This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
start [2021/03/31 12:54] Matteo Saveriano |
start [2022/06/09 06:25] 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.eu/|ELLIS]] PhD Program: [[https://ellis.eu/de/news/ellis-phd-program-call-for-applications|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><!-- | <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 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>2022-05-20</td><td>Justus Piater appears in the media: <a href="https://radiothek.orf.at/podcasts/tir/derwoche/derwoche-maschinenzukunft">ORF |
- | tasks instead of having to program them in painstaking ways. | + | Tirol Podcast (in German)</a>. (Künstliche Intelligenz (KI) ist bereits heute ein täglicher Begleiter, doch vom universellen Haushaltsroboter sind wir noch weit entfernt. Automatisierte Systeme werden zwar Jobs übernehmen, Maschinen werden aber noch lange nicht die Weltherrschaft an sich reißen, falls überhaupt. Zur Langen Nacht der Forschung spricht Martin Kubin im #derWoche „Maschinenzukunft“ mit Prof. Justus Piater vom Institut für Informatik über Chancen und Gefahren von KI. Er weiß auch, warum KI etwa die Justiz unterstützen kann, aber ein KI-Richter niemals objektiv urteilen könnte.)</td></tr><tr valign="top"><td>2022-05-17</td><td>Erwan Renaudo gives an invited talk <i>A Brief tour of autonomous robots' "Cognition"</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('newsitem2', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem2Abstract" style="display:none">In the design of "Cognitive Robots" software architectures, |
- | Robots can learn from experience and can improve their behavior | + | researchers had to face many organizational problems due to |
- | over time. In this talk I will give an overview of methods, | + | the particular nature of robots. Not only should they manage |
- | opportunities, and challenges of machine learning in | + | to achieve complex tasks with long-terms goals, but they must |
- | 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&t=17m43s">Science Slam</a>, online.</td></tr> | + | also be reactive to their surroundings to preserve their environment. |
- | + | We will go over several layered control paradigms developed over | |
- | <tr valign="top"><td>2020-10-22 - 2020-10-23</td><td>Matteo Saveriano, Erwan Renaudo, Antonio Rodríguez-Sánchez, and Justus Piater organize the </i> <a href="https://iis.uibk.ac.at/conferences/hfr2020/"> 13th International Workshop on Human-Friendly Robotics (HFR 2020)</a>, Innsbruck (online).</td></tr> | + | the history of robotics and see how these can relate to the |
- | + | knowledge about the Octopus' brain organization, and discuss | |
- | <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 | + | how the Octopus itself can inspire cognitive robotic research. |
- | 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&idreunion=424">GdR | + | </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 |
- | 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 | + | Science</a>, Innsbruck. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem3', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem3Abstract" style="display:none">Wouldn't it be great to have a helper robot that we can |
- | a novel framework for robot programming by demonstration based on | + | task with our annoying chores? How would we teach the robot to |
- | Conditional Neural Processes (CNP). Like Bayesian methods such as | + | perform these tasks? Can we build such robots by equipping them |
- | Gaussian Processes (GP), CNP learn how target distributions depend | + | with artificial intelligence? We will discuss how human and |
- | on data, and can be conditioned on specific data points to infer | + | machine learning differ and how this impacts what skills, |
- | new target distributions at test time. Unlike GP that are | + | including for communication, our helper robot will be able to |
- | expensive to train and scale poorly to high dimensions, CNP are | + | learn.</blockquote></td></tr><tr valign="top"><td>2022-04-28</td><td>Simon Haller-Seeber contributes a talk <i>STAIR Learning Lab</i> at <a href="http://rie.science">Robotics in Education 2022</a>, online.</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 |
- | neural networks and are trained by gradient descent. CNMP | + | Machines</i> at <a href="https://www.philosophie.uni-konstanz.de/ag-mueller/online-workshop-on-agency-life-and-creativity/">Workshop |
- | leverage CNP to represent motion trajectories that can be | + | on “Agency, Life, and Creativity”</a>, online. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem5', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem5Abstract" style="display:none">Humans constantly engage in creative activity such as |
- | conditioned, at test time, on task paramters such as goal | + | finding explanations, improving technology, or solving novel |
- | locations, via points, and/or force readings. Moreover, CNMP are | + | problems in everyday life. Even imitating other humans, e.g. while |
- | conditioned on sensor readings during execution, resulting in | + | learning a new skill, is creative in that the imitator has to |
- | robust, reactive behavior. This talk will present an overview of | + | infer the conceptual structure underlying the observed |
- | how CNMP work and how they can be used in various robot | + | manifestation and to regenerate the latter from the former. In |
- | 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 | + | contrast, current AI-enabled agents are unable to generate and |
- | „Primers for Predocs – Strategien für eine erfolgreiche | + | draw upon such conceptual structures. Their learning is mostly |
- | 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 | + | driven by statistics, and any ability to produce novelty is |
- | promoting data-driven methods in all areas of science and | + | largely limited to trial and error. I will try to characterize |
- | technology. I will describe how the University of Innsbruck | + | this fundamental difference between learning in human and |
- | supports this via its new Digital Science Center, and will give a | + | artificial agents, and will discuss possible technological |
- | 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> | + | 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 & Global Citizenship, Vrije Universiteit Amsterdam. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem8', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem8Abstract" 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 teaches a tutorial <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></table></HTML> | ||
[[news|Older News]] | [[news|Older News]] |