LoCS-Net: Localizing convolutional spiking neural network for fast visual place recognition.

IF 2.6 4区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Frontiers in Neurorobotics Pub Date : 2025-01-29 eCollection Date: 2024-01-01 DOI:10.3389/fnbot.2024.1490267
Ugur Akcal, Ivan Georgiev Raikov, Ekaterina Dmitrievna Gribkova, Anwesa Choudhuri, Seung Hyun Kim, Mattia Gazzola, Rhanor Gillette, Ivan Soltesz, Girish Chowdhary
{"title":"LoCS-Net: Localizing convolutional spiking neural network for fast visual place recognition.","authors":"Ugur Akcal, Ivan Georgiev Raikov, Ekaterina Dmitrievna Gribkova, Anwesa Choudhuri, Seung Hyun Kim, Mattia Gazzola, Rhanor Gillette, Ivan Soltesz, Girish Chowdhary","doi":"10.3389/fnbot.2024.1490267","DOIUrl":null,"url":null,"abstract":"<p><p>Visual place recognition (VPR) is the ability to recognize locations in a physical environment based only on visual inputs. It is a challenging task due to perceptual aliasing, viewpoint and appearance variations and complexity of dynamic scenes. Despite promising demonstrations, many state-of-the-art (SOTA) VPR approaches based on artificial neural networks (ANNs) suffer from computational inefficiency. However, spiking neural networks (SNNs) implemented on neuromorphic hardware are reported to have remarkable potential for more efficient solutions computationally. Still, training SOTA SNNs for VPR is often intractable on large and diverse datasets, and they typically demonstrate poor real-time operation performance. To address these shortcomings, we developed an end-to-end convolutional SNN model for VPR that leverages backpropagation for tractable training. Rate-based approximations of leaky integrate-and-fire (LIF) neurons are employed during training, which are then replaced with spiking LIF neurons during inference. The proposed method significantly outperforms existing SOTA SNNs on challenging datasets like Nordland and Oxford RobotCar, achieving 78.6% precision at 100% recall on the Nordland dataset (compared to 73.0% from the current SOTA) and 45.7% on the Oxford RobotCar dataset (compared to 20.2% from the current SOTA). Our approach offers a simpler training pipeline while yielding significant improvements in both training and inference times compared to SOTA SNNs for VPR. Hardware-in-the-loop tests using Intel's neuromorphic USB form factor, Kapoho Bay, show that our on-chip spiking models for VPR trained via the ANN-to-SNN conversion strategy continue to outperform their SNN counterparts, despite a slight but noticeable decrease in performance when transitioning from off-chip to on-chip, while offering significant energy efficiency. The results highlight the outstanding rapid prototyping and real-world deployment capabilities of this approach, showing it to be a substantial step toward more prevalent SNN-based real-world robotics solutions.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"18 ","pages":"1490267"},"PeriodicalIF":2.6000,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11813887/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Neurorobotics","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.3389/fnbot.2024.1490267","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/1/1 0:00:00","PubModel":"eCollection","JCR":"Q3","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Visual place recognition (VPR) is the ability to recognize locations in a physical environment based only on visual inputs. It is a challenging task due to perceptual aliasing, viewpoint and appearance variations and complexity of dynamic scenes. Despite promising demonstrations, many state-of-the-art (SOTA) VPR approaches based on artificial neural networks (ANNs) suffer from computational inefficiency. However, spiking neural networks (SNNs) implemented on neuromorphic hardware are reported to have remarkable potential for more efficient solutions computationally. Still, training SOTA SNNs for VPR is often intractable on large and diverse datasets, and they typically demonstrate poor real-time operation performance. To address these shortcomings, we developed an end-to-end convolutional SNN model for VPR that leverages backpropagation for tractable training. Rate-based approximations of leaky integrate-and-fire (LIF) neurons are employed during training, which are then replaced with spiking LIF neurons during inference. The proposed method significantly outperforms existing SOTA SNNs on challenging datasets like Nordland and Oxford RobotCar, achieving 78.6% precision at 100% recall on the Nordland dataset (compared to 73.0% from the current SOTA) and 45.7% on the Oxford RobotCar dataset (compared to 20.2% from the current SOTA). Our approach offers a simpler training pipeline while yielding significant improvements in both training and inference times compared to SOTA SNNs for VPR. Hardware-in-the-loop tests using Intel's neuromorphic USB form factor, Kapoho Bay, show that our on-chip spiking models for VPR trained via the ANN-to-SNN conversion strategy continue to outperform their SNN counterparts, despite a slight but noticeable decrease in performance when transitioning from off-chip to on-chip, while offering significant energy efficiency. The results highlight the outstanding rapid prototyping and real-world deployment capabilities of this approach, showing it to be a substantial step toward more prevalent SNN-based real-world robotics solutions.

LoCS-Net:用于快速视觉位置识别的局部卷积脉冲神经网络。
视觉位置识别(VPR)是一种仅根据视觉输入识别物理环境中位置的能力。由于感知混叠、视点和外观的变化以及动态场景的复杂性,这是一项具有挑战性的任务。尽管有很好的证明,但许多基于人工神经网络(ann)的最先进(SOTA) VPR方法存在计算效率低下的问题。然而,据报道,在神经形态硬件上实现的峰值神经网络(snn)在计算上具有更有效的解决方案的显着潜力。尽管如此,在大型和多样化的数据集上训练SOTA snn用于VPR通常是棘手的,并且它们通常表现出较差的实时操作性能。为了解决这些缺点,我们为VPR开发了一个端到端卷积SNN模型,该模型利用反向传播进行可处理的训练。在训练过程中使用基于速率的泄漏集成-点火(LIF)神经元近似,然后在推理过程中用峰值LIF神经元代替。所提出的方法在具有挑战性的数据集(如Nordland和Oxford RobotCar)上显著优于现有的SOTA snn,在100%召回率下,在Nordland数据集上实现了78.6%的精度(与当前SOTA的73.0%相比),在Oxford RobotCar数据集上实现了45.7%的精度(与当前SOTA的20.2%相比)。我们的方法提供了一个更简单的训练管道,同时与SOTA snn的VPR相比,在训练和推理时间上都有了显著的改进。使用英特尔的神经形态USB外形因子Kapoho Bay进行的硬件在环测试表明,通过ann到SNN转换策略训练的VPR片上峰值模型继续优于SNN同类模型,尽管从片外转换到片上时性能略有但明显下降,同时提供显著的能源效率。结果突出了这种方法的出色的快速原型和实际部署能力,表明它是朝着更普遍的基于snn的实际机器人解决方案迈出的重要一步。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Frontiers in Neurorobotics
Frontiers in Neurorobotics COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCER-ROBOTICS
CiteScore
5.20
自引率
6.50%
发文量
250
审稿时长
14 weeks
期刊介绍: Frontiers in Neurorobotics publishes rigorously peer-reviewed research in the science and technology of embodied autonomous neural systems. Specialty Chief Editors Alois C. Knoll and Florian Röhrbein at the Technische Universität München are supported by an outstanding Editorial Board of international experts. This multidisciplinary open-access journal is at the forefront of disseminating and communicating scientific knowledge and impactful discoveries to researchers, academics and the public worldwide. Neural systems include brain-inspired algorithms (e.g. connectionist networks), computational models of biological neural networks (e.g. artificial spiking neural nets, large-scale simulations of neural microcircuits) and actual biological systems (e.g. in vivo and in vitro neural nets). The focus of the journal is the embodiment of such neural systems in artificial software and hardware devices, machines, robots or any other form of physical actuation. This also includes prosthetic devices, brain machine interfaces, wearable systems, micro-machines, furniture, home appliances, as well as systems for managing micro and macro infrastructures. Frontiers in Neurorobotics also aims to publish radically new tools and methods to study plasticity and development of autonomous self-learning systems that are capable of acquiring knowledge in an open-ended manner. Models complemented with experimental studies revealing self-organizing principles of embodied neural systems are welcome. Our journal also publishes on the micro and macro engineering and mechatronics of robotic devices driven by neural systems, as well as studies on the impact that such systems will have on our daily life.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信