14.07.2014
Schräge Roboter

Das kreative Mitmachlabor kommt in die Schule

Schräge Roboter ist ein Wissenschaftskommunikationsprojekt der Gruppe Vision for Robotics, gefördert vom FWF Wissenschaftsfonds. Das Ziel des Projektes ist es Schülerinnen und Schülern Robotik aus der Produktentwicklungsperspektive näherzubringen und dabei alle SchülerInnen anzusprechen (nicht nur jene, die bereits an Mathematik, Informatik, Naturwissenschaften und Technik – MINT – Fächern interessiert sind). Eine Besonderheit des Projektes ist die Umsetzung nach den Prinzipien des benutzerzentrierten Designs, das nicht nur die Interessen der SchülerInnen und LehrerInnen in den Mittelpunkt stellt, sondern auch andere Stakeholder wie Eltern miteinbezieht.

Das Projektkonzept basiert auf dem „5-Schritte Plan“ und dem „Projektauftrag mit dem Mattie Roboter“. Beide Konzepte und der Roboter wurden von der TU Wien eigens für Kinder entwickelt. Dabei haben die WisschaftlerInnen zwei Ziele:

1. Das Projekt soll SchülerInnen, LehrerInnen und interessierten Eltern einen Einblick in die Robotik bieten und dabei verschiedene Perspektiven aufzeigen, z.B. nicht nur die technische, sondern auch sozialwissenschaftliche oder wirtschaftliche Perspektiven. Weiters sollen Kinder herausfinden wie ihre Interessen und persönlichen Stärken in der Robotik zum Einsatz kommen können.
2. Nebenbei soll das Projekt auch die Wirksamkeit des Konzeptes und, wenn gegeben, die Umsetzbarkeit der Ideen der Kinder in reale Produkte oder Serviceleistungen in der Robotik untersuchen.

Das Projekt hat mit März 2014 begonnen. Nach einer Planungs- und Entwicklungsphase sowie der Kontaktaufnahme zu den Pilotschulen ist die Umsetzung seit Oktober 2014 in vollem Gange. Fünf AHS aus Wien und Umgebung nehmen mit einer 2. oder 3. Klasse (mit ihren LehrerInnen aus Werken oder Physik) am Projekt teil.

Im Detail schaut das Projekt folgendermaßen aus: Jede Klasse lernt über den Produktentwicklungsprozess eines Roboters in drei Workshops verteilt über ein Schulsemester. Jeder Workshop symbolisiert eine prägnante Phase der Produktentwicklung.

Angefangen wird mit der Ideenphase im ersten Workshop „Konzept“, wo die SchülerInnen mit Hilfe des 5-Schritte Plans – einer Struktur, die ihnen hilft ihre Ideen zu ordnen – einen ersten Roboter entwerfen und ein Modell aus Modelliermasse gestalten.

Im zweiten Workshop „Experten“ besucht die Klasse das Vision for Robotics Lab und lernt Robotikexperten kennen, die ihnen während einer Demo über ihre Arbeit – die Bildverarbeitung – erzählen. Danach bekommen die SchülerInnen einen Projektauftrag der Geschäftsleitung der Schräge Roboter GmbH, um einen ersten Prototypen eines Roboters für Kinder zu bauen. Dabei dürfen sie sich entscheiden, ob sie in die Teams Konstruktion, Mensch-Roboter-Interaktion, Forschung&Entwicklung, Design oder Marketing&Vertrieb gehen.

Im dritten Workshop kommen alle Teams zusammen und die verschiedenen Roboterteile werden zusammengefügt. Anschließend wird der Prototyp aus zwei Perspektiven evaluiert: technisch und benutzerorientiert. Zum Abschluss wird die Produktidee der Geschäftsleitung präsentiert und der Prototyp vorgeführt.

Zwischen den Workshops haben die LehrerInnen die Möglichkeit mit der Klasse die Workshops Revue zu passieren und Herausforderungen oder Enttäuschungen näher zu analysieren.

  08.06.2014
SQUIRREL

Clearing Clutter Bit by Bit

Clutter in an open world is a challenge for many aspects of robotic systems, especially for autonomous robots deployed in unstructured domestic settings, affecting navigation, manipulation, vision, human robot interaction and planning.

Squirrel addresses these issues by actively controlling clutter and incrementally learning to extend the robot’s capabilities while doing so. We term this the B3 (bit by bit) approach, as the robot tackles clutter one bit at a time and also extends its knowledge continuously as new bits of information become available. Squirrel is inspired by a user driven scenario, that exhibits all the rich complexity required to convincingly drive research, but allows tractable solutions with high potential for exploitation. We propose a toy cleaning scenario, where a robot learns to collect toys scattered in loose clumps or tangled heaps on the floor in a child’s room, and to stow them in designated target locations.

We will advance science w.r.t. manipulation, where we will incrementally learn grasp affordances with a dexterous hand; segmenting and learning objects and object category models from a cluttered scene; localisation and navigation in a crowded and changing scene based on incrementally built 3D environment models; iterative task planning in an open world; and engaging with multiple users in a dynamic collaborative task.

Progress will be measured in scenarios of increasing complexity, starting with known object classes, via incremental learning of objects and grasp affordances to the full system with failure recovery and active control of clutter, instantiated on two different robot platforms. Systems will be evaluated in nurseries and day cares, where children playfully engage with the robot to teach it to how to clean up.

Partners

• Technische Universität Wien, Institut für Automatisierungs- und Regelungstechnik
• Albert-Ludwigs-Universität Freiburg
• Universität Innsbruck
• King’s College London
• University of Twente
• Frauenhofer IPA
• Festo Didactic
• IDMind
• Verein Pädagogische Initiative 2-10

Funding

FP7 No. 610532.

  08.06.2014
Argonauts

Argo Challenge von Total

Total has launched in December 2013, the ARGOS Challenge (Autonomous Robot for Gas and Oil Sites), an international robotics competition designed to foster the development of a new generation of autonomous robots adapted to the oil and gas sites. These robots will be capable of performing inspection tasks, detecting anomalies and intervening in emergency situations.

In June 2014, five teams from Austria, Spain, France, Japan and Switzerland were selected to take part in the ARGOS challenge. They have less than three years to design and build the first autonomous surface robot complying with ATEX/ IECEx standards*. The robot will be able to operate in specific environments encountered in the oil and gas industry.

By launching this challenge in partnership with the French National Research Agency (ANR), Total has adopted an open innovation strategy. The aim was to involve associations in robotics, partly to make them more aware of the operating constraints encountered in oil and gas production activities, and partly to encourage them to suggest innovative robotics solutions, providing answers to the problems we encounter, and increasing safety for our personnel.

Partners

5 teams Argonauts, Foxiris, Vikings, Air-K and Lio and come from Austria, Spain, France, Japan and Switzerland

Funding

Total Challenge operated by ANR (Total) and EuroSTAR

  14.07.2013
FRANC

Field Robot for Advanced Navigation in bio Crops

Während in der modernen Landwirtschaft zunehmend leistungsfähige komplexe Maschinen mit hochentwickelter Technologie eingesetzt werden, ist der Biolandbau vielfach von manuellen Arbeiten geprägt. Im Projekt FRANC wird ein autonomes Fahrzeug entwickelt und gebaut, welches speziell im Biolandbau eingesetzt werden kann. Das Fahrzeug wird mit der nötigen Antriebs- und Sensortechnik sowie Steuerungshardware und -software ausgestattet um selbständig durch Reihenkulturen fahren zu können. Das Fahrzeug wird vollständig elektrisch angetrieben. Durch lenkbare Vorder- und Hinterachsen werden enge Wenderadien ermöglichen. Ein modularer Aufbau des Fahrzeugs soll eine leichte Adaption an das Arbeitsumfeld ermöglichen.

Um zu gewährleisten, dass das Fahrzeug bei Kollisionsgefahr unmittelbar und verzögerungsfrei zum Stehen gebracht und in einen sicheren Betriebszustand versetzt werden kann, wird ein eigenes Schutzkonzept entwickelt. Im Hinblick auf die Sicherheitstechnik wird davon ausgegangen, dass das Fahrzeug vorerst nicht unbeaufsichtigt eingesetzt wird. Der Feldroboter soll mittels Fernsteuerung bedient werden können, die jederzeit einen Eingriff in die Fahrzeugsteuerung erlaubt.

Mit diesem Projekt wird die Schulausbildung an eine sehr bedeutende technologische Entwicklung in der Landtechnik herangeführt. Dabei soll vor allem das Interesse der Schüler an der Robotik geweckt werden. Der Einsatz moderner Technologien (Sensortechnik, Navigation, Antriebstechnik, Steuerungstechnik, etc.) kann sehr anschaulich vermittelt werden. Das Projekt bietet weiter ein großes Forschungspotenzial: Der Trend in der Entwicklung geht hin zur individuellen Erkennung und Behandlung einzelner Pflanzen. Damit sind Aufgabenstellungen verbunden, die weit über das Projektziel hinausreichen und es wird damit die Basis für eine zukünftige und langjährige Zusammenarbeit mit den Projektpartnern darstellen.

Projektpartner

• Technische Universität Wien, Institut für Automatisierungs- und Regelungstechnik
• Josephinum Research
• Hochschule Osnabrück, Fakultät Ingenieurwissenschaften und Informatik
• Bio Lutz GmbH
• BLT Wieslburg
• Höhere Bundeslehr- und Forschungsanstalt Francisco Josephinum
• Höhere Technische Bundeslehr- und Versuchsanstalt Waidhofen an der Ybbs

Funding

FRANC wird gefördert durch Sparkling Science, einem Forschungsprogramm des Bundesministeriums für Wissenschaft und Forschung.

  09.06.2013
STRANDS

Spatio-Temporal Representations and Activities for Cognitive Control in Long-Term Scenarios

STRANDS aims to enable a robot to achieve robust and intelligent behaviour in human environments through adaptation to, and the exploitation of, long-term experience. Our approach is based on understanding 3D space and how it changes over time, from milliseconds to months.

We will develop novel approaches to extract quantitative and qualitative spatio-temporal structure from sensor data gathered during months of autonomous operation. Extracted structure will include reoccurring geometric primitives, objects, people, and models of activity. We will also develop control mechanisms which exploit these structures to yield adaptive behaviour in highly demanding, real-world security and care scenarios.

The spatio-temporal dynamics presented by such scenarios (e.g. humans moving, furniture changing position, objects (re-)appearing) are largely treated as anomalous readings by state-of-the-art robots. Errors introduced by these readings accumulate over the lifetime of such systems, preventing many of them from running for more than a few hours. By autonomously modelling spatio-temporal dynamics, our robots will be able run for significantly longer than current systems (at least 120 days by the end of the project). Long runtimes provide previously unattainable opportunities for a robot to learn about its world. Our systems will take these opportunities, advancing long-term mapping, life-long learning about objects, person tracking, human activity recognition and self-motivated behaviour generation.

We will integrate our advances into complete cognitive systems to be deployed and evaluated at two end-user sites. The tasks these systems will perform are impossible without long-term adaptation to spatio-temporal dynamics, yet they are tasks demanded by early adopters of cognitive robots. We will measure our progress by benchmarking these systems against detailed user requirements and a range of objective criteria including measures of system runtime and autonomous behaviour.

Partners

• Technische Universität Wien, Institut für Automatisierungs- und Regelungstechnik
• University of Birmingham
• Akademie für Altersforschung am Haus der Barmherzigkeit
• G4S Technology Ltd
• Kungliga Tekniska Högskolan
• Rheinisch-Westfäische Technische Hochschule Aachen
• University of Leeds
• University of Lincoln

Funding

FP7 no. 600623

  01.01.2013
V4HRC

Human-Robot Cooperation: Perspective Sharing

Imagine a human and a robot performing a joint assembly task such as assembling a shelf. This task clearly requires a number of sequential or parallel actions and visual information about the context to be negotiated and performed in coordination by the partners.

However, human vision and machine vision differ. On one hand, computer vision systems are precise, achieve repeatable results, and are able to perceive wavelengths invisible to humans. On the other hand, sense-making of a picture or scenery can be considered a typical human trait. So how should the cooperation in a vision-based task (e.g. building something together out of Lego bricks) work for a human-robot team, if they do not have a common perception of the world?

There is a need for grounding in human-robot cooperation. In order to achieve this we have to combine the strengths of human beings (e.g. problem solving, sense making, and the ability to make decisions) with the strengths of robotics (e.g. omnivisual cameras, consistency of vision measures, and storage of vision data).

Therefore, the aim is to explore how human dyads cooperate in vision-based tasks and how they achieve grounding. The findings from human dyad will then be transferred in an adapted manner to human-robot interaction in order to inform the behavior implementation of the robot. Human and machine vision will be bridged by letting the human “see through the robot’s eyes” at identified moments, which could increase the collaboration performance. User studies using the Wizard-of-Oz technique (the robot is not acting autonomously, but is remote-controlled by a “wizard” behind the scenes) will be conducted and assessed in terms of user satisfaction. The results of human-human dyads and human-robot teams will be compared regarding performance and quality criteria (usability, user experience, and social acceptance), in order to gain an understanding of what makes human-robot cooperation perceived as satisfying for the user. As there is evidence in Human-Robot Interaction research that the cultural-background of the participants and the embodiment of the robot can influence the perception and performance of human-robot collaboration, comparison studies in the USA an Japan will be conducted to explore if this holds true for vision-based cooperation tasks in the final stage of the research undertaking. With this approach, it can be systematically explored how grounding in human-robot vision can be achieved. As such, the research proposed in this project is vital for future robotic vision projects where it is expected that robots share an environment and have to jointly perform tasks. The project follows a highly interdisciplinary approach and brings together research aspects from sociology, computer science, cognitive science, and robotics.

  14.07.2011
HOBBIT

The Mutual Care Robot

Ageing has been prioritised as a key demographic element affecting the population development within the EU member states. Experts and users agree that Ambient Assisted Living (AAL) and Social and Service Robots (SSR) have the potential to become key components in coping with Europe’s demographic changes in the coming years. From all past experiences with service robots, it is evident that acceptance, usability and affordability will be the prime factors for any successful introduction of such technology into the homes of older people.

While world players in home care robotics tend to follow a pragmatic approach such as single function systems (USA) or humanoid robots (Japan, Korea), we introduce a new, more user-centred concept called “Mutual Care”: By providing a possibility for the Human to “take care” of the robot like a partner, real feelings and affections toward it will be created. It is easier to accept assistance from a robot when in certain situations, the Human can also assist the machine. In turn, older users will more readily accept the help of the HOBBIT robot. Close cooperation with institutional caregivers will enable the consortium to continuously improve acceptance and usability.

In contrast to current approaches, HOBBIT, the mutual care robot, will offer practical and tangible benefits for the user with a price tag starting below EUR 14.000 . This offers the realistic chance for HOBBIT to refinance itself in about 18-24 months (in comparison with nursing institutions or 24hr home care). In addition, HOBBIT has the potential to delay institutionalisation of older persons by at least two years which will result in a general strengthening of the competitiveness of the European economy. We will insure that the concept of HOBBIT seeds a new robotic industry segment for aging well in the European Union. The use of standardised industrial components and the participation of two leading industrial partners will ensure the exploitation of HOBBIT.

  26.07.2008
Meta Mechanics

The metamechanics RoboCup@Home team was established in late 2008 at the TU Wien. It is a mixed team of the Faculty of Electrical Engineering and Information Technology and the Department of Computer Science. In 2009 the metamechanics plan to participate in Graz (World Cup) and German Open 2009 for the first time.

The team consists of a mixture of Bachelor, Master and PhD students, which are advised by professors from the university.

  14.07.2008
GRASP

Emergence of Cognitive Grasping through Emulation, Introspection, and Surprise

The aim of GRASP is the design of a cognitive system capable of performing tasks in open-ended environments, dealing with uncertainty and novel situations. The design of such a system must take into account three important facts: i) it has to be based on solid theoretical basis, and ii) it has to be extensively evaluated on suitable and measurable basis, thus iii) allowing for self-understanding and self-extension.

We have decided to study the problem of object manipulation and grasping, by providing theoretical and measurable basis for system design that are valid in both human and artificial systems. We believe that this is of utmost importance for the design of artificial cognitive systems that are to be deployed in real environments and interact with humans and other artificial agents. Such systems need the ability to exploit the innate knowledge and self-understanding to gradually develop cognitive capabilities. To demonstrate the feasibility of our approach, we will instantiate, implement and evaluate our theories on robot systems with different emobodiments and levels of complexity. These systems will operate in real-world scenarios, with and without human intervention and tutoring.

GRASP will develop means for robotic systems to reason about graspable targets, to explore and investigate their physical properties and finally to make artificial hands grasp any object. We will use theoretical, computational and experimental studies to model skilled sensorimotor behavior based on known principles governing grasping and manipulation tasks performed by humans. Therefore, GRASP sets out to integrate a large body of findings from disciplines such as neuroscience, cognitive science, robotics, multi-modal perception and machine learning to achieve a core capability: Grasping any object by building up relations between task setting, embodied hand actions, object attributes, and contextual knowledge.

Goals

Develop computer vision methods to detect grasping points on any objects to grasp any object. At project end we want to show that a basket filled with everyday objects can be emptied by the robot, even if it has never seen some of the objects before. Hence it is necessary to develop the vision methods as well as link percepts to motor commands via an ontology that represents the grasping knowledge relating object properties such as shape, size, and orientation to hand grasp types and posture and the relation to the task.

Our (TUW) tasks/goals in this project are:

• [Task1] – Acquiring (perceiving, formalising) knowledge through hand-environment interaction:
  The objective is to combine expectations from previous grasping experiences with the actual percepts of the present and actual grasping action. Hence we investigate a plethora of cues and features to be able to extract the set of relevant cues related to the grasping task. We will study edge structure features and grouping to objects, surface reconstruction and tracking, figure/ground segmentation, shape from edge and surfaces, recognition/classification of objects, spatio-temporal and pose relations handobject, multimodal grounding and uncertainties of geometric attributes leading to low level surprise detection and the integration or synthesis in the ontology including the combination with prediction (TUM, TUW).
• [Task2] – Perceiving task relations and affordances: The objective is to exploit the set of features extracted in Task 4.1 to obtain a vocabulary of features relevant to the grasping of objects and to learn the feature relations to the potential grasping behaviours and types. These relations will form part of the grasping ontology. Furthermore, the goal is to obtain a hierarchical structure or abstraction of features, such that new objects can be related to this hierarchy. The approach sets out to obtain an asymptotic behaviour for new objects, such that early on extensions are frequently necessary, while over the course of learning more and more objects are known how to be grasped. Finally, the features will be used to propose potential actions (affordances) and are used to invoke the grasping cycle.
• [Task3] – Linking structure, affordance, action and task: The objective is to provide the necessary input to the grasping ontology, which holds in a relational graph or database the grasping experiences learned. It contains an abstraction formed over specific behaviours and sub-parts of reaching and grasping actions. It models relations and constraints to (1) the object and its properties such as size, shape and weight, to (2) perceived affordances (potentialities for actions) and grasping points, to (3) the task that is executed, e.g., grasping for pick up or to move as cup, and to (4) the context or surrounding of relevance, e.g., obstacles to circumnavigate or surfaces to place the object. It will be investigated how such a link can be efficiently established, how the plasticity of the link can be achieved to enable learning and multiple cross-references, and how this can form a hierarchy of behaviours and links to efficiently represent different grasp types/relations exploiting the vocabulary to achieve extendibility to grasp new objects.

Partners

• Kungliga Tekniska Högskolan, Stockholm, Sweden
• Universität Karlsruhe, Karlsruhe, Germany
• Technische Universität München, Munich, Germany
• Lappeenranta University of Technology, Lappeenranta, Finland
• Foundation for Research and Technology – Hellas, Greece
• Universitat Jaume I, Castellón, Spain
• Otto Bock, GmbH, Austria OB

  14.07.2008
Austrian Kangaroos

Wien hat ein neues Fußballteam

Seit Beginn des Jahres arbeiten Wissenschaftler gemeinsam mit Studenten am ersten humanoiden Roboterfußballteam Wiens, den „Austrian-Kangaroos“. Das Institut für Automatisierungs- und Regelungstechnik und jenes für Computersprachen (COMPLANG) der Technischen Universität Wien, sowie das Institut für Informatik der FH Technikum Wien unterstützen hierbei. Um heuer erstmalig am RoboCup, der Weltmeisterschaft im Roboterfussball (29.06.-05.07. in Graz), teilnehmen zu können entwickelt das ca. zehnköpfige Team unter der Leitung von Markus Bader, Dietmar Schreiner und Alexander Hofmann mit Hochdruck an wettbewerbsfähigen Algorithmen aus den Bereichen Robotik und Künstliche Intelligenz.
Die kleinen Kicker namens NAO (60cm groß, 5kg schwer) sind standardisierte, humanoide Roboter des französischen Herstellers Aldebaran, deren individuelle Fähigkeiten und Verhalten durch die jeweiligen Teams entwickelt werden. Zur WM 2009 muss ein Team aus 3 Kickern autonom und ohne jegliche externe Unterstützung auf Torjagd gehen.

Roboterfussball hat einen hohen Unterhaltungswert, ist aber in Wirklichkeit eine ernsthafte Testumgebung für Forschung und Entwicklung in allen Bereichen. Die standardisierten humanoiden Roboter bieten eine ideale Entwicklungsplattform, die an zahlreichen internationalen Universitäten genutzt wird. So wird neben neuartigen Geh-Algorithmen und Künstlicher Intelligenz auch intensiv an verbesserter Computerbildverarbeitung und im Bereich echtzeitfähiger hochparalleler Softwarearchitekturen für Embedded Systems geforscht.

Ausgeklügelte Geh-Algorithmen lassen den Roboter im Eilschritt sicher über den unebenen Rasenteppich balancieren, wobei „echtes Laufen“ eines der angestrebten Fernziele ist. In der Bildverarbeitung muss mit veränderlichen Lichtverhältnissen und geringer Rechenleistung im Robotergehirn umgegangen werden, um den Fußball, die Mitspieler, die Gegner und die Tore zu erkennen. In der KI wird am Zusammenspiel von Reflexen, einfachen bewussten Verhalten und höheren Spielstrategien geforscht. Auf dem Weg zum Ball muss sich der kleine Kicker aller Mitspieler bewusst sein und diesen gegebenenfalls ausweichen um kein Foul zu begehen, sonst zückt der Schiedsrichter die rote Karte. Zu guter Letzt müssen die NAOs ihre vergebenen Rollen im Team wahrnehmen. So gibt es auch hier Tormann, Stürmer und Verteidiger, die nur in gutem Zusammenspiel siegreich sein werden.