Fleet-To-Lab：一种基于模型融合的月球车滑移估计迁移学习框架
Fleet-To-Lab: A Transfer Learning Framework For Lunar Rover Slippage Estimation Via Model Fusion
- University of Luxembourg（卢森堡大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对月球车滑移估计中地月数据域差异问题，提出Fleet-to-Lab迁移学习框架，通过AcoMerge混合群体智能算法融合异构专家模型，在高保真模拟中提升平衡准确率与宏F1，为数据稀缺场景提供有效方案。
AI中文摘要：
准确的车轮滑移估计对于月球车的自主移动和导航至关重要。在地球数据上训练的机器学习模型在月球地形上泛化能力较差，而由于任务数量有限且数据采集成本高昂，真实的月球数据集十分稀缺。我们提出了Fleet-to-Lab，一种迁移学习框架，利用先前部署的异构月球车收集的本体感觉数据来缩小未来可部署单元在滑移估计中的地月域差距。我们将多个异构专家模型融合到一个单一架构中，使用月球车部署后收集的中等规模数据集。我们提出了AcoMerge，一种新的混合群体智能算法，通过搜索专家参数的最优组合来执行模型融合。在高保真物理模拟中进行的实验表明，与深度模型融合基线相比，平衡准确率和宏F1分数均有所提升。AcoMerge在深度架构上与联合训练表现相当，同时在更小的模型上实现了更高的宏F1和平衡准确率。总体而言，我们的框架展示了模型融合作为在数据有限的空间机器人任务中滑移估计的一种可能的迁移学习替代方案。
英文摘要：
Accurate wheel slip estimation is essential for autonomous lunar rover mobility and navigation. Machine Learning models trained on terrestrial data generalize poorly to lunar terrain, and real lunar datasets are scarce due to the limited number of missions and costly data acquisition. We present Fleet-to-Lab, a transfer learning framework that leverages proprioceptive data collected by previously deployed heterogeneous lunar rovers to mitigate the Earth-Moon domain gap in slip estimation for a future deployable unit. We fuse several heterogeneous expert models into a single architecture, using a modest dataset collected after the rover deployment. We propose AcoMerge, a new hybrid swarm-intelligence algorithm that performs model fusion by searching for an optimal combi- nation of expert parameters. Experiments conducted in a high- fidelity physics simulation show balanced accuracy and macro- F1 improvements compared to deep model fusion baselines. AcoMerge exhibits competitive performance with joint training on deep architectures, while achieving higher macro-F1 and balanced accuracy on a smaller model. Overall, our framework shows model fusion as a possible transfer learning alternative for slippage estimation in space robotic missions with limited data.
