ViDRILO: The Visual and Depth Robot Indoor Localization with Objects information dataset

In this article we describe a semantic localization dataset for indoor environments named ViDRILO. The dataset provides five sequences of frames acquired with a mobile robot in two similar office buildings under different lighting conditions. Each frame consists of a point cloud representation of the scene and a perspective image. The frames in the dataset are annotated with the semantic category of the scene, but also with the presence or absence of a list of predefined objects appearing in the scene. In addition to the frames and annotations, the dataset is distributed with a set of tools for its use in both place classification and object recognition tasks. The large number of labeled frames in conjunction with the annotation scheme make this dataset different from existing ones. The ViDRILO dataset is released for use as a benchmark for different problems such as multimodal place classification and object recognition, 3D reconstruction or point cloud data compression.

Comparative study of human age estimation based on hand-crafted and deep face features

In the past few years, human facial age estimation has drawn a lot of attention in the computer vision and pattern recognition communities because of its important applications in age-based image retrieval, security control and surveillance, biomet- rics, human-computer interaction (HCI) and social robotics. In connection with these investigations, estimating the age of a person from the numerical analysis of his/her face image is a relatively new topic. Also, in problems such as Image Classification the Deep Neural Networks have given the best results in some areas including age estimation. In this work we use three hand-crafted features as well as five deep features that can be obtained from pre-trained deep convolutional neural networks. We do a comparative study of the obtained age estimation results with these features.

La responsabilité civile dans les cas de dommages causés par les robots d’assistance au Québec

Le développement exponentiel de la technologie et le vieillissement de la population permettent d’introduire dans notre quotidien les robots d’assistance. La coexistence de l’homme avec ces robots intelligents et autonomes soulève une question fondamentale: dans l’éventualité où un robot provoquerait un accident causant un dommage à une personne ou à un bien qui serait le responsable? Aucune loi ne réglemente les activités de la robotique d’assistance dans le monde. Cette étude vise l’analyse de l’applicabilité des régimes de responsabilité du Code Civil du Québec aux cas de dommages causés par le robot d’assistance. L’analyse des régimes de responsabilité du Code civil du Québec permet de constater que deux régimes de responsabilité sont susceptibles d’être appliqués aux cas spécifiques de dommages causés par le robot d’assistance: le régime de responsabilité du fait des biens, énoncé à l’article 1465 C.c.Q., et le régime de responsabilité du fait des fabricants et vendeurs spécialisés, énoncé à l’article 1468 C.c.Q. Cela s’explique par la présence de critères et de conditions de mise en œuvre des régimes qui sont transposables aux différents aspects concernant la fabrication et l’utilisation du robot d’assistance.

AUTONOMOUS POWER DISTRIBUTION SYSTEMS

Using robotic systems for many missions that require power distribution can decrease the need for human intervention in such missions significantly. For accomplishing this capability a robotic system capable of autonomous navigation, power systems adaptation, and establishing physical connection needs to be developed. This thesis presents developed path planning and navigation algorithms for an autonomous ground power distribution system. In this work, a survey on existing path planning methods along with two developed algorithms by author is presented. One of these algorithms is a simple path planner suitable for implementation on lab-size platforms. A navigation hierarchy is developed for experimental validation of the path planner and proof of concept for autonomous ground power distribution system in lab environment. The second algorithm is a robust path planner developed for real-size implementation based on lessons learned from lab-size experiments. The simulation results illustrates that the algorithm is efficient and reliable in unknown environments. Future plans for developing intelligent power electronics and integrating them with robotic systems is presented. The ultimate goal is to create a power distribution system capable of regulating power flow at a desired voltage and frequency adaptable to load demands.

Comparison of Computer-Based and Optical Face Recognition Paradigms

The main objectives of this thesis are to validate an improved principal components analysis (IPCA) algorithm on images; designing and simulating a digital model for image compression, face recognition and image detection by using a principal components analysis (PCA) algorithm and the IPCA algorithm; designing and simulating an optical model for face recognition and object detection by using the joint transform correlator (JTC); establishing detection and recognition thresholds for each model; comparing between the performance of the PCA algorithm and the performance of the IPCA algorithm in compression, recognition and, detection; and comparing between the performance of the digital model and the performance of the optical model in recognition and detection. The MATLAB © software was used for simulating the models. PCA is a technique used for identifying patterns in data and representing the data in order to highlight any similarities or differences. The identification of patterns in data of high dimensions (more than three dimensions) is too difficult because the graphical representation of data is impossible. Therefore, PCA is a powerful method for analyzing data. IPCA is another statistical tool for identifying patterns in data. It uses information theory for improving PCA. The joint transform correlator (JTC) is an optical correlator used for synthesizing a frequency plane filter for coherent optical systems. The IPCA algorithm, in general, behaves better than the PCA algorithm in the most of the applications. It is better than the PCA algorithm in image compression because it obtains higher compression, more accurate reconstruction, and faster processing speed with acceptable errors; in addition, it is better than the PCA algorithm in real-time image detection due to the fact that it achieves the smallest error rate as well as remarkable speed. On the other hand, the PCA algorithm performs better than the IPCA algorithm in face recognition because it offers an acceptable error rate, easy calculation, and a reasonable speed. Finally, in detection and recognition, the performance of the digital model is better than the performance of the optical model.

MobiMed: Framework for Rapid Application Development of Medical Mobile Apps

In the medical field images obtained from high definition cameras and other medical imaging systems are an integral part of medical diagnosis. The analysis of these images are usually performed by the physicians who sometimes need to spend long hours reviewing the images before they are able to come up with a diagnosis and then decide on the course of action. In this dissertation we present a framework for a computer-aided analysis of medical imagery via the use of an expert system. While this problem has been discussed before, we will consider a system based on mobile devices. Since the release of the iPhone on April 2003, the popularity of mobile devices has increased rapidly and our lives have become more reliant on them. This popularity and the ease of development of mobile applications has now made it possible to perform on these devices many of the image analyses that previously required a personal computer. All of this has opened the door to a whole new set of possibilities and freed the physicians from their reliance on their desktop machines. The approach proposed in this dissertation aims to capitalize on these new found opportunities by providing a framework for analysis of medical images that physicians can utilize from their mobile devices thus remove their reliance on desktop computers. We also provide an expert system to aid in the analysis and advice on the selection of medical procedure. Finally, we also allow for other mobile applications to be developed by providing a generic mobile application development framework that allows for access of other applications into the mobile domain. In this dissertation we outline our work leading towards development of the proposed methodology and the remaining work needed to find a solution to the problem. In order to make this difficult problem tractable, we divide the problem into three parts: the development user interface modeling language and tooling, the creation of a game development modeling language and tooling, and the development of a generic mobile application framework. In order to make this problem more manageable, we will narrow down the initial scope to the hair transplant, and glaucoma domains.

La responsabilité civile dans les cas de dommages causés par les robots d’assistance au Québec

Le développement exponentiel de la technologie et le vieillissement de la population permettent d’introduire dans notre quotidien les robots d’assistance. La coexistence de l’homme avec ces robots intelligents et autonomes soulève une question fondamentale: dans l’éventualité où un robot provoquerait un accident causant un dommage à une personne ou à un bien qui serait le responsable? Aucune loi ne réglemente les activités de la robotique d’assistance dans le monde. Cette étude vise l’analyse de l’applicabilité des régimes de responsabilité du Code Civil du Québec aux cas de dommages causés par le robot d’assistance. L’analyse des régimes de responsabilité du Code civil du Québec permet de constater que deux régimes de responsabilité sont susceptibles d’être appliqués aux cas spécifiques de dommages causés par le robot d’assistance: le régime de responsabilité du fait des biens, énoncé à l’article 1465 C.c.Q., et le régime de responsabilité du fait des fabricants et vendeurs spécialisés, énoncé à l’article 1468 C.c.Q. Cela s’explique par la présence de critères et de conditions de mise en œuvre des régimes qui sont transposables aux différents aspects concernant la fabrication et l’utilisation du robot d’assistance.

Como construir com inteligência

A seleção deste tema deve-se ao fato de para além de ser um tema bastante interessante, o fato de possuir também uma perspetiva futura muito interessante, sobretudo quando contextualizado como solução de problemas tais como dependência energética, poluição e excesso de população. Apesar de muitos dos conceitos ligados ao tema não serem assim tão recentes, a verdade é que os recentes avanços tecnológicos, (informática e robótica), associados a novas ideologias, (preservação do meio ambiente e energias renováveis), e a diferentes conjunturas, nomeadamente a crise económica de 2009, trouxe uma nova perspetiva sobre o tema e sobre as suas potencialidades. Consultando a Internet é possível reunir varias informações sobre como construir com inteligência passando por temáticas como os edifícios Inteligentes, a sustentabilidade ou até mesmo os serviços de saúde em casa, contudo ainda é algo difícil perceber qual a importância que estes aspetos podem vir a desempenhar no futuro. Isto advém em grande medida, da própria dificuldade dos autores em concordar sobre o que realmente é um edifício inteligente e qual pode ser a sua importância para as cidades no futuro. Desta forma o objetivo deste trabalho passa por abordar os conceitos base do que são edifícios inteligentes desde a sua génese até ao presente, não só a partir do ponto de vista tecnológico como também do ponto de vista ambiental e da forma como estes se articulam, principalmente num período de dificuldade económica como o vivido nos dias de hoje. Hoje em dia torna-se demasiado redutor só pensar os edifícios inteligentes a partir da sua componente tecnológica uma vez que a sua adaptabilidade permite que sejam uma solução para um número muito maior de problemas, alguns dos quais onde a componente tecnológica perde o seu lugar de destaque para a componente ambiental, onde um design inteligente pode potenciar grandes melhorias com o mínimo de gastos económicos. Em conclusão um edifício Inteligente é nos dias de hoje muito mais que a soma das suas partes seja ela tecnológica, económica ou ambiental. A “verdadeira” Inteligência está em conjugar o melhor de cada vertente potenciando o que têm de melhor de forma a proporcionarem uma qualidade de vida acrescida ao utilizador sem comprometer o meio e sem implicar gastos económicos incomportáveis.

The conjugate gradient partitioned block frequency-domain for multichannel adaptive filtering

The conjugate gradient is the most popular optimization method for solving large systems of linear equations. In a system identification problem, for example, where very large impulse response is involved, it is necessary to apply a particular strategy which diminishes the delay, while improving the convergence time. In this paper we propose a new scheme which combines frequency-domain adaptive filtering with a conjugate gradient technique in order to solve a high order multichannel adaptive filter, while being delayless and guaranteeing a very short convergence time.

Scene Mapping and Understanding by Robotic Vision

The first mechanical Automaton concept was found in a Chinese text written in the 3rd century BC, while Computer Vision was born in the late 1960s. Therefore, visual perception applied to machines (i.e. the Machine Vision) is a young and exciting alliance. When robots came in, the new field of Robotic Vision was born, and these terms began to be erroneously interchanged. In short, we can say that Machine Vision is an engineering domain, which concern the industrial use of Vision. The Robotic Vision, instead, is a research field that tries to incorporate robotics aspects in computer vision algorithms. Visual Servoing, for example, is one of the problems that cannot be solved by computer vision only. Accordingly, a large part of this work deals with boosting popular Computer Vision techniques by exploiting robotics: e.g. the use of kinematics to localize a vision sensor, mounted as the robot end-effector. The remainder of this work is dedicated to the counterparty, i.e. the use of computer vision to solve real robotic problems like grasping objects or navigate avoiding obstacles. Will be presented a brief survey about mapping data structures most widely used in robotics along with SkiMap, a novel sparse data structure created both for robotic mapping and as a general purpose 3D spatial index. Thus, several approaches to implement Object Detection and Manipulation, by exploiting the aforementioned mapping strategies, will be proposed, along with a completely new Machine Teaching facility in order to simply the training procedure of modern Deep Learning networks.

Distributed Large-scale Mixed-Integer Optimization with Application to Energy and Multi-robot Networks

Several decision and control tasks in cyber-physical networks can be formulated as large- scale optimization problems with coupling constraints. In these "constraint-coupled" problems, each agent is associated to a local decision variable, subject to individual constraints. This thesis explores the use of primal decomposition techniques to develop tailored distributed algorithms for this challenging set-up over graphs. We first develop a distributed scheme for convex problems over random time-varying graphs with non-uniform edge probabilities. The approach is then extended to unknown cost functions estimated online. Subsequently, we consider Mixed-Integer Linear Programs (MILPs), which are of great interest in smart grid control and cooperative robotics. We propose a distributed methodological framework to compute a feasible solution to the original MILP, with guaranteed suboptimality bounds, and extend it to general nonconvex problems. Monte Carlo simulations highlight that the approach represents a substantial breakthrough with respect to the state of the art, thus representing a valuable solution for new toolboxes addressing large-scale MILPs. We then propose a distributed Benders decomposition algorithm for asynchronous unreliable networks. The framework has been then used as starting point to develop distributed methodologies for a microgrid optimal control scenario. We develop an ad-hoc distributed strategy for a stochastic set-up with renewable energy sources, and show a case study with samples generated using Generative Adversarial Networks (GANs). We then introduce a software toolbox named ChoiRbot, based on the novel Robot Operating System 2, and show how it facilitates simulations and experiments in distributed multi-robot scenarios. Finally, we consider a Pickup-and-Delivery Vehicle Routing Problem for which we design a distributed method inspired to the approach of general MILPs, and show the efficacy through simulations and experiments in ChoiRbot with ground and aerial robots.

Geometrico-static modelling of continuum parallel robots

In this thesis, we explore three methods for the geometrico-static modelling of continuum parallel robots. Inspired by biological trunks, tentacles and snakes, continuum robot designs can reach confined spaces, manipulate objects in complex environments and conform to curvilinear paths in space. In addition, parallel continuum manipulators have the potential to inherit some of the compactness and compliance of continuum robots while retaining some of the precision, stability and strength of rigid-links parallel robots. Subsequently, the foundation of our work is performed on slender beam by applying the Cosserat rod theory, appropriate to model continuum robots. After that, three different approaches are developed on a case study of a planar parallel continuum robot constituted of two connected flexible links. We solve the forward and inverse geometrico-static problem namely by using (a) shooting methods to obtain a numerical solution, (b) an elliptic method to find a quasi-analytical solution, and (c) the Corde model to perform further model analysis. The performances of each of the studied methods are evaluated and their limits are highlighted. This thesis is divided as follows. Chapter one gives the introduction on the field of the continuum robotics and introduce the parallel continuum robots that is studied in this work. Chapter two describe the geometrico-static problem and gives the mathematical description of this problem. Chapter three explains the numerical approach with the shooting method and chapter four introduce the quasi-analytical solution. Then, Chapter five introduce the analytic method inspired by the Corde model and chapter six gives the conclusions of this work.

Exploring domain-informed and physics-guided learning in image-to-image translation

Image-to-image (i2i) translation networks can generate fake images beneficial for many applications in augmented reality, computer graphics, and robotics. However, they require large scale datasets and high contextual understanding to be trained correctly. In this thesis, we propose strategies for solving these problems, improving performances of i2i translation networks by using domain- or physics-related priors. The thesis is divided into two parts. In Part I, we exploit human abstraction capabilities to identify existing relationships in images, thus defining domains that can be leveraged to improve data usage efficiency. We use additional domain-related information to train networks on web-crawled data, hallucinate scenarios unseen during training, and perform few-shot learning. In Part II, we instead rely on physics priors. First, we combine realistic physics-based rendering with generative networks to boost outputs realism and controllability. Then, we exploit naive physical guidance to drive a manifold reorganization, which allowed generating continuous conditions such as timelapses.

Unsupervised reinforcement learning via state entropy maximization

Reinforcement Learning (RL) provides a powerful framework to address sequential decision-making problems in which the transition dynamics is unknown or too complex to be represented. The RL approach is based on speculating what is the best decision to make given sample estimates obtained from previous interactions, a recipe that led to several breakthroughs in various domains, ranging from game playing to robotics. Despite their success, current RL methods hardly generalize from one task to another, and achieving the kind of generalization obtained through unsupervised pre-training in non-sequential problems seems unthinkable. Unsupervised RL has recently emerged as a way to improve generalization of RL methods. Just as its non-sequential counterpart, the unsupervised RL framework comprises two phases: An unsupervised pre-training phase, in which the agent interacts with the environment without external feedback, and a supervised fine-tuning phase, in which the agent aims to efficiently solve a task in the same environment by exploiting the knowledge acquired during pre-training. In this thesis, we study unsupervised RL via state entropy maximization, in which the agent makes use of the unsupervised interactions to pre-train a policy that maximizes the entropy of its induced state distribution. First, we provide a theoretical characterization of the learning problem by considering a convex RL formulation that subsumes state entropy maximization. Our analysis shows that maximizing the state entropy in finite trials is inherently harder than RL. Then, we study the state entropy maximization problem from an optimization perspective. Especially, we show that the primal formulation of the corresponding optimization problem can be (approximately) addressed through tractable linear programs. Finally, we provide the first practical methodologies for state entropy maximization in complex domains, both when the pre-training takes place in a single environment as well as multiple environments.

Preventing worker’s musculoskeletal disorders with wearable inertial sensors: ergonomics and modelling of physical human-robot interactions

The most widespread work-related diseases are musculoskeletal disorders (MSD) caused by awkward postures and excessive effort to upper limb muscles during work operations. The use of wearable IMU sensors could monitor the workers constantly to prevent hazardous actions, thus diminishing work injuries. In this thesis, procedures are developed and tested for ergonomic analyses in a working environment, based on a commercial motion capture system (MoCap) made of 17 Inertial Measurement Units (IMUs). An IMU is usually made of a tri-axial gyroscope, a tri-axial accelerometer, and a tri-axial magnetometer that, through sensor fusion algorithms, estimates its attitude. Effective strategies for preventing MSD rely on various aspects: firstly, the accuracy of the IMU, depending on the chosen sensor and its calibration; secondly, the correct identification of the pose of each sensor on the worker’s body; thirdly, the chosen multibody model, which must consider both the accuracy and the computational burden, to provide results in real-time; finally, the model scaling law, which defines the possibility of a fast and accurate personalization of the multibody model geometry. Moreover, the MSD can be diminished using collaborative robots (cobots) as assisted devices for complex or heavy operations to relieve the worker's effort during repetitive tasks. All these aspects are considered to test and show the efficiency and usability of inertial MoCap systems for assessing ergonomics evaluation in real-time and implementing safety control strategies in collaborative robotics. Validation is performed with several experimental tests, both to test the proposed procedures and to compare the results of real-time multibody models developed in this thesis with the results from commercial software. As an additional result, the positive effects of using cobots as assisted devices for reducing human effort in repetitive industrial tasks are also shown, to demonstrate the potential of wearable electronics in on-field ergonomics analyses for industrial applications.