[论文解读] Simple Models, Real Swimming: Digital Twins for Tendon-Driven Underwater Robots

Mike Y. Michelis, Nana Obayashi+2 more|arXiv (Cornell University)|Feb 26, 2026

Biomimetic flight and propulsion mechanisms被引用 0

一句话总结

论文在 MuJoCo 中开发了一种快速、无状态的流体模型，用于创建 tendon-driven 水下鱼机器人数字孪生，从而实现仿真到真实环境的匹配和基于强化学习的控制。

ABSTRACT

Mimicking the graceful motion of swimming animals remains a core challenge in soft robotics due to the complexity of fluid-structure interaction and the difficulty of controlling soft, biomimetic bodies. Existing modeling approaches are often computationally expensive and impractical for complex control or reinforcement learning needed for realistic motions to emerge in robotic systems. In this work, we present a tendon-driven fish robot modeled in an efficient underwater swimmer environment using a simplified, stateless hydrodynamics formulation implemented in the widespread robotics framework MuJoCo. With just two real-world swimming trajectories, we identify five fluid parameters that allow a matching to experimental behavior and generalize across a range of actuation frequencies. We show that this stateless fluid model can generalize to unseen actuation and outperform classical analytical models such as the elongated body theory. This simulation environment runs faster than real-time and can easily enable downstream learning algorithms such as reinforcement learning for target tracking, reaching a 93% success rate. Due to the simplicity and ease of use of the model and our open-source simulation environment, our results show that even simple, stateless models -- when carefully matched to physical data -- can serve as effective digital twins for soft underwater robots, opening up new directions for scalable learning and control in aquatic environments.

研究动机与目标

• 激发实现真实软性水下机器人游动的挑战性及对高效模型的需求。
• 提出一个简单、无状态的流体动力学模型，并以真实数据进行标定作为数字孪生。
• 以最小的实验轨迹实现仿真到真实的匹配。
• 展示下游强化学习任务，如使用数字孪生进行目标跟踪。

提出的方法

• 将关节化的刚体尾部离散为五段脊柱，由刚性肌腱驱动。
• 采用五参数无状态流体模型，包括钝直/纤细阻力、角阻、Kutta升力和Magnus升力。
• 用两条真实轨迹进行参数标定，并结合贝叶斯优化与 Nelder-Mead refinemen​t。
• 将其与 Lighthill 的 Elongated Body Theory 作为基线进行对比。
• 与 MuJoCo 集成，使其实现实时速度运行并支持 RL 流水线。

Figure 1 : Overview of the simulated and real swimmer robots. A) Robot swimming in the pool captured from a top-down view, images overlaid are $3\text{\,}\mathrm{s}$ apart. B) The 11 markers are tracked and extracted from the video. C) Side-view of the hardware with a single motor actuating the tend

实验结果

研究问题

• RQ1 一个从最小真实数据标定的简单无状态流体模型，能否推广至未见的驱动频率？
• RQ2 无状态模型在水下 tendon-driven 游动体的仿真到真实准确性方面，与传统解析模型相比如何？
• RQ3 数字孪生是否能够实现水中有效的基于 RL 的控制任务，如目标跟踪？

主要发现

• 五参数无状态流体模型在用两条轨迹标定后，能在一系列驱动频率下泛化。
• 该模型在 MuJoCo 中以实时的 15x 速度运行，并且在该机器人上优于 Elongated Body Theory 基线。
• 仿真到真实的匹配在不同条件下平均标记位置误差低至 0.016–0.029 m。
• 通过 Soft Actor-Critic 的 RL 在评估环境中实现目标跟踪的成功率达到 93%。
• 数字孪生支持实时的仿真到真实学习以及可扩展的多机器人仿真。

Figure 2 : Overview of the main mechanisms for the swimmer simulation environment. We simplify the deformable spine with multiple hinge joints as an articulated rigid body, we use stiff elastic tendons for the tendon-driven actuation, a velocity-controlled motor that pulls the tendons, and a simplif