From rscherl at monmouth.edu Wed May 2 14:43:08 2007 From: rscherl at monmouth.edu (Scherl, Richard) Date: Wed May 2 14:43:14 2007 Subject: [Pyro-users] (no subject) In-Reply-To: <18093.216.12.72.114.1160741155.squirrel@webmail.brynmawr.edu> References: <18093.216.12.72.114.1160741155.squirrel@webmail.brynmawr.edu> Message-ID: <646CCA15396FD24586392DB998CCF0210BC3943C@WLB-EXCH-VS-01.monmouth.edu> I'm just wondering if anyone has updates to this information sent out back in October of last year. I'm looking to purchase 1 robot for use in an AI class. The idea is to use it for demos and so that students who have written Pyro programs to run under simulations can test their programs on a real robot. Has anyone tried Pyro with Erratic. I'm wondering how Erratic compares to the AmigoBot and how useful it is to have an onboard processor. Rich -----Original Message----- From: pyro-users-bounces@pyrorobotics.org [mailto:pyro-users-bounces@pyrorobotics.org] On Behalf Of dblank@brynmawr.edu Sent: Friday, October 13, 2006 8:06 AM To: pyro-users@pyrorobotics.org Subject: [Pyro-users] (no subject) Here's another option designed by Kurt Konolige that I did not know about: 7. Erratic, http://www.videredesign.com/robotics/. Looks to be an alternate platform to the Pioneer. Runs Linux and Player, so Pyro should work straight away. Videre Design specializes in Vision, and I may have to get their stereo vision option ($1400); that looks quite amazing and fast. (I also agree with Grant's warning about Ebay and Aibo... almost happened to me. Just don't send any money through Western Union, nor do any activity outside of Ebay and you should be safe.) If you want to see some reviews of some of these 7 mentioned robots, you should follow http://blog.roboteducation.org/ -Doug _______________________________________________ Pyro-users mailing list Pyro-users@pyrorobotics.org http://emergent.brynmawr.edu/mailman/listinfo/pyro-users William, This is the $64,000 question! Unfortunately, there is not a $64,000 answer. The answer will really depend on the details of what you want to explore, what you value, and how much money you want to spend. There are pros and cons to all of the following options, and maybe other will have their own opinions. But, here are some options (all of these have some type of vision, and either work with Pyro, or soon will): 1. Roomba, from iRobot. This option is quite cost-effective, and with some clever thinking, you can do a lot. I really think a modern robot has to have a camera, and you can put a laptop with a webcam on the roomba. My roomba is in the mail, so I can't personally can't comment yet on the recent additions to Pyro by James Snow that allow Pyro to control the roomba. (James's code looks excellent, though!) Also, Pyro's vision code currently only works under Linux. This isn't a self-contained robot though, so it will take a little work to get the laptop, software, webcam, and needed parts. 2. ePuck, from GCtronic. I'm just starting to test this out. It is a little pricey and small, but looks like a nice challenger to the Khepera, if you like desktop robotics. Pyro support should be easy (may use the exact same commands as Khepera, which is already supported). 3. Hemisson, from K-Team, and RoadNarrows. A little pricey (once you add all of the needed attachments) and is missing odometry (which the Aibo never had). The vision is done through a separate wireless analog connection. I have had issues with dropped connections, but I know Kim and Robin have been working on this for a couple of years. 4. Surveyor SRV-1, from Surveyor.com. I don't know very much about this one, but it looks like it might be able to quite a bit. I have one of these in the mail, too, so I'll know more in a week or two. 5. AmigoBot from MobileRobot.com. The smallest and cheapest (but still pricey) from the company that produces many robots for research. It can play wav files, has a wireless camera (like the Hemisson), and uses the standard MobileRobot interface. Pyro should work with it through the Player interface. I haven't had one for 8 years, so others might have more to say. 6. Pioneer from MobileRobot.com. The standard in research robotics. Very pricey, but very flexible. Comes in a variety of options (indoor, outdoor, PeopleBot, gripper, etc). There are some other options on the horizon (few months off), and this will surely be a topic at both AAAI Spring Symposium, and at SIGCSE. Any other ideas? -Doug William Yu wrote: > Greetings, > > > > Can anyone suggest an alternative hardware platform to AIBO? > > > > I recently (actual, it's been a few month now) received a small > internal grant to purchase 4-5 > > AIBO for my AI class using the PYRO. Unfortunately, although this > seems a pretty good idea > > when I wrote the proposal in January, I can not get any AIBO now that > the money is available. > > I'm wondering if any of you could suggest an alternative to AIBO. I'm > looking for something that > > is relatively powerful and is supported by PYRO in the window's > environment. As for my AI class, > > I just wanted to do a few simple modules such as reactive control and > behavior-based control modules > > plus one other advanced module. Since it'll be just be a relatively > small part of the AI class, I'd really > > like to work with something that's sufficiently sophisticated yet > already supported by PYRO simulator > > so as to minimize the learning curve. That's also pretty much the > reason that I selected AIBO, besides it being so cool. > > > > Any help will be greatly appreciated! > > > > William Yu > > Computer Science > > Southern Illinois University Edwardsville > > > > > > > ---------------------------------------------------------------------- > -- > > _______________________________________________ > Pyro-users mailing list > Pyro-users@pyrorobotics.org > http://emergent.brynmawr.edu/mailman/listinfo/pyro-users _______________________________________________ Pyro-users mailing list Pyro-users@pyrorobotics.org http://emergent.brynmawr.edu/mailman/listinfo/pyro-users From nswoboda at clip.dia.fi.upm.es Fri May 4 06:17:40 2007 From: nswoboda at clip.dia.fi.upm.es (nswoboda@clip.dia.fi.upm.es) Date: Fri May 4 06:17:48 2007 Subject: [Pyro-users] (no subject) In-Reply-To: <646CCA15396FD24586392DB998CCF0210BC3943C@WLB-EXCH-VS-01.monmouth.edu> from "Scherl, Richard" at May 02, 2007 02:43:08 PM Message-ID: > Has anyone tried Pyro with Erratic. I'm wondering how Erratic compares > to the AmigoBot and how useful it is to have an onboard processor. Last year we bought an Amigobot and haven't been all that happy with it. We have never been able to get the WIFI working and have had problems with interferences with wireless video. In general they seem to be way too expensive (today) for what you get. This year we switched to the Erratic. We are just getting started with them so I can't say how well they work with Pyro but in general they are much nicer machines (nicer components, more modular, and more 'heavy duty' (compared to the amigobot's 'plastic' feeling)). Also we are excited about having a much nicer camera and the possibility to do video processing on-board the robot. Nik ____________________________________________________ White butterfly Darting among pinks- Whose Spirit? -Shiki From kwame at nmsu.edu Tue May 1 14:47:08 2007 From: kwame at nmsu.edu (kwame@nmsu.edu) Date: Fri May 4 22:29:43 2007 Subject: [Pyro-users] recurrent fuzzy neural net? Message-ID: <1178045228.46378b2cb9aa4@webmail.nmsu.edu> Hi, I am considering using Pyro to implement a recurrent fuzzy neural net. I see that a recurrent neural net is given and a fuzzy logic set is given. Would I then just modify the various weight functions to work with fuzzy logic? Sincerely, Kwame P.R. From dblank at brynmawr.edu Fri May 4 22:35:41 2007 From: dblank at brynmawr.edu (Douglas S. Blank) Date: Fri May 4 22:35:46 2007 Subject: [Pyro-users] recurrent fuzzy neural net? In-Reply-To: <1178045228.46378b2cb9aa4@webmail.nmsu.edu> References: <1178045228.46378b2cb9aa4@webmail.nmsu.edu> Message-ID: <17898.76.98.12.59.1178332541.squirrel@webmail.brynmawr.edu> On Tue, May 1, 2007 2:47 pm, kwame@nmsu.edu said: > Hi, > > I am considering using Pyro to implement a recurrent fuzzy neural net. I > see > that a recurrent neural net is given and a fuzzy logic set is given. Would > I > then just modify the various weight functions to work with fuzzy logic? Kwame, That sounds reasonable. Note that Pyro's Conx neural network code only implements Simple Recurrent Networks, but output node activations will be between -1 and 1. -Doug > Sincerely, > > Kwame P.R. > _______________________________________________ > Pyro-users mailing list > Pyro-users@pyrorobotics.org > http://emergent.brynmawr.edu/mailman/listinfo/pyro-users > -- Douglas S. Blank Associate Professor, Bryn Mawr College http://cs.brynmawr.edu/~dblank/ Office: 610 526 6501 From gschoep at gmail.com Tue May 8 02:47:17 2007 From: gschoep at gmail.com (Gary Schoep) Date: Tue May 8 02:47:22 2007 Subject: [Pyro-users] Installing Pyro - Player stage public key error Message-ID: <9bfdf01a0705072347r696a45fdh7d57aec87ef88bc5@mail.gmail.com> I am installing pyro on clean install of FC6. I get errors with either the player or the stage public key - warning: rpmts_HdrFromFdno: Header V3 DSA signature: NOKEY, key ID c17d8428 Public key for stage-2.0.3-fc6.i386.rpm is not installed So this text should be changed... or simply, as root: cd /etc/yum.repos.d/ wget http://pyrorobotics.org/pyrobot.repo Then, all you need to do is issue an install command as root: yum install player stage gazebo pyrobot That will find the RPMs and any other dependencies, and install them. That's it! Thanks, -- Gary Schoep gschoep@gmail.com -------------- next part -------------- An HTML attachment was scrubbed... URL: http://emergent.brynmawr.edu/pipermail/pyro-users/attachments/20070508/93f9d74f/attachment.htm From bthom at cs.hmc.edu Tue May 8 04:19:56 2007 From: bthom at cs.hmc.edu (belinda thom) Date: Tue May 8 04:20:04 2007 Subject: [Pyro-users] conx propagation question Message-ID: <1C982125-A9E4-4DD0-8C1F-E9ECBDBE4603@cs.hmc.edu> Hi, I'm writing today because I'm afraid I've made something more complicated than it needs to be. I have successfully trained a network using cross validation (wrote my own train method loosely using some of Lisa's examples so I could control the termination conditions very finely). Now I want to display what's learned (its a 1-d input, fitting a polynomial, with a 1-d output and several hidden units) in the form of a curve. But I wasn't sure the easiest way to propagate a bunch of new values through the net. Here's what I ended up using. Its pretty icky; I'd have liked a "test network with these inputs" function, but couldn't find one. Any tips greatly appreciated. Thx, --b # estimate curve network.loadWeightsFromFile(__name__+'.weights') network.setLearning(0) network.setOrderedInputs(True) global gridRes _tmpX = pylab.linspace(mn,mx,gridRes) tmpX = [[float(x)] for x in _tmpX] tmpY = [[0.0] for x in _tmpX] # some bogus thing so we can sweep network.setInputs(tmpX) network.setOutputs(tmpY) # w/o same number of targets, can't sweep for layer in network.layers : name = layer.name network.logLayer(name,__name__+'.est.'+name+'s') network.sweep() for layer in network.layers : name = layer.name network.closeLog(name) _tmpY = [] try : f = open(__name__+'.est.outputs') for line in f : o = float(line) _tmpY += [o] f.close() except: assert False, "bogus" pylab.figure(f1.number) pylab.plot(_tmpX,_tmpY,'--') From dblank at brynmawr.edu Tue May 8 12:37:05 2007 From: dblank at brynmawr.edu (Douglas S. Blank) Date: Tue May 8 12:37:10 2007 Subject: [Pyro-users] Installing Pyro - Player stage public key error In-Reply-To: <9bfdf01a0705072347r696a45fdh7d57aec87ef88bc5@mail.gmail.com> References: <9bfdf01a0705072347r696a45fdh7d57aec87ef88bc5@mail.gmail.com> Message-ID: <12755.201.238.234.98.1178642225.squirrel@webmail.brynmawr.edu> Hmmm... wonder what changed? I re-signed the rpms; let me know if you still get the error with "gpgcheck=1". So, you are saying it works with "gpgcheck=0" in the pyrobot.repo file? -Doug On Tue, May 8, 2007 2:47 am, Gary Schoep said: > I am installing pyro on clean install of FC6. I get errors with either > the > player or the stage public key - > > warning: rpmts_HdrFromFdno: Header V3 DSA signature: NOKEY, key ID > c17d8428 > > Public key for stage-2.0.3-fc6.i386.rpm is not installed > > So this text should be changed... > > or simply, as root: > > cd /etc/yum.repos.d/ > wget http://pyrorobotics.org/pyrobot.repo > > Then, all you need to do is issue an install command as root: > > yum install player stage gazebo pyrobot > > That will find the RPMs and any other dependencies, and install them. > That's it! > > > Thanks, > > -- > Gary Schoep > gschoep@gmail.com > _______________________________________________ > Pyro-users mailing list > Pyro-users@pyrorobotics.org > http://emergent.brynmawr.edu/mailman/listinfo/pyro-users > -- Douglas S. Blank Associate Professor, Bryn Mawr College http://cs.brynmawr.edu/~dblank/ Office: 610 526 6501 From dblank at brynmawr.edu Tue May 8 12:48:13 2007 From: dblank at brynmawr.edu (Douglas S. Blank) Date: Tue May 8 12:48:17 2007 Subject: [Pyro-users] conx propagation question In-Reply-To: <1C982125-A9E4-4DD0-8C1F-E9ECBDBE4603@cs.hmc.edu> References: <1C982125-A9E4-4DD0-8C1F-E9ECBDBE4603@cs.hmc.edu> Message-ID: <12671.201.238.234.98.1178642893.squirrel@webmail.brynmawr.edu> Yes, that was a bit icky :) You should be able to use the step() method passing in layernames and activation values, like: # estimate curve network.loadWeightsFromFile(__name__+'.weights') network.setLearning(0) global gridRes _tmpX = pylab.linspace(mn,mx,gridRes) _tmpY = [] for x in _tmpX: _tmpY += network.step(input = [float(x)]) pylab.figure(f1.number) pylab.plot(_tmpX,_tmpY,'--') I forget what step() will return with one output layer, with one unit, but this should get you in the ballpark. -Doug On Tue, May 8, 2007 4:19 am, belinda thom said: > Hi, > > I'm writing today because I'm afraid I've made something more > complicated than it needs to be. > > I have successfully trained a network using cross validation (wrote > my own train method loosely using some of Lisa's examples so I could > control the termination conditions very finely). Now I want to > display what's learned (its a 1-d input, fitting a polynomial, with a > 1-d output and several hidden units) in the form of a curve. But I > wasn't sure the easiest way to propagate a bunch of new values > through the net. > > Here's what I ended up using. Its pretty icky; I'd have liked a "test > network with these inputs" function, but couldn't find one. Any tips > greatly appreciated. > > Thx, > > --b > > > > # estimate curve > network.loadWeightsFromFile(__name__+'.weights') > network.setLearning(0) > network.setOrderedInputs(True) > global gridRes > _tmpX = pylab.linspace(mn,mx,gridRes) > tmpX = [[float(x)] for x in _tmpX] > tmpY = [[0.0] for x in _tmpX] # some bogus thing so we can > sweep > network.setInputs(tmpX) > network.setOutputs(tmpY) # w/o same number of targets, can't > sweep > for layer in network.layers : > name = layer.name > network.logLayer(name,__name__+'.est.'+name+'s') > network.sweep() > for layer in network.layers : > name = layer.name > network.closeLog(name) > > _tmpY = [] > try : > f = open(__name__+'.est.outputs') > for line in f : > o = float(line) > _tmpY += [o] > f.close() > except: > assert False, "bogus" > pylab.figure(f1.number) > pylab.plot(_tmpX,_tmpY,'--') > > _______________________________________________ > Pyro-users mailing list > Pyro-users@pyrorobotics.org > http://emergent.brynmawr.edu/mailman/listinfo/pyro-users > -- Douglas S. Blank Associate Professor, Bryn Mawr College http://cs.brynmawr.edu/~dblank/ Office: 610 526 6501 From nswoboda at clip.dia.fi.upm.es Thu May 17 11:55:32 2007 From: nswoboda at clip.dia.fi.upm.es (nswoboda@clip.dia.fi.upm.es) Date: Thu May 17 11:55:43 2007 Subject: [Pyro-users] Pyro with the Erratic Message-ID: Hello. I have been working on getting the Erratic robot to work with pyro. The robot comes with a patched version of player 2.0.3 which seems to work well. I can start up the server and control the robot using playerjoy, playerv etc. After some struggle I now have pyro running on the Erratic's on-board PC (Ubuntu), but when I try to connect to the Player6665 robot from inside pyro I get the following on the console: calling connect done accepted client 0 on port 6665, fd 9 calling connect done playerc error : connect call on [localhost:7000] failed with error [111:Connection refused] playerc warning : warning : no socket to write to playerc error : failed to get response One strange thing is that neither playerjoy nor playerv seem to try to do the second connect. Any ideas regarding what is going wrong? Thanks, Nik ____________________________________________________ The rose of yore is but a name, mere names are left to us. From dblank at brynmawr.edu Thu May 17 12:09:23 2007 From: dblank at brynmawr.edu (Douglas S. Blank) Date: Thu May 17 12:10:23 2007 Subject: [Pyro-users] Pyro with the Erratic In-Reply-To: References: Message-ID: <464C7E33.4060902@brynmawr.edu> Nik, That may not be a problem---it is probably just Pyro trying to connect to port 7000 which is used by the simulation interface. Does everything work ok? -Doug nswoboda@clip.dia.fi.upm.es wrote: > Hello. > > I have been working on getting the Erratic robot to work with > pyro. The robot comes with a patched version of player 2.0.3 > which seems to work well. I can start up the server and control > the robot using playerjoy, playerv etc. > > After some struggle I now have pyro running on the Erratic's > on-board PC (Ubuntu), but when I try to connect to the Player6665 > robot from inside pyro I get the following on the console: > > calling connect > done > accepted client 0 on port 6665, fd 9 > calling connect > done > playerc error : connect call on [localhost:7000] failed with error [111:Connection refused] > playerc warning : warning : no socket to write to > playerc error : failed to get response > > One strange thing is that neither playerjoy nor playerv seem to > try to do the second connect. Any ideas regarding what is going > wrong? > > Thanks, > > Nik > ____________________________________________________ > > The rose of yore is but a name, mere names are left to us. > _______________________________________________ > Pyro-users mailing list > Pyro-users@pyrorobotics.org > http://emergent.brynmawr.edu/mailman/listinfo/pyro-users > From nswoboda at clip.dia.fi.upm.es Thu May 17 13:49:28 2007 From: nswoboda at clip.dia.fi.upm.es (nswoboda@clip.dia.fi.upm.es) Date: Thu May 17 13:49:34 2007 Subject: [Pyro-users] Pyro with the Erratic In-Reply-To: <464C7E33.4060902@brynmawr.edu> from "Douglas S. Blank" at May 17, 2007 12:09:23 PM Message-ID: > That may not be a problem---it is probably just Pyro trying to connect > to port 7000 which is used by the simulation interface. Yes, simulation[0] was the last thing in the pyro message area. > Does everything work ok? I can get the pan/tilt to work, and I get sensor info but I don't think that it is correct. However, the motors don't become enabled so I can't try moving it. I haven't started on the firewire stereo camera yet. Nik ____________________________________________________ When it's cold, water freezes into ice; when it's warm, ice melts into water. Similarly, when you are confused, essence freezes into mind; when you are enlightened, mind melts into essence. -Muso Kokushi From dblank at cs.brynmawr.edu Tue May 29 15:31:38 2007 From: dblank at cs.brynmawr.edu (Douglas S. Blank) Date: Tue May 29 15:31:46 2007 Subject: [Pyro-users] Want to run the Pyrobot Simulator 2300 times faster? Message-ID: <465C7F9A.4040808@cs.brynmawr.edu> I've updated some notes on the page: http://pyrorobotics.org/?page=PyroFromPython in the section named "1.2 Even Faster!" I've added some details about how to make the Pyrobot Simulator run much faster by eliminating the threads, brains, and engines. This relies on talking to the simulator directly. It is a raw but fast interface. This might be of use to those doing genetic algorithm or learning experiments. -Doug