Differences

This shows you the differences between two versions of the page.

--- start [2015/10/29 10:24]
c7031082 [News]
+++ start [2026/05/24 06:25] (current)
IIS Webadmin
@@ Line 1: / Line 1: @@
 ====== Intelligent and Interactive Systems ======
-Research at %%IIS%% is situated at the intersection of computer vision, machine learning and robotics.  Much of our work is motivated by the perceptual needs of autonomous robots, and focuses on visual inference as it serves activity such as grasping.  Other areas of interest include the psychology and biology of perception, and video analysis for applications such as sports or human-computer interaction.
+//**Making robots learn to perceive and act with understanding**//
+At %%IIS%% we enable autonomous robots to perceive and act flexibly and robustly in unstructured environments, leveraging machine learning methods to build perceptual, motor and reasoning skills.
+We seek to answer the question: //How can we enable robots to acquire the knowledge and understanding they require to interact sensibly with unstructured environments? //
+Our research addresses complete perception-action loops, from computer vision to grasping and manipulation, using reactive algorithms and/or cognitive models.  Much of our work uses machine learning to enable robots to synthesize and improve complex and robust sensorimotor behavior with experience. Related areas of interest include human-robot interaction, image and video analysis, and visual neuroscience.
 ===== Working With Us =====
+  * Check our thesis topics for [[theses/start|Bachelor and Master students]].
+  * [[:jobs:#notice_for_non-eueea_prospective_master_students|Notice]] for non-[[https://en.wikipedia.org/wiki/EU|EU]]/[[https://en.wikipedia.org/wiki/European_Economic_Area|EEA]] prospective Master students
+  * We currently do not have any open PhD positions.
+<html><!--We currently have [[jobs|one open PhD position]].--></html>
 <html><!--
-  * We have multiple open positions for [[jobs|doctoral students and postdocs]].
+//Bachelor students://{{ ::mobile-manipulator-crop.jpg?nolink&100|}} **Want to create artificial intelligence for autonomous robots?** Want to join our [[@/uibk/piater/courses/RC_Poster2.pdf |interdisciplinary LFUI team]] to compete in the 2020 [[https://www.robocup.org/leagues/16|RoboCup@Work]] competition? Take the [[https://lfuonline.uibk.ac.at/public/lfuonline_lv.details?sem_id_in=19W&lvnr_id_in=703135|Introduction to Robotics]] course in the winter semester 2019-20!
-  * [[asstprof|Assistant Professor position in computer and biological vision]] (apply by 6 November 2014; earliest starting date 5 January, 2015)
 --></html>
-Check our thesis topics for [[theses/start|Bachelor and Master students]].
-===== News =====
+<html>
-  * Emre Ugur is guest editor of the Special Issue on [[http://robotics-worldwide.1046236.n5.nabble.com/robotics-worldwide-journals-CALL-FOR-PAPERS-IEEE-TRANSACTIONS-ON-COGNITIVE-AND-DEVELOPMENTAL-SYSTEMSs-td5712577.html | Computational Models of Affordances for Cognitive Robots]] in the [[http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=4563672 | IEEE Transactions on Autonomous Mental Development]].
+<div style="clear:both"><br></div>
-  * Justus Piater is an **invited speaker** at the [[http://www.iis.ee.ic.ac.uk/ComputerVision/3DPose-2015.html|1st International Workshop on Recovering 6D Object Pose]], at [[http://pamitc.org/iccv15/|ICCV]] in December 2015.
+</html>
-  * Antonio Rodriguez-Sanchez is organizing, jointly with George Azzopardi (Univ. Malta) a BICT [[http://cmvc.bionetics.org/2015/show/home | workshop on Computer Models of the Visual Cortex]], to be held in New York in December.
-  * Justus Piater is co-organizing **Dagstuhl Seminar** 15411 on [[http://www.dagstuhl.de/15411|Multimodal Manipulation Under Uncertainty]] in October 2015.
-  * Justus Piater is an **invited speaker** at the workshop on [[http://objectaffordances.blogspot.pt/|Learning Object Affordances: A fundamental step to allow prediction, planning and tool use in autonomous robots]], at [[http://www.iros2015.org/|IROS]] in October 2015.
-  * Emre Ugur is co-organizing, with Lorenzo Jamone, Angelo Cangelosi, Tamim Asfour, and Jose Santos-Victor, a workshop on [[http://objectaffordances.blogspot.pt/|Learning Object Affordances: A fundamental step to allow prediction, planning and tool use in autonomous robots]], at [[http://www.iros2015.org/|IROS]] in October 2015.
-  * Justus Piater is an **invited speaker** at the workshop on Robot Learning, [[http://emreugur.net/ICAR2015-WS-RobotLearning/|Bottom-up and top-down development of robot skills]] at [[http://icar2015.org/|ICAR]] in July 2015.
-  * Emre Ugur is organizing, with Lorenzo Jamone, Yukie Nagai, and Erhan Oztop, a workshop on Robot Learning, [[http://emreugur.net/ICAR2015-WS-RobotLearning/|Bottom-up and top-down development of robot skills]] at [[http://icar2015.org/|ICAR]] in July 2015.
-  * Emre Ugur is an **invited speaker** at the workshop on [[https://iis.uibk.ac.at/conferences/lrc2015/|Learning Reusable Concepts in Robotics]] at [[http://www.roboticsconference.org/|RSS]] in July 2015.
-  * Justus Piater is organizing, with Tamim Asfour (KIT), the workshop on [[https://iis.uibk.ac.at/conferences/lrc2015/|Learning Reusable Concepts in Robotics]] at [[http://www.roboticsconference.org/|RSS]] in July 2015. Check our exciting lineup of invited speakers!
-  * Our following paper won the **Best Robotic Vision Paper Award** at [[http://www.computerrobotvision.org|CRV 2015]]: <html><div class="li CONF" id="Rezapour-2015-CRV" title="Rezapour-2015-CRV"><span><span class="author"><span class="firstname">Safoura</span> <span class="surname">Rezapour Lakani</span></span>, <span class="author"><span class="firstname">Mirela</span> <span class="surname">Popa</span></span>, <span class="author"><span class="firstname">Antonio</span> <span class="surname">Rodríguez-Sánchez</span></span>, <span class="author"><span class="firstname">Justus</span> <span class="surname">Piater</span></span>, <span class="parttitle">CPS: 3D Compositional Part Segmentation through Grasping. </span><a href="http://www.computerrobotvision.org/">12th Conference on Computer and Robot Vision</a>, <span class="pubdate">2015</span>. <span class="actions"> <a href="https://iis.uibk.ac.at/public/papers/Rezapour-2015-CRV.pdf">[PDF]</a> <a href="javascript:void(0)" onclick="showHide('Rezapour-2015-CRV', 'Abstract')">[Abstract]</a> <a href="javascript:void(0)" onclick="showHide('Rezapour-2015-CRV', 'BibTeX')">[BibTeX]</a></span></span></div></html>
-  * Justus Piater is an **invited speaker** at the workshop on [[http://www.rhgm.org/activities/workshopicra15/|Robotic Hands, Grasping, and Manipulation]] May 30, 2015, at [[http://www.icra2015.org/|ICRA 2015]] in Seattle.
-[[news|Older News]]
+{{ ::iis_retreat_2024.jpg?direct&900 |}}\\
+<html>
-===== Press =====
+<div style="text-align: center;">
-  * [[http://www.uibk.ac.at/ipoint/news/2015/eine-kamera-als-sehhilfe.html.de|Eine Kamera als Sehhilfe]] ([[http://www.uibk.ac.at/ipoint/|iPoint]] 06.02.2015, in German)
+  <p>Group picture taken at our 2024 retreat at Meissner Haus.</p>
-  * <HTML>
-<div class="embedded_video">
-<style type="text/css" scoped>
-#tiroltvvideo {
-  display: none;
-}
-#tiroltvvideo:target {
-  display: block;
-}
-</style>
-<div>
-  <a href="#tiroltvvideo">Robotik an der Uni Innsbruck - TirolTV vom 1 Dezember 2014<span id="tiroltvvideo"><span>
-   <iframe src="https://player.vimeo.com/video/113292313?color=878787" width="500" height="281" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>
-    </span></a>
 </div>
+</html>
-</div>
+===== News =====
-</HTML>
-  * <HTML>
-<div class="embedded_video">
-<style type="text/css" scoped>
-#raivideo {
-  display: none;
-}
-#raivideo:target {
+<HTML><table><tr valign="top"><td>2026-05-07</td><td>Justus Piater is a panelist at a public discussion on <a href="https://www.uibk.ac.at/de/medien-kommunikation/kommunikation/intern/">Invited
-  display: block;
+    expert interview on “Human-robotics relations: What does the
-}
+    future hold?”</a>, Innsbruck. (Public event organized by the Department of Media, Society and Communication, Universität Innsbruck)</td></tr><tr valign="top"><td>2026-04-15</td><td>Justus Piater gives an invited talk <i>Some Latest Results in Robot Learning of Structure by
-</style>
+    Interaction</i> at <a href="https://airov.at/2026/workshop/TactileRobotics.html">Austrian
-<div>
+    Robotics Workshop</a>, Leoben. (Annual workshop of the GMAR; at AIRoV 2026)</td></tr><tr valign="top"><td>2026-04-08</td><td>Justus Piater gives an invited talk <i>Generative KI: Funktionsweise, Möglichkeiten und
-  <a href="#raivideo">RAI Südtirol - Tagesschau vom 12 Juli 2014<span id="raivideo">
+    Grenzen</i> at SchulleiterInnen-Tagung „IT-Sicherheit und KI-Einsatz in
-    <video width="560" height="340" controls preload="metadata">
+    der Schule“, Pädagogische Hochschule Tirol. (Veranstaltung für Schulleitungen der Bildungsdirektion für Tirol) <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem2', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem2Abstract" style="display:none">Generative KI-Systeme wie ChatGPT und Midjourney haben
-      <source src="/public/videos/RAI_Tagesschau_12-07-2014.ogg"
+    die Welt im Sturm erobert. Wie können wir sie produktiv nutzen?
-        type='video/ogg; codecs="theora, vorbis"'>
+    Wie können wir mit den Herausforderungen umgehen, die durch sie
-      <applet code="com.fluendo.player.Cortado.class"
+    entstehen? Ich werde diese Fragen von der technischen Seite her
-        archive="/public/cortado.jar" width="560" height="340">
+    angehen und einen Eindruck davon vermitteln, wie diese Systeme
-        <param name="autoPlay" value"false" />
+    funktionieren. Daraus ergeben sich ein realistisches Verständnis
-        <param name="url" value="/public/videos/RAI_Tagesschau_12-07-2014.ogg"/>
+    für ihre Möglichkeiten und Grenzen sowie einige grundlegende
-      </applet>
+    Empfehlungen für den Umgang mit ihnen im Schulbetrieb.</blockquote></td></tr><tr valign="top"><td>2025-11-19</td><td>Justus Piater gives an invited talk <i>Structural Understanding – The Grand Challenge of Robot
-    </video>
+    Learning</i> at <a href="https://elliit.se/news-and-events/focus-period-lund-2025/symposium/">ELLIIT Focus Period Symposium: Robot Learning</a>, Lund University. (The ELLIIT Focus Period Symposium is the highlight of the five-week focus period, during which young international scholars, ELLIIT researchers and other well-established international academics gather in Lund to work together on joint research challenges.) <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem3', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem3Abstract" style="display:none">AI has made great progress in recent years, and the
-    </span></a>
+    sophistication of robots has been rising with costs falling. Yet,
-</div>
+    the capabilities of AI-enabled robots are not keeping pace. I
+    argue that this is due to a lack of structural understanding by
-</div>
+    current AI systems. I will discuss several lines of research in my
-</HTML>
+    lab that seek to enable robots to generalize better and learn
-  * [[http://www.uibk.ac.at/ipoint/blog/1135417.html|Roboter, die von Menschen lernen]] - ([[http://www.uibk.ac.at/ipoint/|iPoint]] 03.01.2014, in German)
+    faster thanks to explicit notions of structure.</blockquote></td></tr><tr valign="top"><td>2025-09-18</td><td>Samuele Tosatto gives an invited keynote <i>Where are all the intelligent robots? A quest for efficiency in reinforcement learning</i> at <a href="https://sarl-plus.github.io/RL-Bootcamp2025/">Reinforcement Learning Bootcamp 2025</a>, Salzburg. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem4', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem4Abstract" style="display:none">As artificial intelligence reshapes our digital world at a breathtaking pace,
-  * [[http://www.uibk.ac.at/ipoint/news/2012/vom-gehirn-lernen.html.en|Learning from the Brain]] - UIBK news 21/11/2012 reports on 2DSIL, a biologically-inspired model of shape representation.
+    a curious question arises: Where are all the real-world, intelligent robots?
-  * [[http://20er.at/|Stille Welt - Gehörlos in Tirol]] - the Tyrolean street newspaper reports on the [[http://www.signspeak.eu/|SignSpeak]] project. ([[http://20er.at/|20er]], pp. 6-7, April 2012, in German)
+    While we have mastered the generation of text, images, and video by leveraging vast web-scale datasets,
-  * [[http://www.uibk.ac.at/public-relations/medien/wissenswert/wissenswert18.pdf|Übersetzungslücken schließen]] - the UIBK supplement to an Austrian newspaper reports on our [[http://www.signspeak.eu/|SignSpeak]] project ([[http://www.uibk.ac.at/public-relations/medien/wissenswert/|wissenswert]] 18 pp. 16-17, February 2012, in German)
+    robotics still faces a fundamental data bottleneck. Reinforcement learning (RL) offers a compelling solution,
-  * [[http://www.uibk.ac.at/ipoint/news/2011/schlaue-roboter-im-haushalt.html.de|Schlaue Roboter im Haushalt]] ([[http://www.uibk.ac.at/ipoint/|iPoint]] 13.04.2011, in German)
+    enabling agents to learn autonomously by collecting their own experience.
-  * [[http://www.uibk.ac.at/forschung/magazin/5/artikel/neuberufung.pdf|Roboter lernen lernen]] ([[http://www.uibk.ac.at/forschung/magazin/|zukunft forschung]] [[http://www.uibk.ac.at/forschung/magazin/5/|2/2010]], in German)
+    However, the path to autonomy is often blocked by the staggering inefficiency of current RL algorithms,
+    which can require millions of trials to master simple tasks. This talk embarks on a quest to tackle this
+    efficiency problem head-on. I will argue that a crucial step toward unlocking the potential of
+    robot learning lies in a two-pronged approach: first, by developing statistically efficient
+    algorithms that can reuse data by leveraging sound off-policy techniques, and second,
+    by designing better action representations for physical, real-world agents.
+    By making our algorithms more efficient and refining their core hypotheses,
+    we can accelerate the journey toward real embodied artificial intelligence.</blockquote></td></tr><tr valign="top"><td>2025-07-15</td><td>Justus Piater gives an invited keynote <i>Making robots learn to perceive and act with
+    understanding</i> at <a href="https://www.uibk.ac.at/en/congress/multibody2025/">The
+th ECCOMAS Thematic Conference on Multibody Dynamics</a>, Innsbruck. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem5', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem5Abstract" style="display:none">The flexibility and robustness of current robots is
+    limited by their lack of understanding of their environment. For
+    this reason, most robots operate in controlled environments.
+    Machine learning can circumvent modeling problems but introduces
+    new problems of generalizing from examples. How can robots acquire
+    understanding (of structure, function, causality, etc.) that
+    allows them to generalize from sparse experience? Motivated by
+    shortcomings of current machine-learning methods, I will argue
+    that &quot;understanding&quot; is a meaningful notion in AI that reaches
+    beyond prediction and control. I will discuss examples of our
+    recent work on learning visual relational concepts, extrapolation
+    of learned movements beyond the training distribution, learning of
+    symbolic concepts and rules, and structure-driven skill learning
+    from sensorimotor experience. Our long-term objective is to
+    improve abstraction, generalization, robustness, and ultimately
+    explainability of robot perception and action.</blockquote></td></tr><tr valign="top"><td>2025-07-11</td><td>Justus Piater and Alejandro Agostini give an invited talk <i>Learning Symbols and Abstractions in Robot Planning</i> at <a href="https://www.unibz.it/en/events/abstraction-language-science-engineering">Abstraction:
+    Language - Science - Engineering</a>, Bolzano. (International Workshop)</td></tr><tr valign="top"><td>2025-04-25</td><td>Simon Haller-Seeber gives an invited talk <i>AI-powered tools for real-time transcription and translation in action: A self-hosted open-source framework for digital spaces.</i> at <a href="https://www.uibk.ac.at/de/medien/veranstaltungen/tagungen/medien-wissen-bildung-2025/">Medien - Wissen - Bildung 2025: Streifzüge an den Nahtstellen von Medien, Bildung und Philosophie</a>, Universität Innsbruck.</td></tr><tr valign="top"><td>2025-04-10</td><td>Simon Haller-Seeber gives an invited keynote <i>Hands-on Approaches to Software, Robotics, and AI: Exploring Experiments and Science in Action</i> at <a href="https://iis.uibk.ac.at/public/simon/ECER-2025/">European Conference on Educational Robotics (ECER 2025)</a>, HTL Anichstrasse.</td></tr><tr valign="top"><td>2025-04-10</td><td>Simon Haller-Seeber and Christopher Kelter teach a tutorial <i>Was sind Roboter, was macht eine KI? Entwickle deine eigene KI und programmiere unsere Minibots</i> at Campustag BG/BRG Sillgasse, Universität Innsbruck.</td></tr></table></HTML>
+[[news|Older News]]
 ===== Postal Address =====
 University of Innsbruck\\
-Institute of Computer Science\\
+Department of Computer Science\\
 Technikerstr. 21a\\
 Innsbruck\\
 Austria
-**How to find us:** See the [[http://informatik.uibk.ac.at/how-to-reach-us/|directions]].
+**How to find us:** See the [[https://www.uibk.ac.at/informatik/kontakt/anfahrt.html.en|directions]].
-**Legal Notice:** See the [[:impressum|Impress]].
+**Legal Notice:** See the [[:impressum|Impress and Privacy Notice]].

User Tools

Site Tools

Differences

Page Tools