{"ID":5935791,"CreatedAt":"2026-07-07T01:22:02.77346169Z","UpdatedAt":"2026-07-07T02:10:06.972658124Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.03204","arxiv_id":"2607.03204","title":"Layout-independent actuation allocator for fin-actuated marine robots","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. 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.","short_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 Mixt...","url_abs":"https://arxiv.org/abs/2607.03204","url_pdf":"https://arxiv.org/pdf/2607.03204v1","authors":"[\"Yuya Hamamatsu\",\"Maarja Kruusmaa\",\"Asko Ristolainen\"]","published":"2026-07-03T11:18:58Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Graph Neural Network\",\"Transformer\"]","has_code":false}