A state-of-the-art review on mobile robotics tasks using artificial intelligence and visual data

Cebollada, Sergio; Payá, Luis; Flores, María; Peidró, Adrián

doi:10.1016/j.eswa.2020.114195

Cited by 107 publications

(39 citation statements)

References 112 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Machine learning techniques have been used to solve a variety of problems in computer vision and robotics (Cebollada et al 2021). Gonzalez et al (2018) use machine learning to detect different levels of slippage for robotic missions in Mars; Dymczyk et al (2018) present the use of a boosted classifier to classify landmark observations and carry out the localization task in a more robust fashion.…”

Section: State Of the Artmentioning

confidence: 99%

Development and use of a convolutional neural network for hierarchical appearance-based localization

et al. 2021

Self Cite

View full text Add to dashboard Cite

This paper reports and evaluates the adaption and re-training of a Convolutional Neural Network (CNN) with the aim of tackling the visual localization of a mobile robot by means of a hierarchical approach. The proposed method addresses the localization problem from the information captured by a catadioptric vision sensor mounted on the mobile robot. A CNN is adapted and evaluated with a twofold purpose. First, to perform a rough localization step (room retrieval) by means of the output layer. Second, to refine this localization in the retrieved room (fine localization step) by means of holistic descriptors obtained from intermediate layers of the same CNN. The robot estimates its position within the selected room/s through a nearest neighbour search by comparing the obtained holistic descriptor with the visual model of the retrieved room/s. Additionally, this method takes advantage of the likelihood information provided by the output layer of the CNN. This likelihood is helpful to determine which rooms should be considered in the fine localization process. This novel hierarchical localization method constitutes an efficient and robust solution, as shown in the experimental section even in presence of severe changes of the lighting conditions.

show abstract

Section: State Of the Artmentioning

confidence: 99%

Development and use of a convolutional neural network for hierarchical appearance-based localization

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…En la literatura relacionada se pueden encontrar diversos trabajos que han abordado tareas en robótica y procesamiento de imágenes mediante técnicas de aprendizaje automático [4]. En cuanto al uso de las CNNs en el campo de la robótica móvil, son muchos los autores que han demostrado suéxito utilizando esta herramienta.…”

Section: Estado Del Arteunclassified

Entrenamiento, optimización y validación de una CNN para localización jerárquica mediante imágenes omnidireccionales.

Cabrera¹,

Cebollada²,

Ballesta³

et al. 2021

Xlii Jornadas De Automática : Libro De Actas

Self Cite

View full text Add to dashboard Cite

El objetivo del presente trabajo es abordar la localización de un robot móvil mediante el entrenamiento de una Red Neuronal Convolucional (CNN) de manera que se obtengan unos resultados óptimos. El problema de localización se aborda de forma jerárquica empleando un sistema catadióptrico omnidireccional y se trabaja directamente con las imágenes capturadas sin pasar a panorámicas, ahorrando así el tiempo de cálculo asociado a este proceso. La localización se lleva a cabo en dos pasos y en ambos se emplea la arquitectura de la CNN con diferentes objetivos. Primero se lleva a cabo una localización gruesa que consiste en identificar la estancia en la que se encuentra el robot por medio de la CNN. Después se realiza una localización fina en dicha estancia, en la cual la CNN es empleada para la obtención de descriptores holísticos a partir de las capas intermedias de la red. Estos descriptores globales permiten encontrar la posición donde se encuentra el robot de manera más precisa por medio de una búsqueda del vecino más cercano, comparando el descriptor correspondiente de la imagen test con los descriptores de las imágenes capturadas en la estancia seleccionada en el primer paso. Con el fin de mejorar el desempeño de la red se recurre a un aumento de datos y a una optimización bayesiana de hiperparámetros. Estas técnicas demuestran ser una solución eficiente y robusta para afrontar el problema de localización tal y como se muestra en la sección de experimentos.

show abstract

“…Therefore, with this kind of information, global features constitute an effective alternative, compared to local features, to many tasks, such as, for example, the reconstruction of complex indoor environments. In this regard, Sun et al [ 5 ] and Pintone et al [ 6 ] make use of deep learning approaches [ 7 , 8 , 9 ] to panoramic image analysis, with the objective of understanding the layout of indoor environments.…”

Section: Introductionmentioning

confidence: 99%

The Role of Global Appearance of Omnidirectional Images in Relative Distance and Orientation Retrieval

Román

Payá

Peidró

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Over the last few years, mobile robotics has experienced a great development thanks to the wide variety of problems that can be solved with this technology. An autonomous mobile robot must be able to operate in a priori unknown environments, planning its trajectory and navigating to the required target points. With this aim, it is crucial solving the mapping and localization problems with accuracy and acceptable computational cost. The use of omnidirectional vision systems has emerged as a robust choice thanks to the big quantity of information they can extract from the environment. The images must be processed to obtain relevant information that permits solving robustly the mapping and localization problems. The classical frameworks to address this problem are based on the extraction, description and tracking of local features or landmarks. However, more recently, a new family of methods has emerged as a robust alternative in mobile robotics. It consists of describing each image as a whole, what leads to conceptually simpler algorithms. While methods based on local features have been extensively studied and compared in the literature, those based on global appearance still merit a deep study to uncover their performance. In this work, a comparative evaluation of six global-appearance description techniques in localization tasks is carried out, both in terms of accuracy and computational cost. Some sets of images captured in a real environment are used with this aim, including some typical phenomena such as changes in lighting conditions, visual aliasing, partial occlusions and noise.

show abstract

A state-of-the-art review on mobile robotics tasks using artificial intelligence and visual data

Cited by 107 publications

References 112 publications

Development and use of a convolutional neural network for hierarchical appearance-based localization

Development and use of a convolutional neural network for hierarchical appearance-based localization

Entrenamiento, optimización y validación de una CNN para localización jerárquica mediante imágenes omnidireccionales.

The Role of Global Appearance of Omnidirectional Images in Relative Distance and Orientation Retrieval

Contact Info

Product

Resources

About