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...

Focal length calibration for depth recovery using a focusing technique

[EN]The work presented in this paper is related to Depth Recovery from Focus The approach starts calibrating focal length of the camera using the Gaussian lens law for the thin lens camera model Two approaches are presented based on the availability of the internal distance of the lens

Localization of a mobile robot based on odometry and natural landmarks using extended kalman filter

SANTANA, André M.; SOUZA, Anderson A. S.; BRITTO, Ricardo S.; ALSINA, Pablo J.; MEDEIROS, Adelardo A. D. Localization of a mobile robot based on odometry and natural landmarks using extended Kalman Filter. In: INTERNATIONAL CONFERENCE ON INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS, 5., 2008, Funchal, Portugal. Proceedings... Funchal, Portugal: ICINCO, 2008.

Fast and accurate hand pose detection for human-robot interaction

[EN]Enabling natural human-robot interaction using computer vision based applications requires fast and accurate hand detection. However, previous works in this field assume different constraints, like a limitation in the number of detected gestures, because hands are highly complex objects difficult to locate. This paper presents an approach which integrates temporal coherence cues and hand detection based on wrists using a cascade classifier. With this approach, we introduce three main contributions: (1) a transparent initialization mechanism without user participation for segmenting hands independently of their gesture, (2) a larger number of detected gestures as well as a faster training phase than previous cascade classifier based methods and (3) near real-time performance for hand pose detection in video streams.

Radiometric Calibration

Resources created at the University of Southampton for the module Remote Sensing for Earth Observation

VISSIM Calibration for Urban Freeways, 2015

In urban areas, interchange spacing and the adequacy of design for weaving, merge, and diverge areas can significantly influence available capacity. Traffic microsimulation tools allow detailed analyses of these critical areas in complex locations that often yield results that differ from the generalized approach of the Highway Capacity Manual. In order to obtain valid results, various inputs should be calibrated to local conditions. This project investigated basic calibration factors for the simulation of traffic conditions within an urban freeway merge/diverge environment. By collecting and analyzing urban freeway traffic data from multiple sources, specific Iowa-based calibration factors for use in VISSIM were developed. In particular, a repeatable methodology for collecting standstill distance and headway/time gap data on urban freeways was applied to locations throughout the state of Iowa. This collection process relies on the manual processing of video for standstill distances and individual vehicle data from radar detectors to measure the headways/time gaps. By comparing the data collected from different locations, it was found that standstill distances vary by location and lead-follow vehicle types. Headways and time gaps were found to be consistent within the same driver population and across different driver populations when the conditions were similar. Both standstill distance and headway/time gap were found to follow fairly dispersed and skewed distributions. Therefore, it is recommended that microsimulation models be modified to include the option for standstill distance and headway/time gap to follow distributions as well as be set separately for different vehicle classes. In addition, for the driving behavior parameters that cannot be easily collected, a sensitivity analysis was conducted to examine the impact of these parameters on the capacity of the facility. The sensitivity analysis results can be used as a reference to manually adjust parameters to match the simulation results to the observed traffic conditions. A well-calibrated microsimulation model can enable a higher level of fidelity in modeling traffic behavior and serve to improve decision making in balancing need with investment.

Diseño, construcción y control de un robot balancín.

Se diseñó, construyó, simuló e implementó un dispositivo robot balancín para la aplicación y estudio de técnicas avanzadas de control. Para esto se realizó el diseño mecánico del dispositivo, de acuerdo a una elección entre dos modelos distintos y cuatro tipos diferentes de transmisión. Luego se instrumentó el dispositivo con encoders de posición , acelerómetro y giróscopo para obtener el estado del dispositivo y controlarlo. Se realizó una placa electrónica para la lectura y procesamiento de señales de sensores con un micro controlador, un regulador de tensión, y un driver para los motores, capaz de obtener las señales de los encoders y el módulo acelerómetro-giróscopo y enviarlas por comunicación hacia una mini-computadora, la cual ejecuta el control, y se comunica nuevamente a la placa diseñada para comandar los motores. Se desarrolló un modelo teórico simplificado en dos dimensiones para facilitar la posterior identificación de planta. Se realizaron experimentos para lograr una identificación de planta. A partir de lo obtenido, se diseñó y simuló el control necesario para mantener la estabilidad. Se implementó posteriormente el control diseñado. Se reajustaron los parámetros correspondientes de acuerdo a la práctica experimental para mejorar la respuesta dinámica del sistema.

Sistema di guida robot per operazioni di pick and place

Uno dei fattori che ha favorito la diffusione della robotica è legato alla nascita, allo sviluppo e al perfezionamento dei sistemi di guida robot. Per guida robot si intende un sistema di visione artificiale capace di guidare un robot durante lo svolgimento di un determinato compito. All'interno di questo elaborato di tesi, verrà illustrato in dettaglio un sistema di guida robot realizzato per una operazione di pick and place 2D multistrato. Sebbene la procedura proposta sia stata sviluppata per risolvere un problema specifico, la sua validità è del tutto generale e può essere estesa anche ad altre applicazioni appartenenti alla stessa categoria.

Modélisation de la sécurité des tâches coopératives humain-robot

L’interaction physique humain-robot est un domaine d’étude qui s’est vu porter beaucoup d’intérêt ces dernières années. Une optique de coopération entre les deux entités entrevoit le potentiel d’associer les forces de l’humain (comme son intelligence et son adaptabilité) à celle du robot (comme sa puissance et sa précision). Toutefois, la mise en service des applications développées reste une opération délicate tant les problèmes liés à la sécurité demeurent importants. Les robots constituent généralement de lourdes machines capables de déplacements très rapides qui peuvent blesser gravement un individu situé à proximité. Ce projet de recherche aborde le problème de sécurité en amont avec le développement d’une stratégie dite "pré-collision". Celle-ci se caractérise par la conception d’un système de planification de mouvements visant à optimiser la sécurité de l’individu lors de tâches d’interaction humain-robot dans un contexte industriel. Pour ce faire, un algorithme basé sur l’échantillonnage a été employé et adapté aux contraintes de l’application visée. Dans un premier temps, l’intégration d’une méthode exacte de détection de collision certifie que le chemin trouvé ne présente, a priori, aucun contact indésirable. Ensuite, l’évaluation de paramètres pertinents introduit notre notion de sécurité et définit un ensemble d’objectifs à optimiser. Ces critères prennent en compte la proximité par rapport aux obstacles, l’état de conscience des êtres humains inclus dans l’espace de travail ainsi que le potentiel de réaction du robot en cas d'évènement imprévu. Un système inédit de combinaison d’objectifs guide la recherche et mène à l’obtention du chemin jugé comme étant le plus sûr, pour une connaissance donnée de l’environnement. Le processus de contrôle se base sur une acquisition minimale de données environnementales (dispositif de surveillance visuelle) dans le but de nécessiter une installation matérielle qui se veut la plus simple possible. Le fonctionnement du système a été validé sur le robot industriel Baxter.

The Inverse Jacobian Control Method Applied to a Four Degree of Freedom Confined Space Robot

Thesis (Master's)--University of Washington, 2016-06