arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.01595cs.ROcs.AI
收藏

面向目标定位的内存高效型粒子滤波循环神经网络

Memory-efficient particle filter recurrent neural network for object localization

Novosibirsk Technology Center(新西伯利亚技术中心);Schlumberger(斯伦贝谢);AIRI;Skoltech(斯科尔科沃科学技术研究院)

Roman Korkin, Ivan Oseledets, Aleksandr Katrutsa

AI总结:

本研究针对噪声环境下的目标定位问题,结合经典粒子滤波思想与GRU RNN架构提出内存高效的mePFRNN模型,其参数量不随环境规模变化,在对称高噪环境中定位精度更优且参数更少。

摘要:

本研究提出一种专为解决目标定位问题设计的新型内存高效循环神经网络(RNN)架构。该问题旨在从存在噪声的环境中还原目标的运动状态及其变化过程。我们借鉴经典粒子滤波的思想,将其与GRU RNN架构相结合。由此得到的内存高效粒子滤波RNN模型(mePFRNN)的核心特性是,处理不同规模的环境所需的参数量保持一致。因此,与此前提出的PFRNN模型相比,本研究提出的mePFRNN架构存储参数所需的内存更少。为验证模型性能,我们在对滤波算法极具挑战的对称且含噪环境中开展测试。实验结果显示,mePFRNN模型的定位精度优于所有对比模型,且所需训练参数量更少。

英文摘要:

This study proposes a novel memory-efficient recurrent neural network (RNN) architecture specified to solve the object localization problem. This problem is to recover the object states along with its movement in a noisy environment. We take the idea of the classical particle filter and combine it with GRU RNN architecture. The key feature of the resulting memory-efficient particle filter RNN model (mePFRNN) is that it requires the same number of parameters to process environments of different sizes. Thus, the proposed mePFRNN architecture consumes less memory to store parameters compared to the previously proposed PFRNN model. To demonstrate the performance of our model, we test it on symmetric and noisy environments that are incredibly challenging for filtering algorithms. In our experiments, the mePFRNN model provides more precise localization than the considered competitors and requires fewer trained parameters.

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。

↑