awm@ai.mit.edu (Andrew W. Moore) (12/07/90)
About 2 years ago on British TV I think I remember seeing a robot playing snooker (a game like Pool) against a human professional (the robot lost). I'd be very grateful if anyone can tell me anything about this project or even confirm that I'm not imagining it. Andrew Moore awm@ai.mit.edu 617-253-4547 Room NE43-759, MIT AI Lab, 545 Technology Sq, Cambridge MA 02139
hollombe@ttidca.TTI.COM (The Polymath) (12/08/90)
In article <12247@life.ai.mit.edu> awm@ai.mit.edu (Andrew W. Moore) writes: } }About 2 years ago on British TV I think I remember seeing a robot }playing snooker (a game like Pool) against a human professional }(the robot lost). I'd be very grateful if anyone can tell me anything }about this project or even confirm that I'm not imagining it. You're not imagining it, though I saw it somewhat more than two years ago. As I recall, the robot lost because the human player knew how to put spin (aka English) on the ball for various special conditions while the robot could only do simple vector calculations. -- The Polymath (aka: Jerry Hollombe, M.A., CDP, aka: hollombe@ttidca.tti.com) Head Robot Wrangler at Citicorp(+)TTI Illegitimis non 3100 Ocean Park Blvd. (213) 450-9111, x2483 Carborundum Santa Monica, CA 90405 {csun | philabs | psivax}!ttidca!hollombe
pic@mlb.dmt.csiro.au (Peter Corke) (12/10/90)
A British pool playing robot is described in; Rennel, I.J., and Khodabadehloo, K. "Development of Skilled Robots: A new approach in robotics" Proc.Int.Symp.on Industrial Robots (20th ISIR) Tokyo, 1989. pp. 145-153 Peter ----- Peter Corke, PHONE: +61 3 487-9259 Senior Research Scientist INTERNET: pic@mlb.dmt.csiro.au CSIRO Div. Manufacturing Technology ACSNET or CSNET:pic@mimir.dmt.oz.au Melbourne, Australia. 3072
smithc@motcid.UUCP (Chris Smith) (12/10/90)
In article <12247@life.ai.mit.edu>, awm@ai.mit.edu (Andrew W. Moore) writes:
<
< About 2 years ago on British TV I think I remember seeing a robot
< playing snooker (a game like Pool) against a human professional
< (the robot lost). I'd be very grateful if anyone can tell me anything
< about this project or even confirm that I'm not imagining it.
<
< Andrew Moore
< awm@ai.mit.edu
< 617-253-4547
< Room NE43-759, MIT AI Lab, 545 Technology Sq, Cambridge MA 02139
Could you please summarize the information you receive and post the
results. I would be very interested in any information you might
receive.
--
o-------------------------------------------------------------------------o
o Chris Smith @ Motorola Inc. uunet!motcid!smithc o
o "Our great computers fill these hallowed halls..." - N. Peart o
o---------------------My thoughts, not my employer's----------------------o
lance@motcsd.csd.mot.com (lance.norskog) (12/11/90)
This brings up a subject dear to my heart: I'd like a robot fencing partner. Are there low-cost robots around which have the speed and flexibility to handle this? I've got the Power Glove already... Software for repetitive training drills shouldn't be a big problem :-) lance@motcsd.csd.mot.com
hollombe@ttidca.TTI.COM (The Polymath) (12/12/90)
In article <2323@greek.csd.mot.com> lance@motcsd.csd.mot.com (lance.norskog) writes: }This brings up a subject dear to my heart: I'd like a robot fencing }partner. Are there low-cost robots around which have the speed and }flexibility to handle this? I've got the Power Glove already... } }Software for repetitive training drills shouldn't be a big problem :-) I've heard the human arm has something over 30 degrees of freedom. I don't think there's anything commercially available that even comes close to that, let alone adding the flexibility of the human body supporting it. I can visualize your fencing partner being built around a nine or ten DOF hybrid arm with a force sensing gripper. You'd have to wear a position sensing garment to tell its controller where you were and what you were doing. The computing power required would be non-trivial, but doable with custom, dedicated hardware. The power needed to give it useful speed would also make it very dangerous. It still wouldn't behave like a human being, or even look much like one. As for low-cost, it could probably be kept under $1 million. If you could get the grants to pay for it and were willing to trust unpaid student labor for design, construction and programming it might be kept under $200K, but I doubt it. Paul Atreides wanna-bes are just going to have to wait for technology to catch up with their dreams. -- The Polymath (aka: Jerry Hollombe, M.A., CDP, aka: hollombe@ttidca.tti.com) Head Robot Wrangler at Citicorp(+)TTI Illegitimis non 3100 Ocean Park Blvd. (213) 450-9111, x2483 Carborundum Santa Monica, CA 90405 {csun | philabs | psivax}!ttidca!hollombe
dennisg@felix.UUCP (Dennis Griesser) (12/15/90)
In article <2323@greek.csd.mot.com> lance@motcsd.csd.mot.com (lance.norskog) writes: >This brings up a subject dear to my heart: I'd like a robot fencing >partner. Are there low-cost robots around which have the speed and >flexibility to handle this? I've got the Power Glove already... > >Software for repetitive training drills shouldn't be a big problem :-) I'm not sure how serious that request is, but it's a little scary. Think about it: a "low-cost robot" (read imprecise), with hacked-together software (read non-certified for safety-critical). Then you hand it a weapon (even though a training type) and get close enough for it to whack you? Not me, brother. How about taking your Power Glove, clamping on some Eyephones (or a cheaper equivalent), and firing up a Virtual Reality with a simulated partner to practice with. If the simulation breaks down, at least it doesn't thrash around with a foil!
rg@msel.unh.edu (Roger Gonzalez) (12/27/90)
In the movie "Silent Running" they show a robotic pool player. I'm not sure if it was just SFX or actually real. Looked neat. -Roger -- "The question of whether a computer can think is no more interesting than the question of whether a submarine can swim" - Edsgar W. Dijkstra rg@[msel|unhd].unh.edu | UNH Marine Systems Engineering Laboratory r_gonzalez@unhh.bitnet | Durham, NH 03824-3525