Differences

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

--- start [2019/12/04 06:25]
IIS Webadmin
+++ start [2020/06/23 06:25] (current)
IIS Webadmin
@@ Line 13: / Line 13: @@
   * Check our thesis topics for [[theses/start|Bachelor and Master students]].
+<html><!--
 //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!
+--></html>
 <html>
 <div style="clear:both"><br></div>
@@ Line 25: / Line 28: @@
 ===== News =====
-<HTML><table><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
+<HTML><table><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
+    ISIS Réunion Apprentissage et Robotique</a>, online. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem0', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem0Abstract" style="display:none">Conditional Neural Movement Primitives (CNMP) constitute
+    a novel framework for robot programming by demonstration based on
+    Conditional Neural Processes (CNP).  Like Bayesian methods such as
+    Gaussian Processes (GP), CNP learn how target distributions depend
+    on data, and can be conditioned on specific data points to infer
+    new target distributions at test time.  Unlike GP that are
+    expensive to train and scale poorly to high dimensions, CNP are
+    neural networks and are trained by gradient descent.  CNMP
+    leverage CNP to represent motion trajectories that can be
+    conditioned, at test time, on task paramters such as goal
+    locations, via points, and/or force readings.  Moreover, CNMP are
+    conditioned on sensor readings during execution, resulting in
+    robust, reactive behavior.  This talk will present an overview of
+    how CNMP work and how they can be used in various robot
+    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
+    „Primers for Predocs – Strategien für eine erfolgreiche
+    Promotion“</a>, Universität Heidelberg. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem3', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem3Abstract" 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 Center, and 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><tr valign="top"><td>2020-01-03</td><td>Justus Piater gives an invited talk <i>Künstliche Intelligenz: Grundlagen, Erfolge,
+    Herausforderungen</i> at 47. Tagung des Innsbrucker Kreises von MoraltheologInnen
+    und SozialethikerInnen, Innsbruck.</td></tr><tr valign="top"><td>2019-12-19</td><td>Justus Piater appears in the media: <a href="https://tvthek.orf.at/profile/Tirol-heute/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
     Understand My Robot?</i> at <a href="http://www.trustrobots.eu/">TrustRobots Lecture series
     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
-    brain-like computation to neuromorphic algorithms</i> at <a href="https://www.uibk.ac.at/informatik/forschung/lunchtime-seminar/index.html.en">IFI Lunchtime Seminar</a>.</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://www.uibk.ac.at/informatik/studium/inday-students/index.html.en">inday students</a>.</td></tr><tr valign="top"><td>2019-11-25</td><td>Justus Piater gives an invited talk <i>Enabling Robots to Learn Abstract Concepts</i> at <a href="https://tricolore.inf.unibz.it/tricolore2019/program/">TriCoLore
+    brain-like computation to neuromorphic algorithms</i> at <a href="https://www.uibk.ac.at/informatik/forschung/lunchtime-seminar/index.html.en">IFI Lunchtime Seminar</a>. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem8', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem8Abstract" style="display:none">A fundamental task of sensory processing is to detect
-    – Creativity | Cognition | Computation</a>, Bolzano, Italy.</td></tr><tr valign="top"><td>2019-11-18</td><td>Justus Piater gives an invited talk <i>Künstliche Intelligenz in einer menschlichen
+    and integrate feature items to group them into perceptual units
-    Gesellschaft</i> at Robotik in Medizin und Pflege – Jubiläumssymposium
+    segregating them from other objects and the background. A
-    des Klinischen Ethikkommittees, A.ö. Landeskrankenhaus – Universitätskliniken
+    framework is discussed which explains how perceptual grouping at
-    Innsbruck.</td></tr><tr valign="top"><td>2019-11-08</td><td>Justus Piater gives an invited talk <i>AI Transparency in Autonomous Vehicles</i> at <a href="https://cogvehicles2019.github.io/">Towards Cognitive
+    early as well as higher-level cognitive stages may be implemented
-    Vehicles: perception, learning and decision making under
+    in cortex. Different grouping mechanisms are implemented which are
-    real-world constraints. Is bio-inspiration helpful?</a>, Macau.</td></tr><tr valign="top"><td>2019-11-03</td><td>Justus Piater, Philipp Gschwandtner, and Simon Haller appear in the media: Österreich-Bild: Bits und Berge - 350 Jahre Forschung in Innsbruck; TV Documentary by ORF 2 (in German).</td></tr><tr valign="top"><td>2019-10-23</td><td>Simon Haller appears in the media: TV interview by ORF 2 Tirol Heute (in German).</td></tr><tr valign="top"><td>2019-10-11</td><td>Justus Piater appears in the media: <a href="https://issuu.com/eco.nova/docs/eco_06_2019_issuu/24">KI oder
+    attuned to basic features and feature combinations and mainly
-    die Geschichte einer gleichzeitigen Über- und Unterschätzung
+    evaluated along the forward sweep of stimulus processing. However,
-    (eco.nova, in German)</a>.</td></tr><tr valign="top"><td>2019-10-10</td><td>IIS guest <span style="font-weight:bold">Georg Martius</span>, Max Planck Institute for Intelligent Systems,
+    due to limitations of local feature detection mechanisms and
-    Tübingen,  gives an invited colloquium <i>Control What You Can – Intrinsically Motivated
+    inherent ambiguities, top-down feedback is required to deliver
-    Hierarchical RL</i> at IIS Colloquium.</td></tr></table></HTML>
+    contextual information helping to disambiguate initial
+    measurements. Feedback of contextual information is demonstrated
+    to improve object recognition performance, stabilize learning of
+    object categories, and integrate multi-sensory representations.
+    The canonical principles of neural computation define a set of
+    core operations to implement above-mentioned mechanisms of
+    perceptual and cognitive inference. These operations can be
+    mapped, in a simplified form, onto neuromorphic platforms to
+    emulate brain-like computation. It is demonstrated that an
+    architecture composed of canonical circuit mechanisms can be
+    mapped onto neuromorphic chip technology facilitating low-energy
+    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://www.uibk.ac.at/informatik/studium/inday-students/index.html.en">inday students</a>. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem9', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem9Abstract" style="display:none">Humanoid robotics plays a central role in robotics
+    research as well as in understanding intelligence. Engineering
+    humanoid robots that are able to learn from humans and
+    sensorimotor experience, to predict the consequences of actions
+    and exploit the interaction with the world to extend their
+    cognitive horizon remains a research grand challenge. Currently,
+    we are experiencing AI systems with superhuman performance in
+    games, image and speech processing. However, the generation of
+    robot behaviors with human-like motion intelligence and
+    performance has yet to be achieved. In this talk, I will present
+    recent progress towards engineering 24/7 humanoid robots that link
+    perception and action to generate intelligent behavior. I will
+    show the ARMAR humanoid robots performing complex grasping and
+    manipulation tasks in kitchen and industrial environments,
+    learning actions from human observation and experience as well as
+    reasoning about object-action relations.</blockquote></td></tr><tr valign="top"><td>2019-11-25</td><td>Justus Piater gives an invited talk <i>Enabling Robots to Learn Abstract Concepts</i> at <a href="https://tricolore.inf.unibz.it/tricolore2019/program/">TriCoLore
+    – Creativity | Cognition | Computation</a>, Bolzano, Italy.</td></tr></table></HTML>
 [[news|Older News]]

User Tools

Site Tools

Differences

Page Tools