<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META content="text/html; charset=iso-8859-1" http-equiv=Content-Type>
<META name=GENERATOR content="MSHTML 8.00.6001.18828">
<STYLE></STYLE>
</HEAD>
<BODY bgColor=#ffffff>
<DIV>
<DIV><FONT face="Times New Roman">Dear All</FONT></DIV>
<DIV><FONT face="Times New Roman"></FONT> </DIV>
<DIV><FONT face="Times New Roman">I have a question about "Robot Inspection and
Poster Session", for those teams who have 2 robots the time of this test is
2+2+5=9 min. it is correct or not?</FONT></DIV>
<DIV><FONT face="Times New Roman"></FONT> </DIV>
<DIV><FONT face="Times New Roman">Meanwhile I would like to request from TCs to
extend period of rulebook discussion, because its expected to finalized
rulebook at end of Jan but it made ready at 11th Feb and in regards of volume of
changes 17 days is not enough for reviewing it.</FONT></DIV>
<DIV><FONT face="Times New Roman"></FONT> </DIV>
<DIV><FONT face="Times New Roman">Regards,</FONT></DIV>
<DIV><FONT face="Times New Roman">Fariborz</FONT></DIV></DIV>
<BLOCKQUOTE
style="BORDER-LEFT: #000000 2px solid; PADDING-LEFT: 5px; PADDING-RIGHT: 0px; MARGIN-LEFT: 5px; MARGIN-RIGHT: 0px">
<DIV style="FONT: 10pt arial">----- Original Message ----- </DIV>
<DIV
style="FONT: 10pt arial; BACKGROUND: #e4e4e4; font-color: black"><B>From:</B>
<A title=dgossow@uni-koblenz.de href="mailto:dgossow@uni-koblenz.de">David
Gossow</A> </DIV>
<DIV style="FONT: 10pt arial"><B>To:</B> <A
title=robocup-athome@lists.robocup.org
href="mailto:robocup-athome@lists.robocup.org">robocup-athome@lists.robocup.org</A>
</DIV>
<DIV style="FONT: 10pt arial"><B>Sent:</B> Monday, March 01, 2010 12:52
AM</DIV>
<DIV style="FONT: 10pt arial"><B>Subject:</B> Re: [robocup-athome] Rulebook
discussion?</DIV>
<DIV><BR></DIV>Hello Thomas,<BR><BR>thank you for your useful and constructive
comments on the rule book.<BR>I'll give you my (personal) views on
them.<BR><BR>Thomas Breuer schrieb:<BR>> Hi together,<BR>><BR>> we
(team b-it-bots) have a few questions and suggestions:<BR>><BR>>
----------------------------------------------------------------<BR>> Robot
Inspection and Poster Session:<BR>>
----------------------------------------------------------------<BR>> - Is
the environment known in this test?<BR>I'd say this would make sense.<BR>>
- What exactly (!) should the robot do to register itself?<BR>There are some
examples in the text on what to say. I don't think this<BR>is really
important, what matters is that your robot is operative, able<BR>to go to the
desk, say some sentences and preferably hand over the<BR>registration
form.<BR>> - Where is the poster presentation? Who will judge the posters?
The <BR>> time for doing so is too few (7 minutes for self registration AND
<BR>> poster session)<BR>We'll have many teams and not much time this year,
that's why the<BR>schedule for this test is so narrow. You'll have two minutes
for the<BR>registration. After that, the team leader has 5 minutes for a
poster<BR>presentation and answering questions from the other team
leaders.<BR>Parallel to that, someone from the TC will inspect the robot and
the<BR>robot has to leave autonomously (So e.g. 4 min. inspection and 1
minute<BR>leaving).<BR><BR>Probably this is going to be hectic somehow,
however the time<BR>limitations are just there. The only solution I see to
this would be to<BR>reduce the number of teams that are accepted to
participate in the<BR>competition.<BR><BR>><BR>>
----------------------------------------------------------------<BR>>
Follow Me:<BR>>
----------------------------------------------------------------<BR>> - Too
few time for all the tasks. Either tasks have to be reduced or <BR>> time
limit has to be extended. Suppose, that a robot needs 30-60 <BR>> seconds
to reach the next checkpoint, then there will be nearly no <BR>> time
anymore to fullfil the given tasks.<BR>You have five minutes for this test.
Suppose the robot needs 1 minute to<BR>calibrate on the operator. It needs 30
seconds to get from one<BR>checkpoint to the next (4x). Then you have 2
minutes left for the tasks.<BR>If you manage to do the the first and second
task in 30 seconds and the<BR>third one in one minute, you'll cross the finish
line right in time.<BR><BR>The tests are going to be more difficult than in
the last year in<BR>general, however. This is intended. Maybe no team is going
to be able to<BR>achieve the full score in this test and several
others.<BR>> - Checkpoint 3: The owner, who has to be recognized is
the <BR>> professional walker (whose face is learned at the beginning), is
this <BR>> correct? This should be made clear.<BR>Agreed.<BR>><BR>>
----------------------------------------------------------------<BR>> Go
Get It!:<BR>>
----------------------------------------------------------------<BR>> - 2
objects are lying on the floor. What happens, if the robot <BR>> collides
with one of them or drives over them? We suggest that the <BR>> robot is
allowed to collide with the objects on the floor (at least if <BR>> they
are not visible for the laser scanner).<BR>Good point, this should be made
clear in the rules. I'm not sure about<BR>allowing the robot to drive over
anything lying on the floor.<BR><BR>Anyway, if your robot drives over one the
objects and falls over,<BR>according to the current version of the rules I'd
say then your team can<BR>be disqualified for dangerous behaviour.<BR><BR>The
'laser scanner' rule however makes no sense in this form, as there<BR>is no
requirement that robots have any laser scanners on them.<BR>> - Why does
the robot just have one try to solve a subtask? What <BR>> happens, if the
robot fails to grasp the object. Is it not allowed to <BR>> try to grasp
the object again? What happens, if a robot identifies an <BR>> object,
which is not graspable for it? Can it then identify another <BR>> one to
grasp it? How do the referees know that a robot tried to solve <BR>> a
sub-task? Or is meant, that a robot will just get 1 time points for <BR>>
identifying and grasping etc? We suggest to delete this rule /
sentence.<BR>The idea behind this is that it should not be possible to solve
the task<BR>by just getting as many objects as possible in the time,
without<BR>explicitly identifying them.<BR>But your objections are right. I
would suggest making this less<BR>restrictive by giving a penalty for
unsuccessfully grasping an object,<BR>or grasping the wrong one, as (in a
similar form) in Who is Who.<BR>><BR>>
----------------------------------------------------------------<BR>> Who
Is Who:<BR>>
----------------------------------------------------------------<BR>> - We
suggest, that the provided names are common / easy names.<BR>This is how it is
planned to be. We'll have to work on a clearer<BR>definition of that point.
Maybe a general rule would make sense, as for<BR>the predefined
objects.<BR>> - We suggest, that if the robot stands next to a person (in
range of 1 <BR>> meter), that it is allowed to advise the person to look
into the <BR>> camera. It should be to allowed that the robot always
(without being <BR>> next to a person) says, that the person should look
into the camera.<BR>It is intentional that the persons are not necessarily
looking into the<BR>camera to increase complexity. However, I would be okay
with saying that<BR>the robot may tell a person to look at it while trying to
recognize it.<BR>However, if the robot asks something to look into its camera
which isn't<BR>a human, this would result in a -150 points penalty, as it is
now.<BR>><BR>>
----------------------------------------------------------------<BR>>
Enhanced Who Is Who:<BR>>
----------------------------------------------------------------<BR>> - We
suggest, that if the robot stands next to a person (in range of 1 <BR>>
meter), that it is allowed to advise the person to look into the <BR>>
camera. It should be to allowed that the robot always (without being <BR>>
next to a person) says, that the person should look into the camera.<BR>see
above<BR>> - Who defines the graspable drinks? Can the team select own
drinks? We <BR>> suggest, that each team can select their own
drinks.<BR>I'd be okay with that.<BR>> - In this test also there is too few
time to solve all tasks. There <BR>> should be delivered just one or two
drinks.<BR>I think you're right, however if you look at the other stage 2
games,<BR>it's going to be pretty hard to achieve the full score there as
well, so<BR>you could say it's balanced in some kind of way.<BR>> - Is it
allowed to directly grasp all 3 drinks, or does one drink have <BR>> to be
grasped, then delivered and then the next drink grasp etc. This <BR>> will
be unfair for teams which have just one manipulator and / or are <BR>> not
able to carry more than one drink at a time. We suggest, that <BR>> either
all teams have to grasp one drink at a time, or it should be <BR>> allowed
to grasp all drinks in a row and put them back on the table to <BR>> get
the points for grasping.<BR>I wouldn't support that view. The task is to
deliver three drinks. If<BR>the robot has the ability to transport more than
one drink, then it is<BR>better suited for the task and at a justified
advance. I don't see why<BR>this should be unfair.<BR><BR>I'd say just
grasping drinks and putting them back is currently possible<BR>following the
rules, since it's not explicitly forbidden, however this<BR>will cost you
extra time if you're planning to actually deliver them.<BR><BR>> - What
does deliver mean? Does it mean to hand over the drink, or is <BR>> it ok
to have the drink at the robot and the robot says something like <BR>>
"Here is youe Ice-Tea, please take it from my platform"?<BR>That's not
specified yet. We could split the points so handing over<BR>gives more points
than letting the user grab it from some kind of tray.<BR>> In sense of fair
play, we suggest, that every team is just allowed to <BR>> grasp and
deliver one drink at a time.<BR>I don't agree. If a robot is able to deliver
multiple objects at the<BR>same time, why not reward that?<BR>> - Since the
highest score last year was only 1050 points, we suggest, <BR>> that this
test is not furhter complicated. We suggest either to take <BR>> the test
of the last year, or to reduce the complexity of the test. <BR>> Our
suggestion is the following: The order for the drinks is given, <BR>> then
it is searched for persons (before grasping), if the first person <BR>> is
found, it is identified and the correct drink is delivered. Then it <BR>>
is searched for the next person and the according drink is delivered. <BR>>
Otherwise it is luck, if you grasp a drink and find the corresponding <BR>>
person (e.g. it could be, that you find all persons, but not the <BR>>
person whose drink the robot grasped at the beginning).<BR>The persons move by
max. 2 meters and don't change their pose<BR>(standing/sitting), so you can
search for persons first and then decide<BR>to which person you deliver the
drink. The problem of re-encoutering the<BR>same person is less difficult than
finding him/her in the first place.<BR>> - We further suggest, that the
team places the drinks, such that the <BR>> robot could grasp them. This
esures, that the drinks stand not too <BR>> close to each other or too far
away (out of the range for grasping)<BR>This would mean the robot does not
have to recognize the drinks, as you<BR>can put them in a predefined position.
So I don't agree on that.<BR><BR>We should define general constraints on the
placement of objects in this<BR>test, however. Maybe there should be a general
rule for all tests (e.g.<BR>max. 15cm from border, min. 15cm space between
objects).<BR>><BR>>
----------------------------------------------------------------<BR>>
General Purpose Service Robot<BR>>
----------------------------------------------------------------<BR>> -
Task is too abstract. It has to be more conrete.<BR>We're working on that in
the TC. If you have concrete suggestions, don't<BR>hesitate to tell
us.<BR>> - Are the speech commands given by a trained user? We suggest,
that <BR>> the speech commands are given by a team member.<BR>Sounds
plausible to me.<BR>><BR>>
----------------------------------------------------------------<BR>>
Shopping Mall<BR>>
----------------------------------------------------------------<BR>> - It
is not defined, whether the robot can grasp and deliver all <BR>>
three objects at a time. Due to fair play (robots which cannot carry <BR>>
more than one object or just have one manipulator), we suggest, that <BR>>
just one object can be delivered at a time.<BR>Same as for Enhanced Who's
Who.<BR>> - Once it is said, that the robot is guided by a team member, and
then <BR>> it is said that an unknown user shows the robot the three
location. We <BR>> suggest, that a team member guides the robot and gives
the speech <BR>> commands.<BR>That's contradictory, of course. I think that
a team member would be<BR>okay, regarding the overall complexity of this
test.<BR>> - How many objects are in each shelf? Are there many of the same
<BR>> objects standing very next to each other? To be able to grasp the
<BR>> objects, we suggest, that from each object just one is standing in
the <BR>> shelf with enough room around it to be able to grasp it.<BR>This
needs to be specified more clearly. However, I think it would
be<BR>interesting to have many objects of the same type standing next to
each<BR>other.<BR>> - Can good lighting conditions be assumed in this
test?<BR>This is probably going to be a real supermarket. There won't be
extra<BR>lighting. As far as my supermarket experience goes, this probably
means<BR>that there's going to be light from fluorescent lamps attached to
the<BR>ceiling.<BR><BR>Regards,<BR>David (team homer)<BR>><BR>><BR>>
Cheers,<BR>> Thomas (team b-it-bots)<BR>>
_______________________________________________<BR>> robocup-athome mailing
list<BR>> <A
href="mailto:robocup-athome@lists.robocup.org">robocup-athome@lists.robocup.org</A><BR>>
<A
href="http://lists.robocup.org/listinfo.cgi/robocup-athome-robocup.org">http://lists.robocup.org/listinfo.cgi/robocup-athome-robocup.org</A><BR>><BR><BR>_______________________________________________<BR>robocup-athome
mailing list<BR><A
href="mailto:robocup-athome@lists.robocup.org">robocup-athome@lists.robocup.org</A><BR><A
href="http://lists.robocup.org/listinfo.cgi/robocup-athome-robocup.org">http://lists.robocup.org/listinfo.cgi/robocup-athome-robocup.org</A></BLOCKQUOTE></BODY></HTML>