Combat Robotics

[W. Rabbit]

There are a lot of factors that make this unfeasable at least right now. First off you have complexity. To realisitcally mimic the abilities of even a beginner boxer or grappler is a level of complexity that engineers have not been able to meet, if you can get a robot to pull an omoplata than you will get a free ride at any college you want.

I have degrees in electrical and computer engineering and information science, so I already have the necessary background to actually design/build/program this and a new job with more free time for my hobby: building robots. :)

I'll agree that reaching a human level of adaptability is a huge (personally I think impossible given the limitations of PAMs) task, but there is existing work being done today in this field that I can build on. The complexity really depends on the features/goals involved and this is why I am working on a series of progressively complex models, from simple punching, to turning and punching in a lateral plane, to swinging, etc. The idea is eventually all these prototypes could be combined into a single model.

That said its reasonably possible to make a scaled up rock-em sock-em robot but its not likely to be as reactive as a real human sparring partner. You could also in theory make a robot that resists or attempts to apply a basic lock but it would only really work in a specific situation and so would not be very useful as a training tool. Even this would be extremely difficult.

The standing punch/dummybots are easy compared to the grappling ideas, and I agree that building a robot that can submit a human is pie in the sky, however, the idea of a robot that RESISTS attempts to pin it down s quite within modern technology. Don't think so much "this robot can do judo", more along the lines of "this robot can help me become a stronger judoka".

You also have the problem of wearing out components. Anyone who uses grappling dummies or heavy bags know that no matter how heavy duty they are over time they wear out. Now ad complex components and the life span will drop significantly. Imagine putting your laptop in a heavy bag and wailing on it.

This is a very good point, and something I think I can deal with, but again, there are affordable shockproofing and protective options. They make "toughbooks" nearly indestructible laptops now for rough environements that you can throw against a wall without damage. PAMs can get fairly easily destroyed, but with some PVC armor and padding they'd probably have a long life. I'll have to worry about this though for sure.

I think we have all had the idea of a sparring bot at some point (usually when our sparring partner bailed on us for the 100th time) but the technology just isn't there yet.

Which is why I want to invent it. I've read a lot of Edison, Tesla, and Bell and if they all had one thing in common it was they were generally alone in believing there was future merit to their work. :)

Thanks for the comments.

[W. Rabbit]

What about them specifically?

Not sure yet but now I know who to ask when I do :)

This will probably come into play when I get around to modeling.

[Kickapoo]

Just out of curiousity, why would a gym pay 5,000 USD for something that they actually make money off of letting other people do?

[W. Rabbit]

Just out of curiousity, why would a gym pay 5,000 USD for something that they actually make money off of letting other people do?

Well that 5-10k figure is really just a cost target: I don't want the overall cost of materials to be over 10k because that is about the budget I have for the prototypes (which is why CAD modeling kicks ass....not going to waste too much on materials and trial and error, I can model all of this to perfection before I fab a single thing). Most of the components required in robots are cheap (this isn't 1985 when memory cost hundreds of dollars per KB).

But the overall market for conditioning tools is in the billions, and there is a noticeable lack of advanced equipment in the fighting/MA sphere, right? We still use pads, gloves, and dead targets while the musclebuilding and lifting people have all this 21st century ****. I want to make a foray into that untapped fighter's market (but for now, I just want to invent, not thinking about sales that's years away).

Why do people pay thousands and thousands for treadmills, when there are so many perfectly good roads/tracks?

This Nautilus unit costs $15,000.

A gym trainer who puts on gloves and lets you punch at him probably makes/costs a few times that.

[W. Rabbit]

Also, there are already robot boxers built for entertainment value (the robots are in the heavyweight (200+ lb) range, remote controlled and box each other) from the same people who founded Battlekits.com (if anyone remembers the BattleBots tv show from a few years back this is where they are now). So there is a lot to build on here, but I want to take this from toy/entertainment to something real that fighters can use to train. IT CAN BE DONE!





http://www.roboxers.com/robot_boxing_tips.htm

[W. Rabbit]

If anyone in Japan knows how I can get a copy of this, please let me know. Not that I read Japanese...but I am hoping for pictures.

+++
Accession number;00A0098585
Title;Analysis of Posture Control System of JUDO Robot and WAZA.

Author;OMAE SHIGEO(Univ. of Tsukuba) OTA MICHIO(Tsukubadai Kinokogakukei)

Journal Title;Jido Seigyo Rengo Koenkai Maezuri
Journal Code:F0989B
ISSN: VOL.42nd;NO.;PAGE.215-216(1999)
Figure&Table&Reference;FIG.4, TBL.2, REF.2
Pub. Country;Japan
Language;Japanese

Abstract;An experimental study was made on posture control of a JUDO robot as well as on the evaluation of techniques between biginners and experts. Biginners could not show an effective addition of force to the robot at first, which was possible to revise by tuning the robot control characteristics. (author abst.)
http://sciencelinks.jp/j-east/articl...00A0098585.php

[goodlun]

All I am going to say is don't listen to the naysayers, no matter how good of an idea one has their are always naysayers. Hell I have even seen plenty of horrible ideas go on to be commercially successful. Since you can do a lot of the work yourself the investment cost shouldn't be too bad and hell as long as you have fun while doing it what all does it really matter just don't go mortgaging the house or something.

[W. Rabbit]

All I am going to say is don't listen to the naysayers, no matter how good of an idea one has their are always naysayers. Hell I have even seen plenty of horrible ideas go on to be commercially successful. Since you can do a lot of the work yourself the investment cost shouldn't be too bad and hell as long as you have fun while doing it what all does it really matter just don't go mortgaging the house or something.

Lol thx. If you haven't figured out by now I get riled up and feverishly productive when confronted, which I why I chose BS.net and not some robotics nerd forum to engage with this. I think I found the right group of people to bash my ideas against, for sure.

There is WAY more interest in this sort of thing than anyone being outright dismissive, which is a good sign there is a niche to mine here. Let the nerds build R2D2s that fight each other for laughs. I want to build a robot that I can hit and will hit back.

[Permalost]

One of Da Vinci’s inventions that was recreated and on display at the San Diego Museum of Man was a suit of armor attached to a system of levers and pulleys that could be operated via a set of controls. The idea was to create a solution to the dangers of dueling by having inanimate surrogates duke it out.

[W. Rabbit]

One of Da Vinci’s inventions that was recreated and on display at the San Diego Museum of Man was a suit of armor attached to a system of levers and pulleys that could be operated via a set of controls. The idea was to create a solution to the dangers of dueling by having inanimate surrogates duke it out.

Is it this? I had never seen this before. THANKS!!!!!!!!



http://www.thetoyzone.com/2009/blog/...-war-machines/