Planejamento de trajetórias e navegação de robôs móveis

Oil exploration at great depths requires the use of mobile robots to perform various operations such as maintenance, assembly etc. In this context, the trajectory planning and navigation study of these robots is relevant, as the great challenge is to navigate in an environment that is not fully known. The main objective is to develop a navigation algorithm to plan the path of a mobile robot that is in a given position (

Sensor Planning for Bayesian Nonparametric Target Modeling

Bayesian nonparametric models, such as the Gaussian process and the Dirichlet process, have been extensively applied for target kinematics modeling in various applications including environmental monitoring, traffic planning, endangered species tracking, dynamic scene analysis, autonomous robot navigation, and human motion modeling. As shown by these successful applications, Bayesian nonparametric models are able to adjust their complexities adaptively from data as necessary, and are resistant to overfitting or underfitting. However, most existing works assume that the sensor measurements used to learn the Bayesian nonparametric target kinematics models are obtained a priori or that the target kinematics can be measured by the sensor at any given time throughout the task. Little work has been done for controlling the sensor with bounded field of view to obtain measurements of mobile targets that are most informative for reducing the uncertainty of the Bayesian nonparametric models. To present the systematic sensor planning approach to leaning Bayesian nonparametric models, the Gaussian process target kinematics model is introduced at first, which is capable of describing time-invariant spatial phenomena, such as ocean currents, temperature distributions and wind velocity fields. The Dirichlet process-Gaussian process target kinematics model is subsequently discussed for modeling mixture of mobile targets, such as pedestrian motion patterns.

Novel information theoretic functions are developed for these introduced Bayesian nonparametric target kinematics models to represent the expected utility of measurements as a function of sensor control inputs and random environmental variables. A Gaussian process expected Kullback Leibler divergence is developed as the expectation of the KL divergence between the current (prior) and posterior Gaussian process target kinematics models with respect to the future measurements. Then, this approach is extended to develop a new information value function that can be used to estimate target kinematics described by a Dirichlet process-Gaussian process mixture model. A theorem is proposed that shows the novel information theoretic functions are bounded. Based on this theorem, efficient estimators of the new information theoretic functions are designed, which are proved to be unbiased with the variance of the resultant approximation error decreasing linearly as the number of samples increases. Computational complexities for optimizing the novel information theoretic functions under sensor dynamics constraints are studied, and are proved to be NP-hard. A cumulative lower bound is then proposed to reduce the computational complexity to polynomial time.

Three sensor planning algorithms are developed according to the assumptions on the target kinematics and the sensor dynamics. For problems where the control space of the sensor is discrete, a greedy algorithm is proposed. The efficiency of the greedy algorithm is demonstrated by a numerical experiment with data of ocean currents obtained by moored buoys. A sweep line algorithm is developed for applications where the sensor control space is continuous and unconstrained. Synthetic simulations as well as physical experiments with ground robots and a surveillance camera are conducted to evaluate the performance of the sweep line algorithm. Moreover, a lexicographic algorithm is designed based on the cumulative lower bound of the novel information theoretic functions, for the scenario where the sensor dynamics are constrained. Numerical experiments with real data collected from indoor pedestrians by a commercial pan-tilt camera are performed to examine the lexicographic algorithm. Results from both the numerical simulations and the physical experiments show that the three sensor planning algorithms proposed in this dissertation based on the novel information theoretic functions are superior at learning the target kinematics with

little or no prior knowledge

Integrating an entertainment robot

[EN]In this paper we will present Eldi, a mobile robot that has been in opertation at the Elder Museum of Science and Technology at Las Palmas de Gran Canaria since december 1999. This is an ongoing project that was organized in three different stages of which only the first one has been accomplished. The initial phase, termed "The Player", the second stage, actually under develpment, has been called "The Cicerone" and in the final phase, termed "The Vagabond", in which Eldi will be allowed to move erratically across the Museum. This paper will focus on the accomplished first stage to succinctly describe the physical robot and the environment and demos developed. Finally we will summarize some important lessons learnt.

Eldi: an agent based museum robot

[EN]In this paper we will present Eldi, a mobile robot that has been in daily operation at the Elder Museum of Science and Technology at Las Palmas de Gran Canaria since December 1999. This is an ongoing project that was organized in three di erent stages, describing here the one that has been accomplished. The initial phase, termed \The Player", the second stage, actually under development, has been called "The Cicerone" and in a nal phase, termed \The Vagabond", Eldi will be allowed to move erratically across the Museum. This paper will focus on the accomplished rst stage to succinctly describe the physical robot and the environment and demos developed. Finally we will summarize some important lessons learnt.

Experiences with a museum robot

In this paper we will present Eldi, a mobile robot that has been in daily operation at the Elder Museum of S ien e and Te hnology at Las Palmas de Gran Canaria sin e last De ember. This is an ongoing pro je t that was organized in three di erent stages of whi h only the rst one has been a omplished. The initial phase, termed \The Player", the se ond stage, a tually under development, has been alled "The Ci erone" and in a nal phase, termed \The Vagabond", Eldi will be allowed to move errati ally a ross the Museum...

A comparison of sound localisation techniques using cross-correlation and spiking neural networks for mobile robotics

This paper outlines the development of a crosscorrelation algorithm and a spiking neural network (SNN) for sound localisation based on real sound recorded in a noisy and dynamic environment by a mobile robot. The SNN architecture aims to simulate the sound localisation ability of the mammalian auditory pathways by exploiting the binaural cue of interaural time difference (ITD). The medial superior olive was the inspiration for the SNN architecture which required the integration of an encoding layer which produced biologically realistic spike trains, a model of the bushy cells found in the cochlear nucleus and a supervised learning algorithm. The experimental results demonstrate that biologically inspired sound localisation achieved using a SNN can compare favourably to the more classical technique of cross-correlation.

Navegação de robô móvel em ambiente com humanos

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia Mecânica

Teleoperación de un robot móvil mediante dispositivos Android

Resumen: En el siguiente trabajo se aborda un problema para solventar la comunicación con los robots del departamento MAPIR de la Universidad de Málaga, anteriormente sólo podían ser teleoperados mediante comandos escritos en Skype, así que se procede a diseñar un cliente móvil para Android que nos permite conectarse en tiempo real a un robot, obtener la imagen de lo que su cámara capta y además permitir su teleoperación. Por su parte, el robot corre un servidor que administra esos datos al cliente para trabajar conjuntamente. Dicho trabajo se desarrolla haciendo uso de nuevas tecnologias y protocolos como es WebRTC (de Google) para el intercambio de imágenes y del lado del servidor, se ha usado NodeJS.

Mimicking the behaviour of idiotypic AIS robot controllers using probabilistic systems

Previous work has shown that robot navigation systems that employ an architecture based upon the idiotypic network theory of the immune system have an advantage over control techniques that rely on reinforcement learning only. This is thought to be a result of intelligent behaviour selection on the part of the idiotypic robot. In this paper an attempt is made to imitate idiotypic dynamics by creating controllers that use reinforcement with a number of different probabilistic schemes to select robot behaviour. The aims are to show that the idiotypic system is not merely performing some kind of periodic random behaviour selection, and to try to gain further insight into the processes that govern the idiotypic mechanism. Trials are carried out using simulated Pioneer robots that undertake navigation exercises. Results show that a scheme that boosts the probability of selecting highly-ranked alternative behaviours to 50% during stall conditions comes closest to achieving the properties of the idiotypic system, but remains unable to match it in terms of all round performance.

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.

An assisted navigation method for telepresence robots

Telepresence robots have emerged as a new means of interaction in remote environments. However, the use of such robots is still limited due to safety and usability issues when operating in human-like environments. This work addresses these issues by enhancing the robot navigation through a collaborative control method that assists the user to negotiate obstacles. The method has been implemented in a commercial telepresence robot and a user study has been conducted in order to test the suitability of our approach.

Uma contribuição ao estudo de sinais de EEG para avaliar estados emocionais e mentais de crianças com autismo na interação com robô móvel

O Transtorno do Espectro do Autismo (TEA) caracteriza-se por uma série de distúrbios cognitivos e neurocomportamentais e sua prevalência mundial é estimada em 1 criança com TEA a cada 160 crianças com típico desenvolvimento (TD). Indivíduos com TEA apresentam dificuldade em interpretar as emoções alheias e em expressar sentimentos. As emoções podem ser associadas à manifestação de sinais fisiológicos, e, dentre eles, os sinais cerebrais têm sido muito abordados. A detecção dos sinais cerebrais de crianças com TEA pode ser benéfica para o esclarecimento de suas emoções e expressões. Atualmente, muitas pesquisas integram a robótica ao tratamento pedagógico do TEA, através da interação com crianças com esse transtorno, estimulando habilidades sociais, como a imitação e a comunicação. A avaliação dos estados mentais de crianças com TEA durante a sua interação com um robô móvel é promissora e assume um aspecto inovador. Assim, os objetivos deste trabalho foram captar sinais cerebrais de crianças com TEA e de crianças com TD, como grupo controle, para o estudo de seus estados emocionais e para avaliar seus estados mentais durante a interação com um robô móvel, e avaliar também a interação dessas crianças com o robô, através de escalas quantitativas. A técnica de registro dos sinais cerebrais escolhida foi a eletroencefalografia (EEG), a qual utiliza eletrodos colocados de forma não invasiva e não dolorosa sobre o couro cabeludo da criança. Os métodos para avaliar a eficiência do uso da robótica nessa interação foram baseados em duas escalas internacionais quantitativas: Escala de Alcance de Metas (do inglês Goal Attainment Scaling - GAS) e Escala de Usabilidade de Sistemas (do inglês System Usability Scale - SUS). Os resultados obtidos mostraram que, pela técnica de EEG, foi possível classificar os estados emocionais de crianças com TD e com TEA e analisar a atividade cerebral durante o início da interação com o robô, através dos ritmos alfa e beta. Com as avaliações GAS e SUS, verificou-se que o robô móvel pode ser considerado uma potencial ferramenta terapêutica para crianças com TEA.

Um algoritmo PSO híbrido para planejamento de caminhos em navegação de veículos utilizando A*

Utilizar robôs autônomos capazes de planejar o seu caminho é um desafio que atrai vários pesquisadores na área de navegação de robôs. Neste contexto, este trabalho tem como objetivo implementar um algoritmo PSO híbrido para o planejamento de caminhos em ambientes estáticos para veículos holonômicos e não holonômicos. O algoritmo proposto possui duas fases: a primeira utiliza o algoritmo A* para encontrar uma trajetória inicial viável que o algoritmo PSO otimiza na segunda fase. Por fim, uma fase de pós planejamento pode ser aplicada no caminho a fim de adaptá-lo às restrições cinemáticas do veículo não holonômico. O modelo Ackerman foi considerado para os experimentos. O ambiente de simulação de robótica CARMEN (Carnegie Mellon Robot Navigation Toolkit) foi utilizado para realização de todos os experimentos computacionais considerando cinco instâncias de mapas geradas artificialmente com obstáculos. O desempenho do algoritmo desenvolvido, A*PSO, foi comparado com os algoritmos A*, PSO convencional e A* Estado Híbrido. A análise dos resultados indicou que o algoritmo A*PSO híbrido desenvolvido superou em qualidade de solução o PSO convencional. Apesar de ter encontrado melhores soluções em 40% das instâncias quando comparado com o A*, o A*PSO apresentou trajetórias com menos pontos de guinada. Investigando os resultados obtidos para o modelo não holonômico, o A*PSO obteve caminhos maiores entretanto mais suaves e seguros.

Auxiliary mechanisms for telerobotics

Dissertação apresentada na Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa para obtenção do grau de Mestre em Engenharia Electrotécnica e de Computadores