WiFi based communication and localization of an autonomous mobile robot for refinery inspection

Sweatt, Marshall R.; Ayoade, Adewole A.; Han, Qi; Steele, John P.; Al-Wahedi, Khaled; Karki, Hamad

doi:10.1109/icra.2015.7139821

Cited by 21 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Possible application environments include buildings with existing WiFi infrastructure where other solutions are too expensive or yet not reliable enough, i.e. for refinery inspection [9]. Although the most advanced WiFi systems are used for personal indoor localization with mobile devices (smartphones) in order to provide efficient navigation inside buildings and allow to gather statistical information about the movement of clients inside shopping malls, airports, etc.…”

Section: Related Workmentioning

confidence: 99%

Low-Effort Place Recognition with WiFi Fingerprints Using Deep Learning

Nowicki

Wietrzykowski

2017

Advances in Intelligent Systems and Computing

132

View full text Add to dashboard Cite

Abstract. Using WiFi signals for indoor localization is the main localization modality of the existing personal indoor localization systems operating on mobile devices. WiFi fingerprinting is also used for mobile robots, as WiFi signals are usually available indoors and can provide rough initial position estimate or can be used together with other positioning systems. Currently, the best solutions rely on filtering, manual data analysis, and time-consuming parameter tuning to achieve reliable and accurate localization. In this work, we propose to use deep neural networks to significantly lower the work-force burden of the localization system design, while still achieving satisfactory results. Assuming the state-of-the-art hierarchical approach, we employ the DNN system for building/floor classification. We show that stacked autoencoders allow to efficiently reduce the feature space in order to achieve robust and precise classification. The proposed architecture is verified on the publicly available UJIIndoorLoc dataset and the results are compared with other solutions.

show abstract

Section: Related Workmentioning

confidence: 99%

Low-Effort Place Recognition with WiFi Fingerprints Using Deep Learning

Nowicki

Wietrzykowski

2017

Advances in Intelligent Systems and Computing

132

View full text Add to dashboard Cite

show abstract

“…With the development of the robotic industry, robot localization has become more challenging in the past decades: from known to unknown environments, from simple to complex environments, from static to dynamic environments [1], and from short-term to long-term localization [2]. Traditionally, fixed anchors (or routers) are set up in a pre-defined area and the robot pose is obtained by using the distances of the robot from multiple anchors, e.g., Ultra-Wide Band (UWB) [3] and Wi-Fi localization [4]. However, these methods rely on external setup and they are mainly used in a small scale environment.…”

Section: Introductionmentioning

confidence: 99%

Intensity-SLAM: Intensity Assisted Localization and Mapping for Large Scale Environment

Wang,

Xie

2021

Preprint

View full text Add to dashboard Cite

Simultaneous Localization And Mapping (SLAM) is a task to estimate the robot location and to reconstruct the environment based on observation from sensors such as LIght Detection And Ranging (LiDAR) and camera. It is widely used in robotic applications such as autonomous driving and drone delivery. Traditional LiDAR-based SLAM algorithms mainly leverage the geometric features from the scene context, while the intensity information from LiDAR is ignored. Some recent deep-learningbased SLAM algorithms consider intensity features and train the pose estimation network in an end-to-end manner. However, they require significant data collection effort and their generalizability to environments other than the trained one remains unclear. In this paper we introduce intensity features to a SLAM system. And we propose a novel full SLAM framework that leverages both geometry and intensity features. The proposed SLAM involves both intensity-based front-end odometry estimation and intensity-based back-end optimization. Thorough experiments are performed including both outdoor autonomous driving and indoor warehouse robot manipulation. The results show that the proposed method outperforms existing geometric-only LiDAR SLAM methods.

show abstract

“…O pensamento de sistemas e a solução de problemas de sistemas para a fábrica inteligente devem ser priorizados (Li, 2016). Na literatura se encontram vários trabalhos relacionados à aplicação de sistemas inteligentes em processos de gestão, operação e manutenção na indústria de petróleo e gás (Gharbi & Mansoori, 2005); (Espíndola et al, 2013); (Sayda & Taylor, 2007); (Sweatt et al, 2015); (reza Akhondi, Talevski, Carlsen, & Petersen, 2010a); (Vellingiri, Ray, & Kande, 2013); (Gil, Santos, & Cardoso, 2013).…”

Section: Introductionunclassified

Implementação de plataforma de automação por dispositivos móveis para gestão operacional em refinaria de petróleo

Almeida

Cartaxo

Barreiros

et al. 2019

BJD

View full text Add to dashboard Cite

RESUMOEste artigo apresenta uma pesquisa da aplicação de plataforma de automação por dispositivos móveis objetivando otimizar o gerenciamento de rotinas e procedimentos operacionais de uma refinaria de petróleo, mais precisamente no setor de transferência e estocagem. A implementação da plataforma nesta prática se desenvolve em dois segmentos: rotinas operacionais e procedimentos de gestão. No primeiro caso, um breve mapeamento das rotinas operacionais é feito tal como os resultados são coletados e inseridos na plataforma. E no segundo, é apresentado um uso não convencional da plataforma para gestão de um procedimento de validação e acompanhamento de medidores automáticos, onde primeiramente é mapeado todo o fluxo de decisão considerando as etapas e os atores que o desempenham, até a análise dos resultados obtidos nos primeiros meses do emprego na refinaria. O trabalho envolve ainda o estudo da economicidade do monitoramento por meio de medidores automáticos e da viabilidade econômica de informatizar a tomada de decisão. Este estudo foi feito a partir de três cenários, analisando o comportamento dos custos variáveis, fixos e de não qualidade, baseado na confiabilidade do sistema. As técnicas de custeio utilizadas são de Custeio Direto e de Custeio por Atividade Orientado pelo Tempo (TDABC), encontrando ao final a redução de custos totais em até 79% a partir do cenário original. Os

show abstract

WiFi based communication and localization of an autonomous mobile robot for refinery inspection

Cited by 21 publications

References 12 publications

Low-Effort Place Recognition with WiFi Fingerprints Using Deep Learning

Low-Effort Place Recognition with WiFi Fingerprints Using Deep Learning

Intensity-SLAM: Intensity Assisted Localization and Mapping for Large Scale Environment

Implementação de plataforma de automação por dispositivos móveis para gestão operacional em refinaria de petróleo

Contact Info

Product

Resources

About