arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.01398cs.RO
收藏

通过物理知识蒸馏学习具有未知扰动的引力动力学深度网络:初步可行性研究

Learning Deep Nets for Gravitational Dynamics with Unknown Disturbance through Physical Knowledge Distillation: Initial Feasibility Study

The Chinese University of Hong Kong(香港中文大学);Shenzhen Institute of Artificial Intelligence and Robotics for Society(深圳市人工智能与机器人研究院);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Johns Hopkins University(约翰斯·霍普金斯大学)

Hongbin Lin, Qian Gao, Xiangyu Chu, Qi Dou, Anton Deguet, Peter Kazanzides, K. W. Samuel Au

摘要:

由于采样的复杂性,学习高性能深度神经网络用于高自由度(DOF)机器人的动态建模仍然具有挑战性。由未建模动态(如内部柔度、电缆)引起的典型未知系统扰动进一步加剧了该问题。本文提出了一种新的框架,其特点是高数据效率和干扰自适应能力,以解决问题的前馈重力补偿控制的高自由度主机械手的重力动力学建模使用深度网络未知干扰。特别地,前馈深度神经网络(FDNN)通过知识蒸馏(KD)从现有分析模型的先验知识和机器人系统的观察两者中学习。通过大量的实验,在高自由度的主机械手与显着的干扰,我们表明,我们的方法超越了标准的从头学习(LFS)的方法在数据效率和干扰适应。我们最初的可行性研究已经证明,随着训练数据的增加,分析型教师模型的性能有可能超过分析型教师模型。

英文摘要:

Learning high-performance deep neural networks for dynamic modeling of high Degree-Of-Freedom (DOF) robots remains challenging due to the sampling complexity. Typical unknown system disturbance caused by unmodeled dynamics (such as internal compliance, cables) further exacerbates the problem. In this paper, a novel framework characterized by both high data efficiency and disturbance-adapting capability is proposed to address the problem of modeling gravitational dynamics using deep nets in feedforward gravity compensation control for high-DOF master manipulators with unknown disturbance. In particular, Feedforward Deep Neural Networks (FDNNs) are learned from both prior knowledge of an existing analytical model and observation of the robot system by Knowledge Distillation (KD). Through extensive experiments in high-DOF master manipulators with significant disturbance, we show that our method surpasses a standard Learning-from-Scratch (LfS) approach in terms of data efficiency and disturbance adaptation. Our initial feasibility study has demonstrated the potential of outperforming the analytical teacher model as the training data increases.

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。

↑