Intelligent and Interactive Systems

User Tools

Site Tools



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 [2021/03/31 12:52]
Matteo Saveriano
start [2022/05/20 06:25] (current)
IIS Webadmin
Line 11: Line 11:
 ===== Working With Us ===== ===== Working With Us =====
 +  * We are hiring [[jobs|two doctoral students]] in machine learning for computer vision or robotics.
   * Check our thesis topics for [[theses/​start|Bachelor and Master students]].   * Check our thesis topics for [[theses/​start|Bachelor and Master students]].
-  ​* [[https://​​|ELLIS]] PhD Program: [[https://​​news/​ellis-phd-program-call-for-applications|Call for Applications]]+ <​html><​!-- 
 + * [[https://​​|ELLIS]] PhD Program: [[https://​​news/​ellis-phd-program-call-for-applications-deadline-november-15-2021|Call for Applications]] 
 <​html><​!-- <​html><​!--
Line 29: Line 32:
 ===== 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 U, Canada, 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 machine learning +<​HTML><​table><​tr valign="​top"><​td>​2022-06-02</​td><​td>​Erwan Renaudo contributes a talk <i>Deep Learning ​for Fast Segmentation of E-waste Devices’  
-    ​system, the long-elusive AI breakthrough ​is popularly proclaimed +    Inner Parts in a Recycling Scenario</i> at <a href="​https://​">​ICPRAI 2022</​a>​Paris/online. <span class="​actions"><​a href="​javascript:​void(0)"​ onclick="​showHide('​newsitem0',​ '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="​newsitem0Abstract"​ style="​display:​none">​Recycling obsolete electronic devices (E-waste) is 
-    ​to be just around ​the corner Most recent successes have been due +    ​dangerous task for human workers. Automated E-waste recycling  
-    ​in large part to massive data and computation, in particular using +    ​is an area of great interest but challenging for current robotic ​ 
-    ​deep artificial neural networks. ​ But can artificial cognition +    ​applications. We focus on the problem of segmenting inner parts  
-    ​really be achieved just by further scaling up existing +    of E-waste devices into manipulable elementsFirst, we extend ​ 
-    ​machine-learning techniques? ​ I discuss examples ​of simple+    ​a dataset of hard-drive disk (HDD) components with labelled  
-    ​perceptual problems ​that are easily solved by humans but very +    occluded ​and non-occluded points of view of the parts, in order  
-    ​difficult for today'​s machine ​learning methods.  These problems +    ​to increase the diversity and the quality of the learning data  
-    ​reflect how humans conceptualize ​their world. ​ Their mastery is +    ​with different angles. We then perform an extensive evaluation ​ 
-    thus likely to be an essential prerequisite ​for autonomous robots +    ​with three different state-of-the-art models, namely CenterMask
-    ​to attain higher levels of cognitive abilities.  ​To get there, a +    ​BlendMask and SOLOv2 (including variants) and two types of  
-    ​few core issues can be identified that should drive research in +    metrics: the average precision as well as the frame rate. Our  
-    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://​">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</iat <a href="http://​​aktuell/​">Hello Tyrol calling! Robotics Talk onlineGMARInnsbruck</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 PI Talk, Center for +    results show that instance segmentation using state-of-the-art ​ 
-    ​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 +    ​deep learning methods ​can precisely detect complex shapes along  
-    learning capabilities and flexibility. ​ This will enable them to +    ​with their boundaries, as well as being suited ​for fast tracking of 
-    act purposefully in unstructured environments and to react to +    ​parts in a robotic recycling system(Rojas et  al. 2022) 
-    ​unforeseen events. ​ People can teach them intuitively ​to perform +    </​blockquote></​td></​tr><​tr valign="​top"><​td>​2022-05-17</​td><​td>​Erwan Renaudo ​gives an invited talk <i>A Brief tour of autonomous ​robots' &​quot;​Cognition&​quot;​</i> at <a href="​https://​​meldungsdetails-ag-mueller/2022/5/17/event/46426-Creating-Agency-and-Cogn/​tx_cal_phpicalendar/">Creating Agency ​and Cognition in Automated Systems: What can we learn from the Octopus? International Hybrid Workshop</​a>, ​Innsbruck. <span class="​actions"​><a href="javascript:​void(0)"​ onclick="​showHide('​newsitem1',​ '​Abstract'​)">[Abstract]</a></span><blockquote id="newsitem1Abstract"​ style="​display:none">In the design of &​quot;​Cognitive Robots&​quot;​ software architectures 
-    tasks instead of having to program ​them in painstaking ways. +    researchers had to face many organizational problems due to  
-    ​Robots can learn from experience ​and can improve their behavior +    the particular nature of robots. Not only should they manage  
-    ​over time.  In this talk I will give an overview of methods+    to achieve complex tasks with long-terms goalsbut they must  
-    ​opportunitiesand challenges of machine learning in +    also be reactive to their surroundings to preserve their environment. 
-    ​robotics.</​blockquote></​td></​tr><​tr valign="​top"><​td>​2020-11-20</​td><​td>​Simon Haller-Seeber and Patrick Lamprecht present a show <i>Explainable AI: A sneak peek into the Black-Box</i> at <a href="​https://​​v=4NVfPwdLnCg&​amp;​t=17m43s">Science Slam</a>, online.</​td></tr+    We will go over several layered control paradigms developed over 
-     +    the history of robotics and see how these can relate to the  
-    <tr valign="​top"><​td>​2020-10-22/23</​td><​td>​Matteo Saveriano, Erwan Renaudo, Antonio Rodríguez-Sánchez,​ and Justus Piater ​organize the </​i> ​<a href="​https://​​hfr2020/"> ​13th International Workshop on Human-Friendly Robotics (HFR 2020)</​a>, ​Innsbruck (online).</​td></​tr>​ +    knowledge about the Octopus'​ brain organization,​ and discuss  
-     +    how the Octopus itself can inspire cognitive robotic research. 
-    ​<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://​​9783030674106">Robotics in  +    ​</blockquote></​td></​tr><​tr valign="​top"><​td>​2022-05-11</​td><​td>​Justus Piater gives an invited talk <i>Robots That Learn Like Humans?</i> at <a href="​https://​​innsbruck">Pint of 
-    ​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://​​index.php?​page=reunion&amp;idreunion=424">​GdR +    ​Science</​a>, ​Innsbruck. <span class="​actions"><​a href="​javascript:​void(0)"​ onclick="​showHide('​newsitem2', '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="newsitem2Abstract" style="​display:​none">​Wouldn'​t it be great to have a helper robot that we can 
-    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 +    ​task with our annoying chores? How would we teach the robot to 
-    ​a novel framework for robot programming by demonstration based on +    ​perform these tasks? Can we build such robots by equipping ​them 
-    Conditional Neural Processes (CNP). ​ Like Bayesian ​methods ​such as +    ​with artificial intelligence?​ We will discuss how human and 
-    ​Gaussian Processes (GP), CNP learn how target distributions depend +    ​machine learning differ and how this impacts what skills
-    on data, and can be conditioned on specific data points ​to infer +    ​including for communicationour helper robot will be able to 
-    new target distributions at test time ​Unlike GP that are +    ​learn.</​blockquote></​td></​tr><​tr valign="​top"><​td>​2022-02-19</​td><​td>​Justus Piater gives an invited talk <i>Learning as a Creative Process in Humans and 
-    ​expensive to train and scale poorly to high dimensions, CNP are +    Machines</i> at <a href="​https://​​ag-mueller/​online-workshop-on-agency-life-and-creativity/">Workshop 
-    ​neural networks and are trained by gradient descent.  ​CNMP +    on “Agency, Life, and Creativity”</a>, online. ​<span class="​actions"><​a href="​javascript:​void(0)"​ onclick="​showHide('​newsitem3',​ '​Abstract'​)">​[Abstract]</a></span><​blockquote id="​newsitem3Abstract"​ style="​display:​none">​Humans constantly engage in creative activity such as 
-    ​leverage CNP to represent motion trajectories that can be +    ​finding explanations,​ improving technology, or solving novel 
-    conditioned, ​at test time, on task paramters such as goal +    ​problems in everyday life. Even imitating other humans, e.g. while 
-    ​locations, via points, ​and/or force readings ​Moreover,​ CNMP are +    learning a new skill, is creative in that the imitator has to 
-    ​conditioned on sensor readings during execution, resulting in +    infer the conceptual structure underlying the observed 
-    robust, reactive behavior. ​ This talk will present ​an overview ​of +    manifestation and to regenerate the latter from the former. In 
-    ​how CNMP work and how they can be used in various robot +    contrast, current AI-enabled agents are unable to generate and 
-    ​applications.</​blockquote></​td></​tr><​tr valign="​top"><​td>​2020-06-03</​td><​td>​Justus Piater ​appears in the mediaWie 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://​">​Vortragsreihe +    draw upon such conceptual structures. Their learning is mostly 
-    „Primers for Predocs – Strategien für eine erfolgreiche +    driven by statistics, and any ability to produce novelty is 
-    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 +    largely limited to trial and error. I will try to characterize 
-    ​promoting data-driven methods in all areas of science and +    this fundamental difference between learning in human and 
-    ​technology. ​ I will describe how the University of Innsbruck +    artificial agents, and will discuss possible technological 
-    supports this via its new Digital Science Center, and will give a +    approaches that might help close this gap.</​blockquote></​td></​tr>​<tr valign="​top"><​td>​2021-11-24</​td><​td>​Justus Piater ​is a panelist at a public discussion on <a href="​https://​">Privacy 
-    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="">Ergänzung Digital ​Science ​erfolgreich gestartet – UIBK Newsroom</​a>​.</​td></​tr></​table></​HTML>​+    in the Digital Age</a>, online. ​(Organized by ELSA Innsbruck)</​td></​tr><​tr valign="​top"><​td>​2021-10-22</​td><​td>​Justus Piater gives an invited ​talk <i>Robotik und KI in der Medizin – nur 
 +    Bedarfserweckung?​</i> at <a href="​https://​">Medical 
 +    ​Update Hall 2021 – Fit für das neue Jahrzehnt</​a>, ​UMIT, Hall in Tirol.</​td></​tr><​tr valign="​top"><​td>​2021-08-26</​td><​td>​Justus Piater ​contributes a talk <i>Digital Science at the University of Innsbruck</i> at Aurora Research Conference Digital Society ​&​amp; ​Global CitizenshipVrije Universiteit Amsterdam. <span class="​actions"><​a href="​javascript:​void(0)"​ onclick="​showHide('​newsitem6', '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="newsitem6Abstract" style="​display:​none">​Growing data processing capacities and progress in 
 +    ​analytical ​methods ​and artificial intelligence are motivating 
 +    ​entire branches of science to raise new questions ​and to develop 
 +    new approachesThis digital transformation requires progressive,​ 
 +    ​interdisciplinary synergies between the computational sciences ​and 
 +    ​all other scientific disciplines.  ​The Digital Science Center 
 +    ​(DiSC) ​at the University of Innsbruck meets this challenge by 
 +    ​integrating ​and promoting digitalisation of scientific research
 +    ​In this talk will present ​some examples ​of interdisciplinary 
 +    ​research by DiSC staff researchers who are experts ​in specific 
 +    ​aspects of digital science.</​blockquote></​td></​tr><​tr valign="​top"><​td>​2021-08-24</​td><​td>​Justus Piater ​contributes a lecture <​i>​Picking and Placing</​i>​ at <a href="​https://​​informatik/​forschung/​gmar-robotics-school-2021.html">​2021 GMAR Summer School</​a>,​ Villa Blanka, Innsbruck.</​td></​tr><​tr valign="​top"><​td>​2021-07-01</​td><​td>​Justus Piater ​and Matteo Saveriano give an invited talk <i>Making Robots Learn to Perceive and Act with Understanding</i> at <a href="​https://​​200894">Workshop 
 +    ​and Open Lab on Field Robotics ​Interdisciplinary aspects ​of 
 +    ​robotics and its applications in outdoor scenarios</a>, NOI Techpark, Bolzano, Italy.</​td></​tr><​tr valign="​top"><​td>​2021-05-26</​td><​td>​Justus Piater ​contributes a talk <​i>​Intelligente und interaktive Systeme</​i>​ at <a href="">GMAR Robotics ​Science 
 +    Talks</a>, online.</​td></​tr></​table></​HTML>​
 [[news|Older News]] [[news|Older News]]
start.1617187965.txt.gz · Last modified: 2021/03/31 12:52 by Matteo Saveriano