-2789(05)80014-4 ↗
33. 10.1587/nolta.8.210.1587/nolta.8.2 ↗
34. 10.1063/1.511918710.1063/1.5119187 ↗
35. 10.1038/s42256-021-00321-210.1038/s42256-021-00321-2 ↗
36. 10.1007/s10884-022-10159-w10.1007/s10884-022-10159-w ↗
37. 10.1109/RoboSoft48309.2020.911597410.1109/RoboSoft48309.2020.9115974 ↗
38. 10.1002/polb.1057110.1002/polb.10571 ↗
39. 10.1137/SIREAD00004000000300073200000110.1137/SIREAD000040000003000732000001 ↗
40. 10.1038/ncomms147610.1038/ncomms1476 ↗
41. 10.1103/PhysRevApplied.8.02403010.1103/PhysRevApplied.8.024030 ↗
42. 10.1038/nature2301110.1038/nature23011 ↗
43. 10.1038/srep0051410.1038/srep00514 ↗
44. 10.1103/PhysRevResearch.3.04313510.1103/PhysRevResearch.3.043135 ↗
45. Jaeger H. · 2001 · 5
46. Jaeger H. · Bonn, Germany: German National Research Center for Information Technology GMD Technical Report · 2001 · 148 · 13
47. 10.1016/j.conengprac.2012.01.00210.1016/j.conengprac.2012.01.002 ↗
48. 10.1109/JAS.2020.100335110.1109/JAS.2020.1003351 ↗
49. Sun W. · 2021 · 1
50. 10.1109/RoboSoft54090.2022.976218110.1109/RoboSoft54090.2022.9762181 ↗
51. 10.1109/LRA.2022.317849610.1109/LRA.2022.3178496 ↗
52. 10.1162/neco.1997.9.8.173510.1162/neco.1997.9.8.1735 ↗
53. 10.1016/j.neunet.2008.03.01410.1016/j.neunet.2008.03.014 ↗
54. 10.1103/PhysRevApplied.11.03402110.1103/PhysRevApplied.11.034021 ↗
55. 10.1016/0375-9601(76)90101-810.1016/0375-9601(76)90101-8 ↗
56. 10.1007/s00422-012-0516-410.1007/s00422-012-0516-4 ↗
57. 10.1007/978-0-387-21830-4_610.1007/978-0-387-21830-4_6 ↗
58. 10.1126/sciadv.abb398910.1126/sciadv.abb3989 ↗
59. 10.1364/OE.20.00324110.1364/OE.20.003241 ↗
60. 10.1002/aisy.20220012310.1002/aisy.202200123 ↗
61. 10.1088/1367-2630/ac024d10.1088/1367-2630/ac024d ↗
62. 10.1098/rsos.22161410.1098/rsos.221614 ↗
63. 10.1038/s41928-023-01069-w10.1038/s41928-023-01069-w ↗
64. D. P.Kingma J.Ba arXiv 2017.
65. 10.1109/70.48175310.1109/70.481753 ↗
66. 10.1177/1045389X1143543510.1177/1045389X11435435 ↗
67. 10.1109/TIE.2009.202465710.1109/TIE.2009.2024657 ↗
68. 10.1038/s41467-019-13993-710.1038/s41467-019-13993-7 ↗
69. 10.1089/soro.2020.002410.1089/soro.2020.0024 ↗