Intelligent and Interactive Systems

User Tools

Site Tools


start

Differences

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

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
start [2021/08/06 20:13]
Justus Piater
start [2025/07/16 06:25] (current)
IIS Webadmin
Line 12: Line 12:
 ===== Working With Us ===== ===== Working With Us =====
   * Check our thesis topics for [[theses/​start|Bachelor and Master students]].   * Check our thesis topics for [[theses/​start|Bachelor and Master students]].
-  * [[https://​ellis.eu/​|ELLIS]] PhD Program: [[https://​ellis.eu/​news/​ellis-phd-program-call-for-applications-deadline-november-15-2021|Call for Applications]]+ 
 +<​html><​!--We currently have [[jobs|one open PhD position]].--></​html>​
  
 <​html><​!-- <​html><​!--
Line 22: Line 23:
 </​html>​ </​html>​
  
- +{{ ::iis_retreat_2024.jpg?direct&​900 ​|}}\\ 
-{{::dsc_0052.jpg?640|Group Picture}}\\ +<​html>​ 
-Group picture taken at our retreat ​in Obergurgl +<div style="​text-align:​ center;">​ 
 +  <p>Group picture taken at our 2024 retreat ​at Meissner Haus.</​p>​ 
 +</​div>​ 
 +</​html>​
  
 ===== News ===== ===== News =====
  
-<​HTML><​table><​tr valign="​top"><​td>​2021-03-24</​td><​td>​Justus Piater gives an invited ​lecture ​<i>Machine Learning, Perception, And Abstract Concepts</i> at Invited lecture ​at Ontario Tech UCanada, online. <span class="​actions"><​a href="​javascript:​void(0)"​ onclick="​showHide('​newsitem0',​ '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="​newsitem0Abstract"​ style="​display:​none">​With every spectacular achievement ​of a machine learning +<​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 
-    system, the long-elusive AI breakthrough ​is popularly proclaimed +    understanding</i> at <a href="​https://​www.uibk.ac.at/​en/​congress/​multibody2025/">​The 
-    ​to be just around the corner Most recent successes have been due +    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 
-    ​in large part to massive data and computation, in particular using +    ​limited by their lack of understanding of their environmentFor 
-    ​deep artificial neural networks ​But ​can artificial cognition +    ​this reasonmost robots operate ​in controlled environments. 
-    ​really be achieved just by further scaling up existing +    ​Machine learning can circumvent modeling problems but introduces 
-    machine-learning ​techniques?  ​I discuss examples of simple+    new problems of generalizing from examplesHow can robots acquire 
-    ​perceptual problems that are easily solved by humans but very +    ​understanding (of structure, function, causality, etc.) that 
-    ​difficult for today'​s machine ​learning ​methods. ​ These problems +    allows them to generalize from sparse experience? Motivated ​by 
-    ​reflect how humans conceptualize their world Their mastery ​is +    ​shortcomings of current ​machine-learning ​methods, ​will argue 
-    thus likely ​to be an essential prerequisite for autonomous robots +    that &​quot;​understanding&​quot;​ is a meaningful notion in AI that reaches 
-    ​to attain higher levels of cognitive abilities. ​ To get therea +    beyond prediction and control. I will discuss examples of our 
-    ​few core issues can be identified that should drive research in +    recent work on learning visual relational conceptsextrapolation 
-    cognitive robotics.</​blockquote></​td></​tr><​tr valign="​top"><​td>​2021-01-28</​td><​td>​Matteo Saveriano gives an invited talk <i>Making robots to learn from human observation?​</i> at <a href="​https://​www.bmeia.gv.at/en/​austrian-embassy-ottawa/​news/events/detail/​article/​showcasing-young-austrian-scholars-and-scientists-an-original-seven-part-virtual-lectures-ser/">​Showcasing Young Austrian Scholars and Scientists, Austrian cultural forum, Ottawa</​a>, ​online.</​td></​tr><​tr valign="​top"><​td>​2021-01-14</​td><​td>​Matteo Saveriano ​gives an invited talk <i>Hierarchical action decomposition ​and motion learning ​for the execution of manipulation tasks</i> at <a href="http://www.gmar.at/aktuell/">Hello Tyrol calling! Robotics Talk onlineGMAR, Innsbruck</​a>, ​online.</​td></​tr><​tr valign="​top"><​td>​2020-11-19</​td><​td>​Justus Piater ​gives an invited ​talk <i>Machine Learning in Robotics</​i>​ at <a href="​https://​baiome.org/">​bAIome PI Talk, Center for +    ​of learned movements beyond the training distribution,​ learning of 
-    Biomedical AI, University Medical Center Hamburg-Eppendorf<​/a>, online. <span class="​actions"><a href="​javascript:​void(0)" onclick="​showHide('​newsitem4',​ '​Abstract'​)">​[Abstract]</a></​span><​blockquote id="​newsitem4Abstract"​ style="​display:​none">​Machine Learning increasingly equips robots with +    ​symbolic concepts and rules, and structure-driven skill learning 
-    learning capabilities and flexibility. ​ This will enable them to +    ​from sensorimotor experienceOur long-term objective ​is to 
-    act purposefully in unstructured environments and to react to +    ​improve abstractiongeneralization,​ robustness, and ultimately 
-    unforeseen events. ​ People can teach them intuitively to perform +    ​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:​ 
-    tasks instead of having to program them in painstaking ways. +    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 MedienBil­dung 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 tutorial ​<i>Was sind Roboter, was macht eine KI? Entwickle deine eigene KI und programmiere unsere Minibots</i> at Campustag BG/BRG SillgasseUniversität 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 
-    Robots can learn from experience and can improve their behavior +    Seminar: AI in Law and Practice: Regional Perspectives on European 
-    over time.  In this talk I will give an overview of methods, +    ​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 späterHallo KI, hilfst du 
-    opportunities,​ and challenges of machine learning in +    ​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&​quot;​ bezeichnet derzeit Systeme, die 
-    robotics.</​blockquote>​</​td></​tr><​tr valign="​top"><​td>​2020-11-20</​td><​td>​Simon Haller-Seeber and Patrick Lamprecht present ​show <i>Explainable AI: A sneak peek into the Black-Box</i> at <a href="​https:​//​youtube.com/​watch?​v=4NVfPwdLnCg&​amp;​t=17m43s">​Science Slam</​a>​online.</​td></​tr><​tr valign="​top"><​td>​2020-09-30</​td><​td>​Erwan Renaudo contributes a talk <i>ROSSINI: RobOt kidS deSIgn thiNkIng</i> at <a href="​https://​www.springer.com/gp/book/9783030674106">Robotics ​in  +    ​auf maschinellem Lernen ​(MLbasierenDieser Workshop führt in 
-    ​Education 2020</​a>, ​online.</​td></​tr><​tr valign="​top"><​td>​2020-06-22</​td><​td>​Justus Piater ​gives an invited talk <i>Conditional Neural Movement Primitives</i> at <a href="​http://​www.gdr-isis.fr/​index.php?​page=reunion&​amp;​idreunion=424">​GdR +    ​die Grundlagen des ML einmit besonderem Augenmerk auf neuronale 
-    ​ISIS Réunion Apprentissage et Robotique</​a>​online. <span class="​actions"><​a href="​javascript:​void(0)"​ onclick="​showHide('​newsitem7', '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="newsitem7Abstract" style="​display:​none">​Conditional Neural Movement Primitives (CNMP) constitute +    ​Netzeder derzeit populärsten ML-TechnologieDarauf aufbauend 
-    ​a novel framework for robot programming by demonstration based on +    ​vermittelt er ein Grundverständnis für prinzipielle Möglichkeiten 
-    Conditional Neural Processes ​(CNP).  Like Bayesian methods such as +    ​und Grenzen von ML und warum es mit derzeitigen Mitteln extrem 
-    ​Gaussian Processes (GP)CNP learn how target distributions depend +    ​schwierig istDiskriminierung ​in KI-Systemen zu 
-    ​on dataand can be conditioned on specific data points to infer +    ​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 
-    new target distributions at test time ​Unlike GP that are +    ​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 
-    ​expensive to train and scale poorly to high dimensions, CNP are +    flexibility and robustness ​of autonomous robots to the next level? 
-    ​neural networks and are trained by gradient descent. ​ CNMP +    I argue that current AI methods ​are unlikely to get there, no 
-    ​leverage CNP to represent motion trajectories that can be +    ​matter how far we scale them up. Robots need to be able to 
-    conditionedat test time, on task paramters such as goal +    &​quot;​understand&​quot;​ their environment ​in ways that reach beyond 
-    locations, via points, and/or force readings. ​ Moreover, CNMP are +    ​prediction and control. I will discuss examples ​of work (ours and 
-    conditioned on sensor readings during execution, resulting ​in +    ​others'​) on learning visual relational conceptsextrapolation of 
-    ​robust, reactive behavior. ​ This talk will present an overview of +    ​learned movements beyond the training distribution,​ learning ​of 
-    how CNMP work and how they can be used in various robot +    symbolic concepts and rules, and structure-driven skill learning 
-    applications.</​blockquote></​td></​tr><​tr valign="​top"><​td>​2020-06-03</​td><​td>​Justus Piater appears ​in the media: Wie der Roboter denken lernt.</​td></​tr><​tr valign="​top"><​td>​2020-01-29</​td><​td>​Justus Piater gives an invited ​talk <i>Digital Science</i> at <a href="​https://​www.graduateacademy.uni-heidelberg.de/karriere/veranstaltungsreihen.html">Vortragsreihe +    from sensorimotor experience.</blockquote></​td></​tr></​table></​HTML>​
-    ​„Primers for Predocs – Strategien für eine erfolgreiche +
-    Promotion“</​a>, ​Universität Heidelberg. <span class="​actions"><​a href="​javascript:​void(0)"​ onclick="​showHide('​newsitem10', '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="newsitem10Abstract" style="​display:​none">​Massive availability ​of data and computing power are +
-    ​promoting data-driven methods ​in all areas of science and +
-    ​technology I will describe how the University ​of Innsbruck +
-    ​supports this via its new Digital Science Centerand will give a +
-    ​flavor ​of machine learning for data analysis.</​blockquote></​td></​tr><​tr valign="​top"><​td>​2020-01-20</​td><​td>​Joanna Chimiak-Opoka,​ Carina König, and Justus Piater appear in the media: <a href="​https://​www.uibk.ac.at/​newsroom/​ergaenzung-digital-science-erfolgreich-gestartet.html.de">​Ergänzung Digital Science erfolgreich gestartet – UIBK Newsroom</a>.</​td></​tr></​table></​HTML>​+
  
 [[news|Older News]] [[news|Older News]]
Line 85: Line 82:
 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 and Privacy Notice]]. **Legal Notice:** See the [[:​impressum|Impress and Privacy Notice]].
start.1628273612.txt.gz · Last modified: 2021/08/06 20:13 by Justus Piater