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 2012.14313cs.LGcs.RO
收藏

如何训练可微分滤波器

How to Train Your Differentiable Filter

Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Stanford University(斯坦福大学)

Alina Kloss, Georg Martius, Jeannette Bohg

摘要:

在许多机器人应用中,保持对系统状态的信念是至关重要的,它作为规划和决策的输入,并在任务执行期间提供反馈。贝叶斯滤波算法解决了这个状态估计问题,但是它们需要过程动态和传感器观测的模型以及这些模型的相应噪声特性。最近,多项研究表明,这些模型可以通过递归过滤算法的可微版本进行端到端训练来学习。在这项工作中,我们研究了可微滤波器(DF)在非结构化学习方法和手动调整的滤波算法上的优势,并为有兴趣应用这种可微滤波器的研究人员提供了实际指导。为此,我们实现了DF与四种不同的底层滤波算法,并在广泛的实验中比较它们。具体来说,我们(i)评估不同的实现选择和训练方法,(ii)研究在DF中学习复杂的不确定性模型的效果,(iii)评估通过DF进行端到端训练的效果,以及(iv)比较DF之间以及非结构化LSTM模型。

英文摘要:

In many robotic applications, it is crucial to maintain a belief about the state of a system, which serves as input for planning and decision making and provides feedback during task execution. Bayesian Filtering algorithms address this state estimation problem, but they require models of process dynamics and sensory observations and the respective noise characteristics of these models. Recently, multiple works have demonstrated that these models can be learned by end-to-end training through differentiable versions of recursive filtering algorithms. In this work, we investigate the advantages of differentiable filters (DFs) over both unstructured learning approaches and manually-tuned filtering algorithms, and provide practical guidance to researchers interested in applying such differentiable filters. For this, we implement DFs with four different underlying filtering algorithms and compare them in extensive experiments. Specifically, we (i) evaluate different implementation choices and training approaches, (ii) investigate how well complex models of uncertainty can be learned in DFs, (iii) evaluate the effect of end-to-end training through DFs and (iv) compare the DFs among each other and to unstructured LSTM models.

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。

↑