Menu
▾
▴
simspark-devel
|
From: Hedayat V. <hed...@ai...> - 2009-04-10 10:35:13
|
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"> <html style="direction: ltr;"> <head> </head> <body style="direction: ltr;" bgcolor="#ffffff" text="#000000"> <p style="margin-bottom: 0cm; margin-top: 0pt;">Hi all,</p> <p style="margin-bottom: 0cm; margin-top: 0pt;">If we are going to change some settings for 2009, it should be done ASAP. Please share your opinions about these matters. Also, it would be nice if you can do this changes.</p> <p style="margin-bottom: 0cm; margin-top: 0pt;">These are what might be necessary to be done for 2009:</p> <p style="margin-bottom: 0cm; margin-top: 0pt;">1. Adding more flags around the field.</p> <p style="margin-bottom: 0cm; margin-top: 0pt;">2. Increasing the vision noise. The current noise parameters are tuned for a much bigger field that what we have now, and in the current field the vision noise is probably near zero.</p> <p style="margin-bottom: 0cm; margin-top: 0pt;">3. Adding noise to agent's joint actuators and/or perceptors.</p> <p style="margin-bottom: 0cm; margin-top: 0pt;"><br> </p> <p style="margin-bottom: 0cm; margin-top: 0pt;">Did I miss anything?</p> <p style="margin-bottom: 0cm; margin-top: 0pt;"><br> </p> <p style="margin-bottom: 0cm; margin-top: 0pt;">Finally, would you please provide a summary of your current status with regard to simspark development? </p> <p style="margin-bottom: 0cm; margin-top: 0pt;">Personally, I was too busy in the past months and so I didn't do much (except that the current simspark and rcssserver3d can be compiled on Windows completely). But hopefully I'll be able to do some work on Player integration, so that it might be a part of what we can show in RoboCup 2009 as one of the features of the server for 2010. If we have enough new features, we might be able to present the new features in RoboCup 2009. (It seems that we can't have any new features to be used in 2009, since there is not much time till the competition.).</p> <p style="margin-bottom: 0cm; margin-top: 0pt;"><br> </p> <p style="margin-bottom: 0cm; margin-top: 0pt;">Thanks a lot,</p> <p style="margin-bottom: 0cm; margin-top: 0pt;">Hedayat</p> <p style="margin-bottom: 0cm; margin-top: 0pt;"><br> </p> </body> </html> |
|
From: Mahdi <zig...@gm...> - 2009-04-12 12:13:40
|
2009/4/10 Hedayat Vatankhah <hed...@ai...> > Hi all, > > If we are going to change some settings for 2009, it should be done ASAP. > Please share your opinions about these matters. Also, it would be nice if > you can do this changes. > > These are what might be necessary to be done for 2009: > > 1. Adding more flags around the field. > Adding field boundry lines seems to work just good. But if we are going to have more vision noise that the current rate (which is proposed by Hedayat in next todo item), it seems better if there be more flags on the two longitude lines of the field. > 2. Increasing the vision noise. The current noise parameters are tuned for > a much bigger field that what we have now, and in the current field the > vision noise is probably near zero. > > 3. Adding noise to agent's joint actuators and/or perceptors. > > > Did I miss anything? > > > Finally, would you please provide a summary of your current status with > regard to simspark development? > I am working on a simple binary protocol for simulator<->monitor connections, thus enabling more details to be sent to monitor/trainer and vice versa. A full briefing will be made after completion of this task. > Personally, I was too busy in the past months and so I didn't do much > (except that the current simspark and rcssserver3d can be compiled on > Windows completely). But hopefully I'll be able to do some work on Player > integration, so that it might be a part of what we can show in RoboCup 2009 > as one of the features of the server for 2010. If we have enough new > features, we might be able to present the new features in RoboCup 2009. (It > seems that we can't have any new features to be used in 2009, since there is > not much time till the competition.). > > > Thanks a lot, > > Hedayat > > > > > ------------------------------------------------------------------------------ > This SF.net email is sponsored by: > High Quality Requirements in a Collaborative Environment. > Download a free trial of Rational Requirements Composer Now! > http://p.sf.net/sfu/www-ibm-com > _______________________________________________ > Simspark Generic Physical MAS Simulator > simspark-devel mailing list > sim...@li... > https://lists.sourceforge.net/lists/listinfo/simspark-devel > > |
|
From: Sander v. D. <sgv...@gm...> - 2009-04-12 16:43:19
|
Hey, On Sun, Apr 12, 2009 at 4:43 PM, Mahdi <zig...@gm...> wrote: > > > 2009/4/10 Hedayat Vatankhah <hed...@ai...> > >> Hi all, >> >> If we are going to change some settings for 2009, it should be done ASAP. >> Please share your opinions about these matters. Also, it would be nice if >> you can do this changes. >> >> These are what might be necessary to be done for 2009: >> >> 1. Adding more flags around the field. >> > > Adding field boundry lines seems to work just good. But if we are going to > have more vision noise that the current rate (which is proposed by Hedayat > in next todo item), it seems better if there be more flags on the two > longitude lines of the field. > I find that localization is very well possible with the current amount of markers. But if only a few teams are able to get it working competitions will be rather boring. Next week during the German Open we will try to use restricted vision, after that we'll have a better idea if the teams manage to cope with it I think. > 2. Increasing the vision noise. The current noise parameters are tuned >> for a much bigger field that what we have now, and in the current field the >> vision noise is probably near zero. >> > I agree to this, the error currently is in the order of milimeters I believe. Perhaps a reasonable way to define the parameters is to look at the view angle and resolution of the real NAO and set the error variance such that it corresponds to 1 (or 2) pixels off. Or see if any team has any real data on measurement errors (I'll see if I can contact some humanoid teams). 3. Adding noise to agent's joint actuators and/or perceptors. >> > I think this isnj't too hard to implement and we can see how that works out. However, I feel that we have to keep in mind that the simulation league is more about higher level control (in my opinion). It is good to make it more realistic, but 3D teams shouldn't have to spend too much time on problems that other leagues are already working on. > Did I miss anything? >> > The automatic referee could use a lookover I think, like balls hitting the goal post being registered as goals or clear goals being registered as goal kicks. And perhaps we can explicitely implement some of the keeper rules that are now enforced by the human referee (eg. handling the ball outside the penalty area, lieing in front of the goal longer than so many seconds). >> Finally, would you please provide a summary of your current status with >> regard to simspark development? >> > > I am afraid I will be quite busy too. I will put the meshes we received from Aldebaran into the simulator (as soon as they have resolved license issues), other than that I can't guarantee I will have much time unfortunately.. Cheers, Sander |
|
From: Hedayat V. <hed...@ai...> - 2009-04-13 07:41:24
|
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html style="direction: ltr;">
<head>
<meta content="text/html;charset=UTF-8" http-equiv="Content-Type">
</head>
<body style="direction: ltr;" bgcolor="#ffffff" text="#000000">
Hi all,<span><br>
<br>
<style type="text/css">blockquote {color: navy !important; background-color: RGB(245,245,245) !important; padding: 0 15 10 15 !important; margin: 15 0 0 0; border-left: #1010ff 2px solid;} blockquote blockquote {color: maroon !important; background-color: RGB(235,235,235) !important; border-left-color:maroon !important} blockquote blockquote blockquote {color: green !important; background-color: RGB(225,225,225) !important; border-left-color:teal !important} blockquote blockquote blockquote blockquote {color: purple !important; background-color: RGB(215,215,215) !important; border-left-color: purple !important} blockquote blockquote blockquote blockquote blockquote {color: teal !important; background-color: RGB(205,205,205) !important; border-left-color: green !important}</style><i><b>Sander
van Dijk <a class="moz-txt-link-rfc2396E" href="mailto:sgv...@gm..."><sgv...@gm...></a></b></i> wrote on ۰۹/۰۴/۱۲ 09:13:16:</span><br>
<blockquote style="border-left: 2px solid rgb(16, 16, 255); color: navy; background-color: rgb(245, 245, 245); padding-left: 15px;" cite="mid:efd...@ma..." type="cite">Hey,<br>
<br>
<div class="gmail_quote">On Sun, Apr 12, 2009 at 4:43 PM, Mahdi <span dir="ltr"><<a moz-do-not-send="true" href="mailto:zig...@gm...">zig...@gm...</a>></span>
wrote:<br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"><br>
<br>
<div class="gmail_quote">2009/4/10 Hedayat Vatankhah <span dir="ltr"><<a moz-do-not-send="true" href="mailto:hed...@ai..." target="_blank">hed...@ai...</a>></span>
<div class="im"><br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div style="direction: ltr;" bgcolor="#ffffff" text="#000000">
<p style="margin-bottom: 0cm; margin-top: 0pt;">Hi all,</p>
<p style="margin-bottom: 0cm; margin-top: 0pt;">If we are going
to
change some settings for 2009, it should be done ASAP. Please share
your opinions about these matters. Also, it would be nice if you can do
this changes.</p>
<p style="margin-bottom: 0cm; margin-top: 0pt;">These are what
might be
necessary to be done for 2009:</p>
<p style="margin-bottom: 0cm; margin-top: 0pt;">1. Adding more
flags
around the field.</p>
</div>
</blockquote>
</div>
<div><br>
Adding field boundry lines seems to work just good. But if we are going
to have more vision noise that the current rate (which is proposed by
Hedayat in next todo item), it seems better if there be more flags on
the two longitude lines of the field.</div>
</div>
</blockquote>
<div><br>
I find that localization is very well possible with the current amount
of markers. But if only a few teams are able to get it working
competitions will be rather boring. Next week during the German Open we
will try to use restricted vision, after that we'll have a better idea
if the teams manage to cope with it I think.<br>
</div>
</div>
</blockquote>
Nice! But IMHO adding boundary lines as mentioned in the sserver
mailing list is not a bad idea anyway.<br>
<br>
<blockquote style="border-left: 2px solid rgb(16, 16, 255); color: navy; background-color: rgb(245, 245, 245); padding-left: 15px;" cite="mid:efd...@ma..." type="cite">
<div class="gmail_quote">
<div><br>
</div>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div class="gmail_quote">
<div><br>
</div>
<div class="im">
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div style="direction: ltr;" bgcolor="#ffffff" text="#000000">
<p style="margin-bottom: 0cm; margin-top: 0pt;"></p>
<p style="margin-bottom: 0cm; margin-top: 0pt;">2. Increasing the
vision noise. The current noise parameters are tuned for a much bigger
field that what we have now, and in the current field the vision noise
is probably near zero.</p>
</div>
</blockquote>
</div>
</div>
</blockquote>
<div><br>
I agree to this, the error currently is in the order of milimeters I
believe. Perhaps a reasonable way to define the parameters is to look
at the view angle and resolution of the real NAO and set the error
variance such that it corresponds to 1 (or 2) pixels off. Or see if any
team has any real data on measurement errors (I'll see if I can contact
some humanoid teams).<br>
</div>
</div>
</blockquote>
Great, thanks. <br>
<br>
<blockquote style="border-left: 2px solid rgb(16, 16, 255); color: navy; background-color: rgb(245, 245, 245); padding-left: 15px;" cite="mid:efd...@ma..." type="cite">
<div class="gmail_quote">
<div><br>
</div>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div class="gmail_quote">
<div class="im">
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div style="direction: ltr;" bgcolor="#ffffff" text="#000000">
<p style="margin-bottom: 0cm; margin-top: 0pt;">3. Adding noise
to
agent's joint actuators and/or perceptors.</p>
</div>
</blockquote>
</div>
</div>
</blockquote>
<div><br>
I think this isnj't too hard to implement and we can see how that works
out. However, I feel that we have to keep in mind that the simulation
league is more about higher level control (in my opinion). It is good
to make it more realistic, but 3D teams shouldn't have to spend too
much time on problems that other leagues are already working on.<br>
</div>
</div>
</blockquote>
Maybe we should discuss about it with TC. Since the current trend in 3D
is to be more realistic as we go. And if I remember correctly, this is
the decision of TC. BTW, I don't know if it is too late to introduce
noise in joints.<br>
<br>
<br>
<blockquote style="border-left: 2px solid rgb(16, 16, 255); color: navy; background-color: rgb(245, 245, 245); padding-left: 15px;" cite="mid:efd...@ma..." type="cite">
<div class="gmail_quote">
<div>�<br>
</div>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div class="gmail_quote">
<div class="im">
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div style="direction: ltr;" bgcolor="#ffffff" text="#000000">
<p style="margin-bottom: 0cm; margin-top: 0pt;"></p>
<p style="margin-bottom: 0cm; margin-top: 0pt;">Did I miss
anything?</p>
</div>
</blockquote>
</div>
</div>
</blockquote>
<div><br>
The automatic referee could use a lookover I think, like balls hitting
the goal post being registered as goals or clear goals being registered
as goal kicks. And perhaps we can explicitely implement some of the
keeper rules that are now enforced by the human referee (eg. handling
the ball outside the penalty area, lieing in front of the goal longer
than so many seconds).<br>
</div>
</div>
</blockquote>
Yes, you're right. The current referee is not dependable! A good point
to consider.<br>
<br>
<blockquote style="border-left: 2px solid rgb(16, 16, 255); color: navy; background-color: rgb(245, 245, 245); padding-left: 15px;" cite="mid:efd...@ma..." type="cite">
<div class="gmail_quote">
<div><br>
</div>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div class="gmail_quote">
<div class="im">
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div style="direction: ltr;" bgcolor="#ffffff" text="#000000">
<p style="margin-bottom: 0cm; margin-top: 0pt;"><br>
</p>
<p style="margin-bottom: 0cm; margin-top: 0pt;">Finally, would
you
please provide a summary of your current status with regard to simspark
development? </p>
</div>
</blockquote>
</div>
<div><br>
</div>
</div>
</blockquote>
</div>
<br>
I am afraid I will be quite busy too. I will put the meshes we received
from Aldebaran into the simulator (as soon as they have resolved
license issues), other than that I can't guarantee I will have much
time unfortunately..<br>
<br>
</blockquote>
Thank you anyway :)<br>
<br>
Good luck,<br>
Hedayat<br>
<br>
<blockquote style="border-left: 2px solid rgb(16, 16, 255); color: navy; background-color: rgb(245, 245, 245); padding-left: 15px;" cite="mid:efd...@ma..." type="cite">Cheers,<br>
Sander<br>
</blockquote>
</body>
</html>
|
×
Want the latest updates on software, tech news, and AI?
Get latest updates about software, tech news, and AI from SourceForge directly in your inbox once a month.
Thanks for helping keep SourceForge clean.
X