This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
start [2015/04/23 08:42] c7031082 [News] |
start [2025/08/29 17:00] (current) Justus Piater |
||
---|---|---|---|
Line 1: | Line 1: | ||
====== Intelligent and Interactive Systems ====== | ====== 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 ===== | ===== 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><!-- | <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> | --></html> | ||
- | Check our thesis topics for [[theses/start|Bachelor and Master students]]. | ||
- | ===== News ===== | + | <html> |
- | * 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! | + | <div style="clear:both"><br></div> |
- | * Emre Ugur is organizing, with Lorenzo Jamone, Yukie Nagai, and Erhan Oztop, a [[http://emreugur.net/ICAR2015-WS-RobotLearning/|Workshop]] on Robot Learning: "Bottom-up and top-down development of robot skills" at [[http://icar2015.org/|ICAR]] in July 2015. | + | </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. | + | |
- | * Our following paper won the **Best Paper Award** at [[http://www.acml2014.jvn.edu.vn/|ACML 2014]]: <html><div class="li CONF" id="Xiong-2014-ACML" title="Xiong-2014-ACML"><p><span class="author"><span class="firstname">Hanchen</span> <span class="surname">Xiong</span></span>, <span class="author"><span class="firstname">Sandor</span> <span class="surname">Szedmak</span></span> <span class="author"><span class="firstname">Justus</span> <span class="surname">Piater</span></span>, <span class="parttitle">Towards Maximum Likelihood: Learning Undirected Graphical Models using Persistent Sequential Monte Carlo. </span> <span class="actions"> <a href="javascript:void(0)" onclick="showHide('Xiong-2014-ACML', 'Abstract')">[Abstract]</a> <a href="javascript:void(0)" onclick="showHide('Xiong-2014-ACML', 'BibTeX')">[BibTeX]</a></span></p></div></html> | + | |
- | * Justus Piater is an **invited speaker** at the workshop on [[http://www.mobilemanipulation.org/rss2014/|Human versus Robot Grasping and Manipulation—How Can We Close the Gap?]] at [[http://www.roboticsconference.org/|RSS]] July 12, 2014, at UC Berkeley. | + | {{ ::iis_retreat_2024.jpg?direct&900 |}}\\ |
- | * Justus Piater is co-organizing the [[http://www.iros2014.org/|IROS]] **[[http://workshops.acin.tuwien.ac.at/clutter2014/|Workshop on Robots in Clutter: Perception and Interaction in Clutter]]** in Chicago, September 18, 2014. | + | <html> |
- | * Antonio Rodriguez-Sanchez is the editor of the special issue on Frontiers in Computational Neuroscience about **[[http://www.frontiersin.org/computational_neuroscience/researchtopics/hierarchical_object_representa/2258|Hierarchical object representations in the visual cortex and computer vision]]**. | + | <div style="text-align: center;"> |
- | * Justus Piater is lecturing on Robot Vision at the **[[http://www.tu-dresden.de/hri-autumn-school|International Autumn School on "Human-Robot-Interaction]]**, November 18th–22nd, 2013, TU Dresden, Germany. | + | <p>Group picture taken at our 2024 retreat at Meissner Haus.</p> |
- | * Emre Ugur is organizing the [[http://www.iros2013.org/|IROS2013]] **[[https://iis.uibk.ac.at/public/emre/IROS2013-NeuroRobotWS/|Workshop on Neuroscience and Robotics: Towards a robot-enabled, neuroscience-guided healthy society]]** in Tokyo, 3 November 2013. | + | |
- | * Our following paper won a **Best Vision Paper Award**: <html><div class="li CONF" id="Teney-2013-CRV" title="Teney-2013-CRV"><p><span class="author"><span class="firstname">Damien</span> <span class="surname">Teney</span></span>, <span class="author"><span class="firstname">Justus</span> <span class="surname">Piater</span></span>, <span class="parttitle">Continuous Pose Estimation in 2D Images at Instance and Category Levels. </span><a href="http://www.computerrobotvision.org/">Tenth Conference on Computer and Robot Vision</a>, <span class="pubdate">2013</span>. <span class="actions"> <a href="/publications#copyright.notice.IEEE" title="IEEE copyright notice">© IEEE</a> <a href="/publications#Teney-2013-CRV">[Link]</a> <a href="https://iis.uibk.ac.at/public/papers/Teney-2013-CRV.pdf">[PDF]</a> <a href="javascript:void(0)" onclick="showHide('Teney-2013-CRV', 'Abstract')">[Abstract]</a> <a href="javascript:void(0)" onclick="showHide('Teney-2013-CRV', 'BibTeX')">[BibTeX]</a></span></p></div></html> | + | |
- | * Justus Piater is co-organizing the [[http://roboticsconference.org/|R:SS]] **[[http://workshops.acin.tuwien.ac.at/clutter2013|Workshop on Robots in Clutter: Preparing Robots for the Real World]]** in Berlin, 27 June 2013. | + | |
- | * Justus Piater is co-organizing the [[http://www.icra2013.org/|ICRA 2013]] **[[http://www.ynl.t.u-tokyo.ac.jp/~takano/ICRA2013WS/|Workshop on Semantics, Identification, and Control of Robot-Human-Environment Interaction]]** in Karlsruhe, 10 May 2013. | + | |
- | * Justus Piater is an **invited speaker** at the [[http://www.icra2013.org/|ICRA 2013]] Workshop on **[[http://covil.sdu.dk/workshop-bootstrapping.htm|Bootstrapping Structural Knowledge from Sensory-motor Experience]]** in Karlsruhe, 6 May 2013. | + | |
- | * **[[http://disi.unitn.it/~sebe/|Nicu Sebe]]**, professor of computer science at the University of Trento, is giving at talk on [[events/2013-04-18-sebe|Human-centered Computing: Challenges and Perspectives]] on **April 18, 2013, at 16:15** in HS D. | + | |
- | * **[[http://bbdl.usc.edu/Francisco.php|Francisco Valero-Cuevas]]**, Professor of biomedical engineering and biokinesiology and physical therapy at the University of Southern California, is giving a talk on [[events/2013-03-14-valero-cuevas|Computational Neuromechanics]] on March 14, 2013, at 16:15 in HS E. | + | |
- | * **[[http://www.cs.rug.nl/~petkov|Nicolai Petkov]]** is visiting %%IIS%% for three days, and is giving a talk on [[http://informatik.uibk.ac.at/index.php/en/kolloquien/243-kolloquium-petkov|Brain-inspired computing vision for machine vision]] on 10 January 2013, 16:15, in HS C. | + | |
- | * Justus Piater and [[@/public/antonio/|Antonio Rodríguez-Sánchez]] are organizing the **[[https://oagm2013.iis.uibk.ac.at/|2013 ÖAGM/AAPR Workshop]]** in Innsbruck. | + | |
- | * %%IIS%% has published a paper in PLoS One: <html><div class="li JOUR" id="RodriguezSanchez-2012-PLoSONE" title="RodriguezSanchez-2012-PLoSONE"><p><span class="author"><span class="firstname">Antonio</span> <span class="surname">Rodríguez-Sánchez</span></span>, <span class="author"><span class="firstname">John</span> <span class="surname">Tsotsos</span></span>, <span class="parttitle">The roles of endstopped and curvature tuned computations in a hierarchical representation of 2D shape. </span>PLoS ONE 7 (8), pp. 1–13, <span class="pubdate">2012</span>. <span class="actions"> <a title="DOI" href="http://dx.doi.org/10.1371/journal.pone.0042058"><img alt="[DOI]" src="doi.png"/></a> <a href="javascript:void(0)" onclick="showHide('RodriguezSanchez-2012-PLoSONE', 'Abstract')">[Abstract]</a> <a href="javascript:void(0)" onclick="showHide('RodriguezSanchez-2012-PLoSONE', 'BibTeX')">[BibTeX]</a></span></p></div></html> | + | |
- | * **[[http://www.cs.ubc.ca/~little/|Jim Little]]** is giving an extended talk on [[events/2012-04-24-little|Finding Objects in Cluttered Scenes for Home Robotics]] on 24 April 2012, 14:15-15:30, in HS D. | + | |
- | * Justus Piater is an **invited speaker** at the [[http://cogsys2012.acin.tuwien.ac.at/|CogSys 2012]] Workshop on **[[http://kovan.ceng.metu.edu.tr/~sinan/DHV/|Deep Hierarchies in Vision]]** in Vienna, 21 February 2012. | + | |
- | * **[[http://vicos.fri.uni-lj.si/alesl/|Ales Leonardis]]** is giving a talk on [[http://informatik.uibk.ac.at/index.php/en/kolloquien/203-kolloquium-leonardis|Combining compositional shape hierarchy and multi-class object taxonomy for efficient object categorisation]] on 1 December 2011, 16:15, in HS C. | + | |
- | * Justus Piater is an **invited speaker** at the **[[http://cmp.felk.cvut.cz/cmp/events/colloquium-2011.10.13/|29th Pattern Recognition and Computer Vision Colloquium]]** in Prague, 13 October 2011. | + | |
- | * **Brian Moore** is giving a talk on [[events/2011-05-25-moore|Transferring grasping skills from humans to robots]] at the Computer Science Department (ICT Building, Seminar Room 1), 25 May 2011, 12.00-13.00. | + | |
- | * Justus Piater is an **invited speaker** at the [[http://www.roboticsconference.org/|R:SS]] Workshop on **[[http://www.willowgarage.com/workshops/2011/rss|Mobile Manipulation: Learning to Manipulate]]** in Los Angeles, 27 June 2011. | + | |
- | * Justus Piater lectures at the **[[http://cogx.eu/|CogX]] 2011 Spring School** in Vienna, 27.4.--5.5. | + | |
- | * **Inaugural Lecture -- //Antrittsvorlesung//** by Justus Piater: 14 April 2011 17:00 in the large auditorium of civil engineering -- //Großer Hörsaal der Fakultät für Bauingenieurwissenschaften//. [[https://iis.uibk.ac.at/public/Antrittsvorlesung_Justus_Piater.pdf|Einladung (Invitation, in German only)]] [[http://streaming.uibk.ac.at/medien/c102/c1021081/j_piater/index.html|Video (in German only)]] | + | |
- | ===== Press ===== | + | |
- | * [[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) | + | |
- | * <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"> | + | |
- | <object width="500" height="281"> | + | |
- | <param name="allowfullscreen" value="true" /> | + | |
- | <param name="allowscriptaccess" value="always" /> | + | |
- | <param name="movie" value="https://vimeo.com/moogaloop.swf?clip_id=113292313&color=878787&force_embed=vimeo.com&fullscreen=1" /> | + | |
- | <embed src="https://vimeo.com/moogaloop.swf?clip_id=113292313&color=878787&force_embed=vimeo.com&fullscreen=1" type="application/x-shockwave-flash" allowfullscreen="true" allowscriptaccess="always" width="500" height="281"></embed> | + | |
- | </object> | + | |
- | </span></a> | + | |
</div> | </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>2025-07-15</td><td>Justus Piater gives an invited keynote <i>Making robots learn to perceive and act with |
- | display: block; | + | understanding</i> at <a href="https://www.uibk.ac.at/en/congress/multibody2025/">The |
- | } | + | 12th ECCOMAS Thematic Conference on Multibody Dynamics</a>, Innsbruck. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem0', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem0Abstract" style="display:none">The flexibility and robustness of current robots is |
- | </style> | + | limited by their lack of understanding of their environment. For |
- | <div> | + | this reason, most robots operate in controlled environments. |
- | <a href="#raivideo">RAI Südtirol - Tagesschau vom 12 Juli 2014<span id="raivideo"> | + | Machine learning can circumvent modeling problems but introduces |
- | <video width="560" height="340" controls preload="metadata"> | + | new problems of generalizing from examples. How can robots acquire |
- | <source src="/public/videos/RAI_Tagesschau_12-07-2014.ogg" | + | understanding (of structure, function, causality, etc.) that |
- | type='video/ogg; codecs="theora, vorbis"'> | + | allows them to generalize from sparse experience? Motivated by |
- | <applet code="com.fluendo.player.Cortado.class" | + | shortcomings of current machine-learning methods, I will argue |
- | archive="/public/cortado.jar" width="560" height="340"> | + | that "understanding" is a meaningful notion in AI that reaches |
- | <param name="autoPlay" value"false" /> | + | beyond prediction and control. I will discuss examples of our |
- | <param name="url" value="/public/videos/RAI_Tagesschau_12-07-2014.ogg"/> | + | recent work on learning visual relational concepts, extrapolation |
- | </applet> | + | of learned movements beyond the training distribution, learning of |
- | </video> | + | symbolic concepts and rules, and structure-driven skill learning |
- | </span></a> | + | from sensorimotor experience. Our long-term objective is to |
- | </div> | + | 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: | |
- | </div> | + | 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><tr valign="top"><td>2025-04-03</td><td>Justus Piater gives an invited keynote <i>What is AI really?</i> at <a href="https://www.uibk.ac.at/events/2025/04/03/ai-in-law-and-practice-regional-perspectives-on-european-rules">Cross-Border |
- | </HTML> | + | Seminar: AI in Law and Practice: Regional Perspectives on European |
- | * [[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) | + | Rules</a>, Universität Innsbruck.</td></tr><tr valign="top"><td>2025-03-06</td><td>Justus Piater teaches a tutorial <i>Funktionsweise, Möglichkeiten und Grenzen von KI</i> at Lieber gleich berechtigt als später: Hallo KI, hilfst du |
- | * [[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. | + | uns bei der Gleichstellung?!, Tiroler Bildungsinstitut Grillhof Vill. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem6', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem6Abstract" style="display:none">Künstliche Intelligenz" bezeichnet derzeit Systeme, die |
- | * [[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) | + | auf maschinellem Lernen (ML) basieren. Dieser Workshop führt in |
- | * [[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) | + | die Grundlagen des ML ein, mit besonderem Augenmerk auf neuronale |
- | * [[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) | + | Netze, der derzeit populärsten ML-Technologie. Darauf aufbauend |
- | * [[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) | + | vermittelt er ein Grundverständnis für prinzipielle Möglichkeiten |
+ | und Grenzen von ML und warum es mit derzeitigen Mitteln extrem | ||
+ | schwierig ist, Diskriminierung in KI-Systemen zu | ||
+ | verhindern.</blockquote></td></tr><tr valign="top"><td>2025-02-26</td><td>Simon Haller-Seeber and Christopher Kelter teach a tutorial <i>Programmieren eines autonomen Roboters anhand einer selbstentwickelten KI</i> at STAIR-Lab INNALP Workshop für das Gymnasium Ursulinenen Innsbruck, Universität Innsbruck.</td></tr><tr valign="top"><td>2025-02-26</td><td>Marko Zarić teaches a tutorial <i>Einführung in das Programmieren mit Microcontrollern</i> at STAIR-Lab INNALP Workshop für das Gymnasium Ursulinenen Innsbruck, Universität Innsbruck.</td></tr><tr valign="top"><td>2025-01-31</td><td>Justus Piater gives an invited lecture <i>High-Level AI For Autonomous Robots</i> at <a href="https://elias-ai.eu/event/ellis-vismac/">ELIAS-ELLIS-VISMAC | ||
+ | Winter School 2025</a>, Brunico, Italy. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem9', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem9Abstract" style="display:none">What barriers will have to be overcome to raise the | ||
+ | flexibility and robustness of autonomous robots to the next level? | ||
+ | I argue that current AI methods are unlikely to get there, no | ||
+ | matter how far we scale them up. Robots need to be able to | ||
+ | "understand" their environment in ways that reach beyond | ||
+ | prediction and control. I will discuss examples of work (ours and | ||
+ | others') 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.</blockquote></td></tr></table></HTML> | ||
+ | [[news|Older News]] | ||
===== Postal Address ===== | ===== Postal Address ===== | ||
University of Innsbruck\\ | University of Innsbruck\\ | ||
- | Institute of Computer Science\\ | + | Department of Computer Science\\ |
Technikerstr. 21a\\ | Technikerstr. 21a\\ | ||
6020 Innsbruck\\ | 6020 Innsbruck\\ | ||
Austria | 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]]. |