Thread: Combat Robotics
11/15/2010 5:23pm, #51
11/15/2010 5:31pm, #52
Agreed that early conceptions/models will be a bit static, but static would not be the overall goal and its still better than soloing a heavy bag which people still do plenty of....that's dark ages **** in my opinion.
The aliveness is something that would come over time, as the approximations get better. Robotics research into human behavior is advancing like mad all over (including the #1 motivation: sex toys), so it's not too much of a stretch to think that you can approximate (somehow) various types of "live" training. That's the ultimate design goal, to build a tool that can imitate, as best as possible, "aliveness" for a solo user. I know it seems like an impossibility but I'm willing to work against that conception.
Computers can follow basic fighting principles pretty easy (don't try X if you're in state Y, if you see an advantage like State A, trigger). State machines can be as complex as they need to be, combined with targeting systems they're as accurate as hell.
I think a bot that moves and adds just a little randomness would still be better than hitting a dead target that never moves, or even better than punching at a human that never moves.
Last edited by W. Rabbit; 11/15/2010 5:36pm at .
11/15/2010 5:38pm, #53
11/15/2010 5:43pm, #54
Check this out dude:
"Toshiba's R&D Labs in Cambridge, UK have developed a system capable of real-time 3D modeling of the human face and body — using a simple set of three different colored lights. Simple it may be, but the results are impressive. Commercial applications for computer vision technology look set to be huge — according professor Roberto Cipolla. On the horizon: cheap and easy digitized everyday objects for ecommerce, plus gesture-based interfaces — a la Natal — and in-car safety systems. Ultimately even driver-less cars. 'This is going to be the decade of computer vision,' predicts Cipolla."
11/15/2010 5:51pm, #55
Some important data in those articles:
The human brain processes the gigabytes of data per second delivered through our eyes, enabling us to see and interact with our surroundings. Computer vision technology seeks to give machines the same ability - to process and act on visual data. For example, using a camera as its eye, a computer vision system could perform tasks such as recognising and following objects - something humans can do very easily but that computers have struggled to do until now.
It is also conjuring up a world of digitised objects - from everyday items you might sell on eBay to the human face and body, all perfectly captured in three dimensions where they can take on a whole new life of their own.
11/15/2010 6:00pm, #56
- Join Date
- Nov 2012
- San Diego
- street paddleboarding
Is processing data through some cameras enough to give a machine “depth perception”, ie will it know if it is close enough or too far away to hit a person?
11/15/2010 6:25pm, #57
IF this works it would be an amazing technical exercise.. But nobody would buy it.
You're creating a solution to a problem that doesn't exist.
You wanna practice fighting, you spar.
if you're a beginner and you need training, you get a coach."The hero and the coward both feel the same thing, but the hero projects his fear onto his opponent while the coward runs. 'Fear'. It's the same thing, but it's what you do with it that matters". - Cus D'Amato
11/15/2010 6:41pm, #58
11/15/2010 6:42pm, #59
- Join Date
- Mar 2009
- Baltimore, Maryland
Oh... never mind.
Last edited by Styygens; 11/15/2010 6:50pm at .
11/15/2010 7:24pm, #60
No one is close to making that sort of motion with robotics, let a lone stacking it up with other punches, movement, processing, vision etc.
I think it's an awesome idea but just not practical... Yet... Bags maybe old school but they're cheap and they work. Same with sparring partners, that 5k can go a long way in training the old fashioned way.