Differences

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

--- start [2021/08/06 20:13]
Justus Piater
+++ start [2022/05/20 06:25] (current)
IIS Webadmin
@@ Line 11: / Line 11: @@
 ===== 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]].
-  * [[https://ellis.eu/|ELLIS]] PhD Program: [[https://ellis.eu/news/ellis-phd-program-call-for-applications-deadline-november-15-2021|Call for Applications]]
+ <html><!--
+ * [[https://ellis.eu/|ELLIS]] PhD Program: [[https://ellis.eu/news/ellis-phd-program-call-for-applications-deadline-november-15-2021|Call for Applications]]
+--></html>
 <html><!--
@@ Line 29: / Line 32: @@
 ===== 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 a 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://icprai2022.sciencesconf.org/">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
-    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 elements. First, 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://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 online, GMAR, 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
+    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://www.philosophie.uni-konstanz.de/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,
-    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 goals, but they must
-    opportunities, and 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://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
+    We will go over several layered control paradigms developed over
-    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
+    the history of robotics and see how these can relate to the
-    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
+    knowledge about the Octopus' brain organization, and discuss
-    a novel framework for robot programming by demonstration based on
+    how the Octopus itself can inspire cognitive robotic research.
-    Conditional Neural Processes (CNP).  Like Bayesian methods such as
+    </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://pintofscience.at/events/innsbruck">Pint of
-    Gaussian Processes (GP), CNP learn how target distributions depend
+    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
-    on data, and can be conditioned on specific data points to infer
+    task with our annoying chores? How would we teach the robot to
-    new target distributions at test time.  Unlike GP that are
+    perform these tasks? Can we build such robots by equipping them
-    expensive to train and scale poorly to high dimensions, CNP are
+    with artificial intelligence? We will discuss how human and
-    neural networks and are trained by gradient descent.  CNMP
+    machine learning differ and how this impacts what skills,
-    leverage CNP to represent motion trajectories that can be
+    including for communication, our helper robot will be able to
-    conditioned, at test time, on task paramters such as goal
+    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
-    locations, via points, and/or force readings.  Moreover, CNMP are
+    Machines</i> at <a href="https://www.philosophie.uni-konstanz.de/ag-mueller/online-workshop-on-agency-life-and-creativity/">Workshop
-    conditioned on sensor readings during execution, resulting in
+    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
-    robust, reactive behavior.  This talk will present an overview of
+    finding explanations, improving technology, or solving novel
-    how CNMP work and how they can be used in various robot
+    problems in everyday life. Even imitating other humans, e.g. while
-    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
+    learning a new skill, is creative in that the imitator has to
-    „Primers for Predocs – Strategien für eine erfolgreiche
+    infer the conceptual structure underlying the observed
-    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
+    manifestation and to regenerate the latter from the former. In
-    promoting data-driven methods in all areas of science and
+    contrast, current AI-enabled agents are unable to generate and
-    technology.  I will describe how the University of Innsbruck
+    draw upon such conceptual structures. Their learning is mostly
-    supports this via its new Digital Science Center, and will give a
+    driven by statistics, and any ability to produce novelty is
-    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>
+    largely limited to trial and error. I will try to characterize
+    this fundamental difference between learning in human and
+    artificial agents, and will discuss possible technological
+    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://www.linkedin.com/posts/elsa-innsbruck_letzte-woche-fand-zum-elsa-day-am-24112021-activity-6871397038093869057-16-7">Privacy
+    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.com/veranstaltungen/">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 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
+    analytical methods and artificial intelligence are motivating
+    entire branches of science to raise new questions and to develop
+    new approaches. This 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 I 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://www.uibk.ac.at/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://webservices.scientificnet.org/rest/entries/api/v1/blobs/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="http://www.gmar.at/aktuell/">GMAR Robotics Science
+    Talks</a>, online.</td></tr></table></HTML>
 [[news|Older News]]

User Tools

Site Tools

Differences

Page Tools