Efficient Transfer Learning of Robot Dynamic Models Using Morphological Similarity

Authors: Pavlo Kupyn, Yuya Hamamatsu, Roza Gkliva, Asko Ristolainen, Maarja Kruusmaa

Abstract: This study proposes a neural network-based transfer learning framework for modeling the dynamics of soft, fin-actuated underwater robots. We focus on morphologically similar robots that differ in scale and hydrodynamic properties. A model trained on data from a larger robot (source domain) is adapted to a smaller one (target domain) with limited labeled data. To enable label-efficient transfer, we… ▽ More This study proposes a neural network-based transfer learning framework for modeling the dynamics of soft, fin-actuated underwater robots. We focus on morphologically similar robots that differ in scale and hydrodynamic properties. A model trained on data from a larger robot (source domain) is adapted to a smaller one (target domain) with limited labeled data. To enable label-efficient transfer, we develop an autoencoder-based domain adaptation approach that learns a shared latent representation aligning the dynamics of both robots. Experiments on two real underwater robots show that the proposed method enables accurate state estimation of the body-frame velocities on a target platform without labeled data, highlighting its potential for efficient cross-robot dynamics transfer among morphologically similar platforms. △ Less

Submitted 6 July, 2026; originally announced July 2026.

Strouhal-Aware Model Predictive Control for Efficient Multi-Fin Flapping Locomotion

Authors: Yuya Hamamatsu, Zixi Chen, Maarja Kruusmaa, Asko Ristolainen

Abstract: Efficient flapping propulsion hinges on operating within a narrow Strouhal number window, a principle nature has converged upon for maximum thrust-to-power ratio. We translate this bioinspired empirical rule into real-time control, demonstrating it on an autonomous underwater vehicle driven by four soft fins. The proposed Strouhal-aware Model Predictive Control (MPC) enhances a quasi-steady hydrod… ▽ More Efficient flapping propulsion hinges on operating within a narrow Strouhal number window, a principle nature has converged upon for maximum thrust-to-power ratio. We translate this bioinspired empirical rule into real-time control, demonstrating it on an autonomous underwater vehicle driven by four soft fins. The proposed Strouhal-aware Model Predictive Control (MPC) enhances a quasi-steady hydrodynamic model with an explicit penalty for Strouhal deviation, solving the resulting nonconvex problem via a two-stage sampling and gradient optimization that runs onboard at 25 Hz. Pool and field trials show that the controller keeps each fin within the optimal Strouhal corridor (0.25-0.35) while precisely tracking commanded forces. This results in a mean reduction in mechanical power of 8.8\% to 32\% throughout the cruising range of 0.1 to 0.3 m/s. The proposed method also allows for a velocity of 0.4 m/s, which is unattainable for a baseline of the conventional inverse model. The results confirm that embedding first-principle flow physics into an MPC objective yields tangible endurance gains without sacrificing agility, offering a generic pathway to energy-aware locomotion in next-generation multifin robots. △ Less

Submitted 3 July, 2026; originally announced July 2026.

Layout-independent actuation allocator for fin-actuated marine robots

Authors: Yuya Hamamatsu, Maarja Kruusmaa, Asko Ristolainen

Abstract: In this study, we propose a layout-independent control allocator capable of zero-shot deployment across diverse actuator configurations. The proposed method utilizes a learning pipeline that integrates a Graph Neural Network (GNN) and a Transformer to represent the robot's geometric layout as a graph, along with a Mixture Density Network (MDN) to predict multi-modal control command distributions.… ▽ More In this study, we propose a layout-independent control allocator capable of zero-shot deployment across diverse actuator configurations. The proposed method utilizes a learning pipeline that integrates a Graph Neural Network (GNN) and a Transformer to represent the robot's geometric layout as a graph, along with a Mixture Density Network (MDN) to predict multi-modal control command distributions. Furthermore, by incorporating a differentiable physics surrogate model, we achieve command refinement during inference to minimize target wrench tracking error and energy consumption. A single generalized model using randomly generated actuator layout data demonstrated high trajectory tracking performance on different actuator layout robots outside the training distribution. Additionally, in real-world pool experiments, our approach achieved performance nearly equivalent to conventional controllers designed to specific layouts. △ Less

Submitted 3 July, 2026; originally announced July 2026.

Cross-platform Learning-based Fault Tolerant Surfacing Controller for Underwater Robots

Authors: Yuya Hamamatsu, Walid Remmas, Jaan Rebane, Maarja Kruusmaa, Asko Ristolainen

Abstract: In this paper, we propose a novel cross-platform fault-tolerant surfacing controller for underwater robots, based on reinforcement learning (RL). Unlike conventional approaches, which require explicit identification of malfunctioning actuators, our method allows the robot to surface using only the remaining operational actuators without needing to pinpoint the failures. The proposed controller lea… ▽ More In this paper, we propose a novel cross-platform fault-tolerant surfacing controller for underwater robots, based on reinforcement learning (RL). Unlike conventional approaches, which require explicit identification of malfunctioning actuators, our method allows the robot to surface using only the remaining operational actuators without needing to pinpoint the failures. The proposed controller learns a robust policy capable of handling diverse failure scenarios across different actuator configurations. Moreover, we introduce a transfer learning mechanism that shares a part of the control policy across various underwater robots with different actuators, thus improving learning efficiency and generalization across platforms. To validate our approach, we conduct simulations on three different types of underwater robots: a hovering-type AUV, a torpedo shaped AUV, and a turtle-shaped robot (U-CAT). Additionally, real-world experiments are performed, successfully transferring the learned policy from simulation to a physical U-CAT in a controlled environment. Our RL-based controller demonstrates superior performance in terms of stability and success rate compared to a baseline controller, achieving an 85.7 percent success rate in real-world tests compared to 57.1 percent with a baseline controller. This research provides a scalable and efficient solution for fault-tolerant control for diverse underwater platforms, with potential applications in real-world aquatic missions. △ Less

Submitted 10 February, 2025; originally announced February 2025.

Underwater Soft Fin Flapping Motion with Deep Neural Network Based Surrogate Model

Authors: Yuya Hamamatsu, Pavlo Kupyn, Roza Gkliva, Asko Ristolainen, Maarja Kruusmaa

Abstract: This study presents a novel framework for precise force control of fin-actuated underwater robots by integrating a deep neural network (DNN)-based surrogate model with reinforcement learning (RL). To address the complex interactions with the underwater environment and the high experimental costs, a DNN surrogate model acts as a simulator for enabling efficient training for the RL agent. Additional… ▽ More This study presents a novel framework for precise force control of fin-actuated underwater robots by integrating a deep neural network (DNN)-based surrogate model with reinforcement learning (RL). To address the complex interactions with the underwater environment and the high experimental costs, a DNN surrogate model acts as a simulator for enabling efficient training for the RL agent. Additionally, grid-switching control is applied to select optimized models for specific force reference ranges, improving control accuracy and stability. Experimental results show that the RL agent, trained in the surrogate simulation, generates complex thrust motions and achieves precise control of a real soft fin actuator. This approach provides an efficient control solution for fin-actuated robots in challenging underwater environments. △ Less

Submitted 5 February, 2025; originally announced February 2025.