<html xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:st1="urn:schemas-microsoft-com:office:smarttags" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv=Content-Type content="text/html; charset=iso-8859-2">
<meta name=Generator content="Microsoft Word 11 (filtered medium)">
<o:SmartTagType namespaceuri="urn:schemas-microsoft-com:office:smarttags"
name="City"/>
<o:SmartTagType namespaceuri="urn:schemas-microsoft-com:office:smarttags"
name="place"/>
<!--[if !mso]>
<style>
st1\:*{behavior:url(#default#ieooui) }
</style>
<![endif]-->
<style>
<!--
/* Font Definitions */
@font-face
{font-family:SimSun;
panose-1:2 1 6 0 3 1 1 1 1 1;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:"\@SimSun";
panose-1:0 0 0 0 0 0 0 0 0 0;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0cm;
margin-bottom:.0001pt;
font-size:12.0pt;
font-family:"Times New Roman";}
a:link, span.MsoHyperlink
{color:blue;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{color:purple;
text-decoration:underline;}
span.EmailStyle17
{mso-style-type:personal-compose;
font-family:Arial;
color:windowtext;}
@page Section1
{size:595.3pt 841.9pt;
margin:70.85pt 70.85pt 70.85pt 70.85pt;}
div.Section1
{page:Section1;}
-->
</style>
</head>
<body lang=SL link=blue vlink=purple>
<div class=Section1>
<p class=MsoNormal><font size=3 face="Times New Roman"><span style='font-size:
12.0pt'>Vabim vas na 4. predavanje iz sklopa "Kolokviji na IJS" v
letu 2008/09, ki bo <strong><b><font color=red face="Times New Roman"><span
style='color:red'>v sredo, 19. novembra 2008, ob 13:00 uri </span></font></b></strong><font
color=red><span style='color:red'>v Veliki predavalnici Instituta »Jožef
Stefan«</span></font> na Jamovi cesti 39 v Ljubljani. Napovednik
predavanja najdete tudi na naslovu <a
href="http://www.ijs.si/ijsw/Koledar_prireditev">http://www.ijs.si/ijsw/Koledar_prireditev</a>,
posnetke preteklih predavanj<font color=blue><span style='color:blue'> </span></font>pa
na <a href="http://videolectures.net/kolokviji_ijs">http://videolectures.net/kolokviji_ijs</a>.
<o:p></o:p></span></font></p>
<p class=MsoNormal><font size=3 face="Times New Roman"><span style='font-size:
12.0pt'>~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~<br>
<b><span style='font-weight:bold'>prof. Florentin <span style='text-transform:
uppercase'>Wörgöter</span><o:p></o:p></span></b></span></font></p>
<p class=MsoNormal><i><font size=3 face="Times New Roman"><span
style='font-size:12.0pt;font-style:italic'>Bernstein Center for Computational
Neuroscience, Göttingen, Nemčija<o:p></o:p></span></font></i></p>
<p class=MsoNormal><font size=3 face="Times New Roman"><span style='font-size:
12.0pt'><o:p> </o:p></span></font></p>
<p class=MsoNormal><b><font size=4 face="Times New Roman"><span
style='font-size:14.0pt;font-weight:bold'><o:p> </o:p></span></font></b></p>
<p class=MsoNormal><b><font size=4 face="Times New Roman"><span
style='font-size:14.0pt;font-weight:bold'>Adaptivno nevronsko krmiljenje
robotskih sistemov<o:p></o:p></span></font></b></p>
<p class=MsoNormal style='mso-margin-top-alt:auto;margin-bottom:12.0pt;
text-align:justify;text-justify:inter-ideograph'><font size=3
face="Times New Roman"><span style='font-size:12.0pt'>Standardne metode
robotskega krmiljenja, na primer PID regulatorji, imajo več neželenih lastnosti
kot so togost, neprilagodljivost in nezmožnost reagiranja na nove situacije. V
tem predavanju bom predstavil dvonožni robotski mehanizem RunBot, ki deluje po
principih nevronskega krmiljenja. V predlaganem sistemu so senzorične
informacije obdelane s pomočjo nevronske mreže, ki proizvaja motorične signale
direktno iz vrednosti nevronskih elementov. Robotski mehanizem pri tem razvije
hiter in gibčen korak, ki ga lahko s pomočjo simulirane nevronske plastičnosti
prilagodi na nove situacije. Z uporabo teorije robotskega krmiljenja lahko
potem pokažemo, da robot na ta način pridobi inverzni model, ki je primeren za
krmiljenje. V splošnem lahko teorijo zaprtozančnega robotskega krmiljenja
uporabimo za boljše razumevanje interakcije med robotom in njegovo okolico. V
drugem delu predavanja bom zato obravnaval zahtevnejše probleme kot je dvonožna
hoja in predstavil nekatere hipoteze o kompleksnih kognitivnih nalogah, ki jih
morajo roboti in živali (opice, ljudje) reševati, ko s svojim delovanjem
spreminjajo svoj svet.<o:p></o:p></span></font></p>
<p class=MsoNormal style='mso-margin-top-alt:auto;margin-bottom:12.0pt;
text-align:justify;text-justify:inter-ideograph'><font size=3
face="Times New Roman"><span style='font-size:12.0pt'>Predavanje bo v
angleščini.<o:p></o:p></span></font></p>
<p class=MsoNormal style='mso-margin-top-alt:auto;margin-bottom:12.0pt'><strong><b><font
size=3 color=red face=Calibri><span style='font-size:12.0pt;font-family:Calibri;
color:red'>Lepo vabljeni!</span></font></b></strong><strong><b><font
face="Times New Roman"><span style='font-weight:normal'><o:p></o:p></span></font></b></strong></p>
<p class=MsoNormal align=center style='text-align:center'><b><font size=6
face=Arial><span style='font-size:24.0pt;font-family:Arial;font-weight:bold'>***<o:p></o:p></span></font></b></p>
<p class=MsoNormal style='text-align:justify;text-justify:inter-ideograph'><font
size=3 face="Times New Roman"><span lang=EN-US style='font-size:12.0pt'><o:p> </o:p></span></font></p>
<p class=MsoNormal style='text-align:justify;text-justify:inter-ideograph'><font
size=3 face="Times New Roman"><span lang=EN-US style='font-size:12.0pt'>We
would like to invite you to 4<sup>th</sup> lecture of the "Kolokvij na
IJS" in the school year 2008/09. The lecture will be held <b><span
style='font-weight:bold'>on Wednesday, November 19, 2008, at 1 pm</span></b> at
<b><span style='font-weight:bold'>JSI main lecture hall</span></b>, Jamova 39, <st1:place
w:st="on"><st1:City w:st="on">Ljubljana</st1:City></st1:place>. The abstract of
the lecture can be found on website: </span></font><font size=2><span
lang=EN-US style='font-size:10.0pt'><a
href="http://www.ijs.si/ijsw/Koledar_prireditev"><font size=3><span
style='font-size:12.0pt'>http://www.ijs.si/ijsw/Koledar_prireditev</span></font></a></span></font><span
lang=EN-US>, the previous recorded lectures can be found on website: </span><font
size=2><span lang=EN-US style='font-size:10.0pt'><a
href="http://videolectures.net/kolokviji_ijs"><font size=3><span
style='font-size:12.0pt'>http://videolectures.net/kolokviji_ijs</span></font></a></span></font><span
lang=EN-US>.</span><font size=2><span lang=EN-US style='font-size:10.0pt'> </span></font><span
lang=EN-US><o:p></o:p></span></p>
<p class=MsoNormal><font size=3 face="Times New Roman"><span lang=EN-US
style='font-size:12.0pt'>********************************************<br>
<br>
<o:p></o:p></span></font></p>
<p class=MsoNormal><b><font size=3 face="Times New Roman"><span
style='font-size:12.0pt;font-weight:bold'>prof. Florentin <span
style='text-transform:uppercase'>Wörgöter</span><o:p></o:p></span></font></b></p>
<p class=MsoNormal><i><font size=3 face="Times New Roman"><span
style='font-size:12.0pt;font-style:italic'>Bernstein Center for Computational
Neuroscience, Göttingen, Nemčija<o:p></o:p></span></font></i></p>
<p class=MsoNormal style='text-align:justify;text-justify:inter-ideograph'><i><font
size=3 face="Times New Roman"><span style='font-size:12.0pt;font-style:italic'><o:p> </o:p></span></font></i></p>
<p class=MsoNormal style='text-align:justify;text-justify:inter-ideograph'><b><font
size=4 face="Times New Roman"><span lang=EN-US style='font-size:14.0pt;
font-weight:bold'>Robots under Adaptive Neural Control<o:p></o:p></span></font></b></p>
<p class=MsoNormal style='text-align:justify;text-justify:inter-ideograph'><b><font
size=4 face="Times New Roman"><span lang=EN-US style='font-size:14.0pt;
font-weight:bold'><o:p> </o:p></span></font></b></p>
<p class=MsoNormal style='text-align:justify;text-justify:inter-ideograph'><font
size=3 face="Times New Roman"><span lang=EN-US style='font-size:12.0pt'>Conventional
robot control, for example using PID controllers, often leads to unwanted
properties, because these controllers are stiff, inflexible, and cannot easily
adapt (“learn”) to new situations. Here we will show a small biped
robot RunBot, which operates under neuronal control, where signals from sensors
are being processed by a network to create motor-control signals directly from
neuronal elements. The little machine thereby develops a fast and flexible
dynamic walking gait and can adapt by ways of simulated neuronal plasticity to
new situations. One can now employ control theory and we can show that synaptic
plasticity in this case leads to the learning of an inverse controller model.
Closed-loop (system theory) can in general be used to better understand the
interactions between a robot and its world. At the end of the talk we would
therefore like to leave walking-control behind and instead discuss some more
speculative notions about how cognitive complexity arises from the way robots
and animals (monkeys, humans) influence their environment by own actions.<o:p></o:p></span></font></p>
<p class=MsoNormal style='text-align:justify;text-justify:inter-ideograph'><font
size=3 face="Times New Roman"><span lang=EN-US style='font-size:12.0pt'><o:p> </o:p></span></font></p>
<p class=MsoNormal><b><font size=4 face="Times New Roman"><span lang=EN-US
style='font-size:14.0pt;font-weight:bold'>We look forward to meeting you at the
“Kolokvij na IJS”!<o:p></o:p></span></font></b></p>
</div>
</body>
</html>