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 [2020/05/13 20:44] Justus Piater |
start [2020/09/11 09:27] Justus Piater |
||
---|---|---|---|
Line 12: | Line 12: | ||
===== Working With Us ===== | ===== Working With Us ===== | ||
* 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><!-- | <html><!-- | ||
Line 28: | Line 29: | ||
===== News ===== | ===== News ===== | ||
- | <HTML><table><tr valign="top"><td>2020-03-19</td><td>Justus Piater gives an invited talk <i>Machine Learning in Robotics</i> at <a href="https://baiome.org/">bAIome PI Talk</a>, Center for Biomedical AI at the University Medical Center | + | <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&idreunion=424">GdR |
- | Hamburg-Eppendorf. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem0', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem0Abstract" style="display:none">Machine Learning increasingly equips robots with | + | 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 |
- | learning capabilities and flexibility. This will enable them to | + | a novel framework for robot programming by demonstration based on |
- | act purposefully in unstructured environments and to react to | + | Conditional Neural Processes (CNP). Like Bayesian methods such as |
- | unforeseen events. People can teach them intuitively to perform | + | Gaussian Processes (GP), CNP learn how target distributions depend |
- | tasks instead of having to program them in painstaking ways. | + | on data, and can be conditioned on specific data points to infer |
- | Robots can learn from experience and can improve their behavior | + | new target distributions at test time. Unlike GP that are |
- | over time. In this talk I will give an overview of methods, | + | expensive to train and scale poorly to high dimensions, CNP are |
- | opportunities, and challenges of machine learning in | + | neural networks and are trained by gradient descent. CNMP |
- | robotics.</blockquote></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 | + | 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 | „Primers for Predocs – Strategien für eine erfolgreiche | ||
- | Promotion“</a>, Universität Heidelberg. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem2', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem2Abstract" style="display:none">Massive availability of data and computing power are | + | 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 | promoting data-driven methods in all areas of science and | ||
technology. I will describe how the University of Innsbruck | technology. I will describe how the University of Innsbruck | ||
Line 48: | Line 55: | ||
Understand My Robot?</i> at <a href="http://www.trustrobots.eu/">TrustRobots Lecture series | 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 | 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>. <span class="actions"><a href="javascript:void(0)" onclick="showHide('newsitem7', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem7Abstract" style="display:none">A fundamental task of sensory processing is to detect | + | 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 |
and integrate feature items to group them into perceptual units | and integrate feature items to group them into perceptual units | ||
segregating them from other objects and the background. A | segregating them from other objects and the background. A | ||
Line 70: | Line 77: | ||
architecture composed of canonical circuit mechanisms can be | architecture composed of canonical circuit mechanisms can be | ||
mapped onto neuromorphic chip technology facilitating low-energy | 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('newsitem8', 'Abstract')">[Abstract]</a></span><blockquote id="newsitem8Abstract" style="display:none">Humanoid robotics plays a central role in robotics | + | 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 | research as well as in understanding intelligence. Engineering | ||
humanoid robots that are able to learn from humans and | humanoid robots that are able to learn from humans and | ||
Line 86: | Line 93: | ||
learning actions from human observation and experience as well as | 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 | 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><tr valign="top"><td>2019-11-18</td><td>Justus Piater gives an invited talk <i>Künstliche Intelligenz in einer menschlichen | + | – Creativity | Cognition | Computation</a>, Bolzano, Italy.</td></tr></table></HTML> |
- | Gesellschaft</i> at Robotik in Medizin und Pflege – Jubiläumssymposium | + | |
- | des Klinischen Ethikkommittees, A.ö. Landeskrankenhaus – Universitätskliniken | + | |
- | Innsbruck.</td></tr></table></HTML> | + | |
[[news|Older News]] | [[news|Older News]] |