Owaki Dai, Austin Max, Ikeda Shuhei, Okuizumi Kazuya, Nakajima Kohei
Department of Robotics, Graduate School of Engineering, Tohoku University, Sendai, Japan.
Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan.
Nat Commun. 2025 May 23;16(1):4642. doi: 10.1038/s41467-025-59889-7.
Jellyfish cyborgs present a promising avenue for soft robotic systems, leveraging the natural energy-efficiency and adaptability of biological systems. Here we present an approach for predicting and controlling jellyfish locomotion by harnessing the natural embodied intelligence of these animals. We developed an integrated muscle electrostimulation and 3D motion capture system to quantify both spontaneous and stimulus-induced behaviors in Aurelia coerulea jellyfish. Our key findings include an investigation of self-organized criticality in jellyfish swimming motions and the identification of optimal periods of electro-stimulus input signal (1.5 and 2.0 seconds) for eliciting coherent and predictable swimming behaviors. Furthermore, using Reservoir Computing, a machine learning framework, we successfully predicted future movements of the stimulated jellyfish, which also characterizes how the jellyfish swimming motions are synchronized with the electro-stimulus. Our findings provide a foundation for developing jellyfish cyborgs capable of autonomous navigation and environmental exploration, with potential applications in ocean monitoring and pollution management.
水母半机械人是软机器人系统的一个有前途的发展方向，它利用了生物系统的自然能量效率和适应性。在此，我们提出一种通过利用这些动物的自然具身智能来预测和控制水母运动的方法。我们开发了一个集成的肌肉电刺激和3D运动捕捉系统，以量化海月水母的自发行为和刺激诱导行为。我们的主要发现包括对水母游泳运动中的自组织临界性的研究，以及确定用于引发连贯且可预测游泳行为的电刺激输入信号的最佳时长（1.5秒和2.0秒）。此外，我们使用机器学习框架——储层计算，成功预测了受刺激水母的未来运动，这也刻画了水母游泳运动与电刺激的同步方式。我们的研究结果为开发能够自主导航和环境探索的水母半机械人奠定了基础，在海洋监测和污染管理方面具有潜在应用价值。
