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 [2020/11/23 08:52]
IIS Webadmin
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>​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://​​amp;​t=17m43s">Science Slam</​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="​page=reunion&​amp;​idreunion=424">GdR +<​HTML><​table><​tr valign="​top"><​td>​2022-06-02</​td><​td>​Erwan Renaudo contributes ​talk <i>Deep Learning for Fast Segmentation of E-waste Devices’  
-    ISIS Réunion Apprentissage et Robotique</​a>, ​online. <span class="​actions"><​a href="​javascript:​void(0)"​ onclick="​showHide('​newsitem1',​ '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="​newsitem1Abstract"​ style="​display:​none">​Conditional Neural Movement Primitives (CNMP) constitute +    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 a 
-    ​a novel framework for robot programming by demonstration based on +    dangerous task for human workers. Automated E-waste recycling  
-    ​Conditional Neural Processes (CNP) Like Bayesian methods such as +    is an area of great interest but challenging for current robotic  
-    ​Gaussian Processes (GP)CNP learn how target distributions depend +    applications. We focus on the problem of segmenting inner parts  
-    ​on data, and can be conditioned on specific data points ​to infer +    of E-waste devices into manipulable elements. Firstwe extend  
-    new target distributions at test time ​Unlike GP that are +    a dataset of hard-drive disk (HDD) components with labelled  
-    ​expensive to train and scale poorly to high dimensions, CNP are +    occluded and non-occluded points of view of the parts, in order  
-    ​neural networks ​and are trained by gradient descent. ​ CNMP +    to increase the diversity and the quality of the learning data  
-    leverage CNP to represent motion trajectories that can be +    with different anglesWe then perform an extensive evaluation  
-    ​conditioned,​ at test time, on task paramters such as goal +    with three different state-of-the-art models, namely CenterMask,​ 
-    locations, via points, and/or force readings. ​ Moreover, CNMP are +    BlendMask and SOLOv2 (including variants) and two types of  
-    conditioned on sensor readings during execution, resulting in +    metrics: the average precision as well as the frame rate. Our  
-    robust, reactive behavior. ​ This talk will present an overview of +    results show that instance segmentation using state-of-the-art  
-    how CNMP work and how they can be used in various robot +    deep learning methods can precisely detect complex shapes along  
-    ​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://​">Vortragsreihe +    with their boundaries, as well as being suited for fast tracking of 
-    ​„Primers for Predocs – Strategien für eine erfolgreiche +    parts in a robotic recycling system. (Rojas et  al. 2022) 
-    Promotion“</​a>, ​Universität Heidelberg. <span class="​actions"><​a href="​javascript:​void(0)"​ onclick="​showHide('​newsitem4', '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="newsitem4Abstract" style="​display:​none">​Massive availability of data and computing power are +    </​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="​ag-mueller/​aktuelles/​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, ​ 
-    ​promoting data-driven methods in all areas of science and +    ​researchers had to face many organizational problems due to  
-    ​technology. ​ I will describe ​how the University of Innsbruck +    ​the particular nature of robotsNot only should they manage ​ 
-    ​supports ​this via its new Digital Science Centerand will give a +    ​to achieve complex tasks with long-terms goalsbut they must  
-    ​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://​">Ergänzung Digital Science erfolgreich gestartet – UIBK Newsroom</​a>​.<​/td></​tr><​tr valign="top"><​td>2020-01-03</td><td>​Justus Piater gives an invited talk <​i>​Künstliche IntelligenzGrundlagenErfolge+    ​also be reactive ​to their surroundings to preserve their environment
-    ​Herausforderungen</​i>​ at 47Tagung des Innsbrucker Kreises von MoraltheologInnen +    ​We will go over several layered control paradigms developed over 
-    ​und SozialethikerInnenInnsbruck.</​td></​tr><​tr valign="​top"><​td>​2019-12-19</​td><​td>​Justus Piater ​appears in the media: ​<a href="​https://​​70023/​Tirol-heute/​14035670/​Alexa-Siri-Co-Spione-im-eigenen-Haus/​14610743">TV interview by ORF 2 Tirol Heute RedHaus (in German)</​a>​.</​td></​tr><​tr valign="​top"><​td>​2019-12-12</​td><​td>​Justus Piater gives an invited ​lecture ​<i>Too Smart to Be Trusted ​– Do I Even Want to +    ​the history of robotics ​and see how these can relate ​to the  
-    ​Understand My Robot?</i> at <a href="">TrustRobots Lecture series +    ​knowledge about the Octopus'​ brain organization, and discuss ​ 
-    ​Trust in Robots</​a>, ​TU Vienna.</​td></​tr><​tr valign="​top"><​td>​2019-12-05</​td><​td>​IIS guest <span style="​font-weight:​bold"​>Heiko Neumann</​span>, ​University of Ulm,  gives an invited colloquium <​i>​Biologically inspired visual-auditory processing – from +    how the Octopus itself ​can inspire cognitive robotic research. 
-    brain-like computation to neuromorphic algorithms</i> at <a href="​https://​​informatik/​forschung/​lunchtime-seminar/​index.html.en">​IFI Lunchtime Seminar</​a>​. <span class="​actions"><​a href="​javascript:​void(0)"​ onclick="​showHide('​newsitem9', '​Abstract'​)">​[Abstract]</​a></​span><​blockquote id="newsitem9Abstract" style="​display:​none">​A fundamental task of sensory ​processing ​is to detect +    </​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://​">Pint of 
-    ​and integrate feature items to group them into perceptual units +    ​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 
-    ​segregating them from other objects ​and the background. A +    ​task with our annoying chores? How would we teach the robot to 
-    framework is discussed which explains how perceptual grouping at +    ​perform these tasks? Can we build such robots by equipping them 
-    early as well as higher-level cognitive stages may be implemented +    with artificial intelligence?​ We will discuss ​how human and 
-    in cortex. Different grouping mechanisms are implemented which are +    ​machine learning differ and how this impacts what skills, 
-    ​attuned to basic features and feature combinations and mainly +    including for communication,​ our helper robot will be able to 
-    evaluated along the forward sweep of stimulus processing. However, +    ​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 
-    due to limitations of local feature detection mechanisms ​and +    Machines</​i>​ at <a href="​https://​​">Workshop 
-    inherent ambiguities,​ top-down feedback is required ​to deliver +    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 
-    ​contextual information helping to disambiguate initial +    finding explanationsimproving technologyor solving novel 
-    measurementsFeedback of contextual information is demonstrated +    ​problems in everyday lifeEven imitating other humans, e.g. while 
-    to improve object recognition performancestabilize learning of +    ​learning a new skillis creative in that the imitator has to 
-    ​object categories, ​and integrate multi-sensory representations. +    infer the conceptual structure underlying the observed 
- +    manifestation and to regenerate the latter from the former. In 
-    The canonical principles of neural computation define a set of +    contrast, current AI-enabled agents are unable to generate and 
-    ​core operations to implement above-mentioned mechanisms ​of +    draw upon such conceptual structures. Their learning is mostly 
-    ​perceptual ​and cognitive inferenceThese operations can be +    driven by statistics, and any ability to produce novelty is 
-    ​mapped, in a simplified form, onto neuromorphic platforms to +    largely limited to trial and error. I will try to characterize 
-    ​emulate brain-like computation. It is demonstrated that an +    this fundamental difference between learning in human and 
-    ​architecture composed ​of canonical circuit mechanisms can be +    artificial agents, and will discuss possible technological 
-    mapped onto neuromorphic chip technology facilitating low-energy +    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 
-    non-von Neumann computation.</​blockquote></​td></​tr><​tr valign="​top"><​td>​2019-11-26</​td><​td>​IIS guest <span style="​font-weight:​bold">​Tamim Asfour</​span>,​ Karlsruhe Institute of Technology, ​ gives an invited keynote ​<i>Engineering Humanoids with Motion Intelligence</i> at <a href="​https://​​informatik/​studium/inday-students/​index.html.en">inday students</a>. <span class="​actions"​><a href="javascript:​void(0)"​ onclick="​showHide('​newsitem10',​ '​Abstract'​)">[Abstract]</a></span><blockquote id="newsitem10Abstract"​ style="​display:none">Humanoid robotics plays a central role in robotics +    ​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 
-    ​research as well as in understanding intelligence. Engineering +    ​Bedarfserweckung?</i> at <a href="​veranstaltungen/">Medical 
-    humanoid robots that are able to learn from humans ​and +    ​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 Citizenship,​ Vrije 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 
-    sensorimotor experience, to predict the consequences ​of actions +    ​analytical methods ​and artificial intelligence ​are motivating 
-    and exploit the interaction with the world to extend their +    ​entire branches ​of science ​to raise new questions ​and to develop 
-    cognitive horizon remains ​research grand challenge. Currently, +    ​new approachesThis digital transformation requires progressive
-    we are experiencing AI systems with superhuman performance in +    ​interdisciplinary synergies between the computational sciences ​and 
-    gamesimage and speech processingHowever, the generation of +    ​all other scientific disciplines.  ​The Digital Science Center 
-    robot behaviors with human-like motion intelligence and +    ​(DiSC) at the University ​of Innsbruck meets this challenge by 
-    performance has yet to be achieved. In this talk, I will present +    ​integrating ​and promoting digitalisation of scientific research
-    recent progress towards engineering 24/7 humanoid robots that link +    ​In this talk I will present some examples of interdisciplinary 
-    perception and action to generate intelligent behaviorI will +    ​research by DiSC staff researchers who are experts in specific 
-    ​show the ARMAR humanoid robots performing complex grasping and +    ​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</iat <a href="https://​​rest/​entries/​api/​v1/​blobs/​200894">Workshop 
-    manipulation tasks in kitchen and industrial environments,​ +    and Open Lab on Field Robotics - Interdisciplinary aspects ​of 
-    learning actions from human observation and experience as well as +    ​robotics ​and its applications in outdoor scenarios</​a>NOI TechparkBolzano, 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="​http:/​/​aktuell/">​GMAR Robotics Science 
-    reasoning about object-action relations.</blockquote></​td></​tr></​table></​HTML>​+    ​Talks</a>, online.</​td></​tr></​table></​HTML>​
 [[news|Older News]] [[news|Older News]]
start.1606117965.txt.gz · Last modified: 2020/11/23 08:52 by IIS Webadmin