arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1907.04490cs.LGcs.ROcs.SYeess.SYstat.ML
收藏

Deep Lagrangian Networks:使用物理学作为深度学习的模型先验

Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning

Technische Universität Darmstadt(达姆施塔特工业大学);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)

Michael Lutter, Christian Ritter, Jan Peters

摘要:

深度学习在许多任务中取得了惊人的结果,这些任务具有大量数据和在训练数据附近的泛化。对于许多重要的现实世界的应用程序,这些要求是不可行的,需要额外的先验知识的任务域来克服由此产生的问题。特别是,学习基于模型的控制的物理模型需要从较少的样本(通常是实时在线收集的)进行鲁棒外推,模型误差可能导致系统的严重损坏。直接结合物理洞察力使我们能够获得一种新的深度模型学习方法,该方法可以很好地外推,同时需要更少的样本。作为第一个例子,我们提出了深层拉格朗日网络(DeLaN)作为一个深层网络结构,拉格朗日力学已经被施加。DeLaN可以学习机械系统的运动方程(即,系统动力学)与深度网络有效地结合,同时确保物理兼容性。由此产生的DeLaN网络在机器人跟踪控制方面表现非常好。所提出的方法不仅在学习速度上优于以前的模型学习方法,而且对新轨迹的外推和实时在线学习具有显著改进和更鲁棒性

英文摘要:

Deep learning has achieved astonishing results on many tasks with large amounts of data and generalization within the proximity of training data. For many important real-world applications, these requirements are unfeasible and additional prior knowledge on the task domain is required to overcome the resulting problems. In particular, learning physics models for model-based control requires robust extrapolation from fewer samples - often collected online in real-time - and model errors may lead to drastic damages of the system. Directly incorporating physical insight has enabled us to obtain a novel deep model learning approach that extrapolates well while requiring fewer samples. As a first example, we propose Deep Lagrangian Networks (DeLaN) as a deep network structure upon which Lagrangian Mechanics have been imposed. DeLaN can learn the equations of motion of a mechanical system (i.e., system dynamics) with a deep network efficiently while ensuring physical plausibility. The resulting DeLaN network performs very well at robot tracking control. The proposed method did not only outperform previous model learning approaches at learning speed but exhibits substantially improved and more robust extrapolation to novel trajectories and learns online in real-time

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。

↑