一种可零样本部署的通用鳍式水下机器人控制分配方法
Layout-independent actuation allocator for fin-actuated marine robots
- 用图神经网络+Transformer建模机器人布局，实现跨配置适配
- 通过可微物理代理模型优化指令，降低误差与能耗
- 在真实水中实验中性能接近定制化控制器，适合多形态机器人
本研究提出一种布局无关的控制分配方法，可在多种推进器配置间实现零样本部署。该方法采用图神经网络（GNN）与Transformer联合建模机器人的几何布局，并利用混合密度网络（MDN）预测多模态控制指令分布。通过引入可微分物理代理模型，在推理阶段对控制指令进行优化，以最小化目标力矩跟踪误差和能量消耗。使用随机生成的推进器布局数据训练的单一通用模型，在训练分布外的不同布局机器人上均表现出优异轨迹跟踪性能。此外，在真实水池实验中，该方法性能几乎等同于针对特定布局设计的传统控制器。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。