MTF-Grasp：一种用于机器人抓取的多层联邦学习方法
MTF-Grasp: A Multi-tier Federated Learning Approach for Robotic Grasping
AI总结：
针对机器人抓取中非独立同分布数据导致的性能下降问题，提出多层联邦学习方法MTF-Grasp，利用数据质量与数量选择顶层机器人训练初始模型并分发给底层，在Cornell和Jacquard数据集上性能提升达8%。
摘要：
联邦学习（FL）是一种极具前景的机器学习范式，能够使参与设备训练保护隐私且协作的模型。FL已证明其在机器人操作任务中的优势。然而，在机器人无需移动数据并确保数据隐私的设置下训练全局模型的场景中，抓取任务缺乏探索。主要挑战在于，每个机器人学习的数据是非独立同分布（non-IID）且数量较少的。这导致了性能下降，在机器人抓取中尤为明显。因此，在本研究中，我们提出了MTF-Grasp，一种用于机器人抓取的多层FL方法，该方法正视了跨机器人non-IID数据分布带来的独特挑战，包括数量偏斜。MTF-Grasp利用跨机器人的数据质量和数量，选择一组具有更好数据分布和更高样本数的“顶层”机器人。随后，它利用顶层机器人训练初始种子模型，并将其分发给其余的“底层”机器人，从而降低底层机器人模型性能下降的风险。在数量偏斜的Cornell和Jacquard抓取数据集上，我们的方法比传统FL设置高出8%。
英文摘要：
Federated Learning (FL) is a promising machine learning paradigm that enables participating devices to train privacy-preserved and collaborative models. FL has proven its benefits for robotic manipulation tasks. However, grasping tasks lack exploration in such settings where robots train a global model without moving data and ensuring data privacy. The main challenge is that each robot learns from data that is nonindependent and identically distributed (non-IID) and of low quantity. This exhibits performance degradation, particularly in robotic grasping. Thus, in this work, we propose MTF-Grasp, a multi-tier FL approach for robotic grasping, acknowledging the unique challenges posed by the non-IID data distribution across robots, including quantitative skewness. MTF-Grasp harnesses data quality and quantity across robots to select a set of "top-level" robots with better data distribution and higher sample count. It then utilizes top-level robots to train initial seed models and distribute them to the remaining "low-level" robots, reducing the risk of model performance degradation in low-level robots. Our approach outperforms the conventional FL setup by up to 8% on the quantity-skewed Cornell and Jacquard grasping datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
