This user has no status.
This user has no status.
This user has no status.
Member
Next Level AI: Use a ball with no markers at all and give Ma Long a bat without sensors and we have the first miserable bot that cries for its mama! 
I don't know about JSH, but Harimoto will mess OMRON's electronics with his high pitch screams!!
Last edited:
This user has no status.
Active Member
AI at its best! 40 years ago I was only dreaming of such computing power. Now it seems the dream is coming true. AI possibly can beat any types of sport within my remaining years.
says
Hi TT Comunity!
Member
This user has no status.
This user has no status.
This user has no status.
Well-Known Member
That's the most entertaining TT video I've seen for ages!!! Dan should update the forum interface for giving 10 likes per post
That's the first robot I've seen with which (or with whom I should say) you can actually play (and lose badly...). Regular robots are just for practicing your technique as they can't return your ball. I saw a brief video of Timo Boll playing with Kukla (?) robot as he is sponsored by them. But it looked like a gimmick. This does not look so at all.
As mentioned before, it seems Dan wasn't giving a 100% for sure. I'd say maybe some 70%? Dan, you should evaluate your efforts on a 100% scale. That would be very interesting...
At the moment, the drawback of such setup IMHO is that the robot is too close to the table (I know, it sounds funny). It's not a problem with his reaction time to the incoming ball (obviously ), but the ability to control a very powerful ball and not to pop it too high over the table. It's a simple thing of physics of fast topspin ball bouncing high and long of the racket. Maybe robot should try super dead /defensive type of setup or practice ( )some super closed angle blocks or chop blocks to counter a heavy top spin rotation close to the table. This should be the first problem to address for the engineers...
That's the future of table tennis and in some 10 years I won't be surprised if we will start seeing such robots at table tennis clubs. You won't be needing a training partner any more.
Robot serving mechanism is hilarious. The net is super cool. They should make such for all tables
and that's the only chance for us
That's the first robot I've seen with which (or with whom
I should say) you can actually play (and lose badly...). Regular robots are just for practicing your technique as they can't return your ball. I saw a brief video of Timo Boll playing with Kukla (?) robot as he is sponsored by them. But it looked like a gimmick. This does not look so at all.As mentioned before, it seems Dan wasn't giving a 100% for sure. I'd say maybe some 70%? Dan, you should evaluate your efforts on a 100% scale. That would be very interesting...
At the moment, the drawback of such setup IMHO is that the robot is too close to the table (I know, it sounds funny). It's not a problem with his reaction time to the incoming ball (obviously
), but the ability to control a very powerful ball and not to pop it too high over the table. It's a simple thing of physics of fast topspin ball bouncing high and long of the racket. Maybe robot should try super dead /defensive type of setup or practice ( )some super closed angle blocks or chop blocks to counter a heavy top spin rotation close to the table. This should be the first problem to address for the engineers...That's the future of table tennis and in some 10 years I won't be surprised if we will start seeing such robots at table tennis clubs. You won't be needing a training partner any more.
Robot serving mechanism is hilarious. The net is super cool. They should make such for all tables
Harimoto will mess OMRON's electronics with his high pitch screams!!
and that's the only chance for us
Last edited:
This user has no status.
Well-Known Member
Considering the price of robot, that Dan mentioned and the 'big' money involved in table tennis, 10 years seems optimistic ...
This user has no status.
Frictionless anti spin on this robot... wouldn't even need to loop or smash, and it would beat the best in the world much faster!
Having said that, I think they envision it more as a training partner rather than a pro player to watch... but for publicity stunt, it could certainly be done much sooner
Having said that, I think they envision it more as a training partner rather than a pro player to watch... but for publicity stunt, it could certainly be done much sooner
This user has no status.
This user has no status.
Well-Known Member
Considering the price of robot, that Dan mentioned and the 'big' money involved in table tennis, 10 years seems optimistic ...
Maybe you are right. Let's wait and see
But... if this robot could replace at least partially a coach for lets say 30 usd/h and could work 8 hours a day 6 days a week....and it could be bought for lets say 100k (and I'd say that's a very pessimistic drop in the price for 10 years period) so
8 hours x 6 days x 4 weeks per month x 12 months per year x30usd=70k per year saved on a coach
so maybe not so utopian
This user has no status.
This user has no status.
Well-Known Member
This user has no status.
This user has no status.
Well-Known Member
i'd say it's not that too distant. Sony is (was?) making human shaped robots for fun. So lets say it's another 10 years
But to make it T1000 it's a whole new level
Last edited:
This user has no status.
Well-Known Member
Maybe you are right. Let's wait and see
But... if this robot could replace at least partially a coach for lets say 30 usd/h and could work 8 hours a day 6 days a week....and it could be bought for lets say 100k (and I'd say that's a very pessimistic drop in the price for 10 years period) so
8 hours x 6 days x 4 weeks per month x 12 months per year x30usd=70k per year saved on a coach
Jeez ... if the current AI has potential to replace a table tennis coach ... than who's job can be safe?
Well maybe not a coach, but a practice partner to some extend ...
This user has no status.
Well-Known Member
Then I guess the practice partners need to elevate their game
Jeez ... if the current AI has potential to replace a table tennis coach ... than who's job can be safe?
This user has no status.
This user has no status.
Well-Known Member
Jeez ... if the current AI has potential to replace a table tennis coach ... than who's job can be safe?
I'd say owners job will be safe. He won't have to pay coaches, less expenses, more profits, so maybe more TT clubs
. And engineers job will be safe too At this point it looks like the world's greatest return board. Doesn't seem like it can cover wide angles, back off the table, serving is rudimentary, etc. But nothing in principle prevents it from having superhuman reflexes, racket speed and ability to read spin and trajectory. Next year's version should be able to out-rally Ma Long if he plays within its limitations. Generating unreturnable serves should be almost trivial compared to what it can already do. Getting costs down while simulating more human-like play will be the real challenges over the next decade.
This user has no status.
This user has no status.
Member
Spinny serves are probably the easiest thing for it to handle because calculating the rotation on the ball is quite easy with front on sensors alone, not even including the ones on the bat.
The thing most difficult is to hit back anything fast and wide due to the limitation of how quickly the arm can move to position.
To beat a world champion... Depends on how much they're willing to invest. I think we have the technology to do this already actually. The frame and movement capability need to be way bigger, the electric motors need to be way faster, the machine learning capabilities to develop and implement actual winning strategies already exist, though. But having a machine to accurately move large distances in that speed and time is probably the most difficult and expensive part. Developing an incredibly good bordering on impossible to return serve should be one of the easier to do, but would most likely need a specific motor capabilities just for serving to actually implement it.
Last edited:
says
Spin and more spin.
says
Spin and more spin.
Well-Known Member
Super Moderator
When Dan gave the serves before the match, it returned them like one of those wily old penholders who puts the racket at the correct angle and just moves the racket forward a little to use the spin on the ball. hahaha.
hahaha.
This user has no status.
This user has no status.
Well-Known Member
I'd like to disagree. To move the racket fast enough is the easiest part. It can move so much quicker. The hardest part imho in this setup is to adjust the racket angle corectly to counter the spin and speed. We do it by adjusting our distance to the table, the force of our stroke and counterspinning the ball with full swing topspin. The robot is more or less blocking. So angle is crucial and subtle miscalculation can result in the ball flying of the table...
Sent from my SM-G935F using Tapatalk
This user has no status.
Active Member
This user has no status.
Active Member
Perhaps Adam Bobrow's snake under the table will confuse the robot lol...
Adam Bobrow's snake under the table will confuse the robot lol...Similar threads
