# Embedding bifurcations into pneumatic artificial muscle

arXiv: https://arxiv.org/abs/2305.03994 · HTML: https://mlsanity.com/paper/2305.03994/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2023.

## Built on by (most cited first, 7 of 7)

- [Designing Chaotic Attractors: A Semi-supervised Approach](https://mlsanity.com/paper/2407.09545/) (2024)
- [Multifunctional physical reservoir computing in soft tensegrity robots](https://mlsanity.com/paper/2507.21496/) (2025)
- [Thermodynamic limit in learning period three](https://mlsanity.com/paper/2405.08825/) (2024)
- [Incorporating Coupling Knowledge into Echo State Networks for Learning Spatiotemporally Chaotic Dynamics](https://mlsanity.com/paper/2504.01532/) (2025)
- [Control Pneumatic Soft Bending Actuator with Online Learning Pneumatic Physical Reservoir Computing](https://mlsanity.com/paper/2503.15819/) (2025)
- [Attractor-merging Crises and Intermittency in Reservoir Computing](https://mlsanity.com/paper/2504.12695/) (2025)
- [Recycling computational processes of dynamic programming for combinatorial optimization problems: a reservoir computing approach](https://mlsanity.com/paper/2607.23009/) (2026)

## Abstract (arXiv)

Harnessing complex body dynamics has been a long-standing challenge in robotics. Soft body dynamics is a typical example of high complexity in interacting with the environment. An increasing number of studies have reported that these dynamics can be used as a computational resource. This includes the McKibben pneumatic artificial muscle, which is a typical soft actuator. This study demonstrated that various dynamics, including periodic and chaotic dynamics, could be embedded into the pneumatic artificial muscle, with the entire bifurcation structure using the framework of physical reservoir computing. These results suggest that dynamics that are not presented in training data could be embedded by using this capability of bifurcation embeddment. This implies that it is possible to embed various qualitatively different patterns into pneumatic artificial muscle by learning specific patterns, without the need to design and learn all patterns required for the purpose. Thus, this study sheds new light on a novel pathway to simplify the robotic devices and training of the control by reducing the external pattern generators and the amount and types of training data for the control.