2026-05-20 バージニア工科大学（Virginia Tech）
A virtual rendering of soft robotics created by Noel Naughton’s team. Photo courtesy of Noel Naughton.
＜関連情報＞
- https://news.vt.edu/articles/2026/05/eng-me-naughton-pnas-reservoir-computing-soft-robotics.html
- https://www.pnas.org/doi/10.1073/pnas.2522094123
- https://www.pnas.org/doi/10.1073/pnas.2318769121
バイオハイブリッドソフトアームのニューラルリザーバー制御 Neural reservoir control of a bio-hybrid soft arm
Noel Naughton, Arman Tekinalp, Keshav Shivam, +3 , and Mattia Gazzola
Proceedings of the National Academy of Sciences Published:April 24, 2026
DOI:https://doi.org/10.1073/pnas.2522094123
Significance
Controlling soft robots is challenging due to their complex, nonlinear dynamics. We show that a bio-inspired reservoir computing approach enables the control of a simulated musculoskeletal bio-hybrid arm beyond traditional neural network performance. The use of neural reservoirs naturally accommodates the arm’s elastic dynamics and allows simultaneous muscle coordination and self-modeling. When implemented on neuromorphic hardware, this approach delivers significant computational energy savings, a key requirement for untethered small-scale robots.
Abstract
A long-standing engineering problem, the control of soft robots is difficult because of their highly nonlinear, heterogeneous, anisotropic, and distributed nature. Here, bridging engineering and biology, neural reservoirs are employed for the dynamic control of a bio-hybrid model arm made of multiple muscle-tendon groups enveloping an elastic spine. We show how the use of reservoirs facilitates simultaneous control and self-modeling across challenging tasks, outperforming classic neural network approaches. Further, through the use of spiking reservoirs on neuromorphic hardware, energy efficiency gains of up to 75 and 45 times are obtained relative to standard and high-efficiency CPUs, with implications for the on-board control of untethered, small-scale systems.
筋肉構造を持つソフトアームのトポロジー、ダイナミクス、および制御 Topology, dynamics, and control of a muscle-architected soft arm
Arman Tekinalp, Noel Naughton, Seung Hyun Kim, +4 , and Mattia Gazzola
Proceedings of the National Academy of Sciences Published:October 1, 2024
DOI:https://doi.org/10.1073/pnas.2318769121
Significance
Muscular hydrostats such as octopus arms or elephant trunks are exceedingly deft and nimble, thanks to their boneless nature and intricate architecture. How effective control over these complex structures is achieved, remains an open question. Here, we combine medical imaging, biomechanics, and live behavioral experiments into an octopus arm model made of nearly 200 muscle groups, to expose simplifying “mechanically intelligent” design and control principles. By relating topology to muscle dynamics, we show how anatomical connectivity and tissue compliance naturally produce complex arm reconfigurations out of simple yet robust actuation patterns. While derived for the octopus, distilled insights, topological analysis, and modeling approach are broadly significant, not only to other muscular hydrostats, but also to robotics, dynamics, and control.
Abstract
Muscular hydrostats, such as octopus arms or elephant trunks, lack bones entirely, endowing them with exceptional dexterity and reconfigurability. Key to their unmatched ability to control nearly infinite degrees of freedom is the architecture into which muscle fibers are weaved. Their arrangement is, effectively, the instantiation of a sophisticated mechanical program that mediates, and likely facilitates, the control and realization of complex, dynamic morphological reconfigurations. Here, by combining medical imaging, biomechanical data, live behavioral experiments, and numerical simulations, an octopus-inspired arm made of ∼200 continuous muscle groups is synthesized, exposing “mechanically intelligent” design and control principles broadly pertinent to dynamics and robotics. Such principles are mathematically understood in terms of storage, transport, and conversion of topological quantities, effected into complex 3D motions via simple muscle activation templates. These are in turn composed into higher-level control strategies that, compounded by the arm’s compliance, are demonstrated across challenging manipulation tasks, revealing surprising simplicity and robustness.
