Advancing Table Tennis Robots: PongFox Tests Service & Return Feature - Thoughts?

[Tony's Table Tennis]

I moved this subject to its own thread because it is not a subject about one specific person's footage and to restrict comments from people who are not on the authorized list would not be fair, especially when the comments are useful.

Hi Carl
This robot already has its own thread by its owner.

I posted in the video thread to get feedback from the dozen coaches who predominantly use that thread only.
i gather other users can use the owner's original thread.

https://www.tabletennisdaily.com/forum/topics/advancing-table-tennis-robots-pongfox-tests-service-return-feature-thoughts.31559/#post-415875

The owner feels coaches who use his technology will be "smart" coaches

I feel that robot is for beginners who hit the ball slow.
If I was to serve long and fast, that service return feed from the robot is so delayed and I will be sipping coffee waiting for the return, thus making the whole training out of sync.
Hence, I feel it will be a unsmart move to be using that robot for any proper training (don't need to be formal training schools like where I am at with good quality multiball feeders, it could just be club members training with each other will add more value than this robot serve return feature).

Owner argues robot "game changing features" - I agree to the delayness and unrealness and will change to the worse.
He argues data, I state, data is more important in game play than training drills.
I guess it is still some time until AI can take over us humans. for now, Humans, 11, robot 0

 

[Tony's Table Tennis]

This is an interesting idea. Reminds me of what I saw from Tom Lodziak's video with robot training.

Here it is:

<- Regarding the video I posted, I don't know how I feel about it being so thick. I think having a lower profile sensor would be the way to go if you can get it into that form factor.

Tony's feedback of getting match data (ball placement, even human positioning) would be pretty valuable as a value add for the next step in your research/production.

now that is a pad.

well, during match play, there are few teams in the world where video analysis (are employed) will provide data to the coaching team of match analysis
and no, you can't put these pads on the match table for real time data gathering lol

 

[UpSideDownCarl]

Hi Carl
This robot already has its own thread by its owner.

I posted in the video thread to get feedback from the dozen coaches who predominantly use that thread only.
i gather other users can use the owner's original thread.

https://www.tabletennisdaily.com/forum/topics/advancing-table-tennis-robots-pongfox-tests-service-return-feature-thoughts.31559/#post-415875

The owner feels coaches who use his technology will be "smart" coaches

I feel that robot is for beginners who hit the ball slow.
If I was to serve long and fast, that service return feed from the robot is so delayed and I will be sipping coffee waiting for the return, thus making the whole training out of sync.
Hence, I feel it will be a unsmart move to be using that robot for any proper training (don't need to be formal training schools like where I am at with good quality multiball feeders, it could just be club members training with each other will add more value than this robot serve return feature).

Owner argues robot "game changing features" - I agree to the delayness and unrealness.
He argues data, I state, data is more important than game play than training drills.
I guess it is still some time until AI can take over us humans

Only problem is, it would not be right to not let someone like BrokenBall or anyone else make comments, especially when their comments are valid. And that thread is to restrict comments on people's play to people whose commentary would be valid. So this would be a hijacking of the thread with the clear result that anyone can comment.

So it does not belong in that thread.

However, you can ask them to comment hear. You can list them with something like: @Tony's Table Tennis, @Der_Echte, @NextLevel etc.

But this can't be in the thread that is for people asking for commentary on their technique that restricts who is allowed to answer.

 

[Tony's Table Tennis]

Only problem is, it would not be right to not let someone like BrokenBall or anyone else make comments, especially when their comments are valid. And that thread is to restrict comments on people's play to people whose commentary would be valid. So this would be a hijacking of the thread with the clear result that anyone can comment.

So it does not belong in that thread.

However, you can ask them to comment hear. You can list them with something like: @Tony's Table Tennis, @Der_Echte, @NextLevel etc.

But this can't be in the thread that is for people asking for commentary on their technique that restricts who is allowed to answer.

fair enough.

well, the three of you have commented.
me too.
so we 29% there haha

 

[UpSideDownCarl]

fair enough.

well, the three of you have commented.
me too.
so we 29% there haha

You can do that to anybody. I think it should give them a notification if you do.

@NDH , @Brs , @Richie , @Lula , @Takkyu_wa_inochi ......

 

[Tony's Table Tennis]

You can do that to anybody. I think it should give them a notification if you do.

@NDH , @Brs , @Richie , @Lula , @Takkyu_wa_inochi ......

just slow down.
i'm busy learning this feature (lol)

@Tinykin
@pingpongpaddy
@VictorMoraga
@cytivrat

Hi gents, that has been tagged - please see OP above.

Carl, I notice a couple of these members hasn't been around of late... continuing our "hijack thread".... one of the sad parts is loosing quality, contributing active posting members.

 

[palguay]

Hi Carl
This robot already has its own thread by its owner.

I posted in the video thread to get feedback from the dozen coaches who predominantly use that thread only.
i gather other users can use the owner's original thread.

https://www.tabletennisdaily.com/forum/topics/advancing-table-tennis-robots-pongfox-tests-service-return-feature-thoughts.31559/#post-415875

The owner feels coaches who use his technology will be "smart" coaches

I feel that robot is for beginners who hit the ball slow.
If I was to serve long and fast, that service return feed from the robot is so delayed and I will be sipping coffee waiting for the return, thus making the whole training out of sync.
Hence, I feel it will be a unsmart move to be using that robot for any proper training (don't need to be formal training schools like where I am at with good quality multiball feeders, it could just be club members training with each other will add more value than this robot serve return feature).

Owner argues robot "game changing features" - I agree to the delayness and unrealness and will change to the worse.
He argues data, I state, data is more important in game play than training drills.
I guess it is still some time until AI can take over us humans. for now, Humans, 11, robot 0

Can you share a video of your students doing service practice alone (not with a partner)?

 

[IB66]

Can you share a video of your students doing service practice alone (not with a partner)?

I think you mean ‘student doing serve and 3rd ball attack practice, alone!!’

 

[palguay]

I think you mean ‘student doing serve and 3rd ball attack practice, alone!!’

No just service practice

 

[Tony's Table Tennis]

I think you mean ‘student doing serve and 3rd ball attack practice, alone!!’

we hired caspers

 

[Tony's Table Tennis]

No just service practice

nah, not part of my queues at the moment

what does serve practice video have anything to do with your robot?
its different market segments
if you trying to justify that high level players should be using robots, then, its really talking apple vs oranges

 

[Tony's Table Tennis]

have to say, this little girl will be 10x more valuable for 3rd ball drills than the robot

she even talks to you and say, close your arm....transfer your weight

 

[palguay]

Hi Carl
This robot already has its own thread by its owner.

I posted in the video thread to get feedback from the dozen coaches who predominantly use that thread only.
i gather other users can use the owner's original thread.

https://www.tabletennisdaily.com/forum/topics/advancing-table-tennis-robots-pongfox-tests-service-return-feature-thoughts.31559/#post-415875

The owner feels coaches who use his technology will be "smart" coaches

I feel that robot is for beginners who hit the ball slow.
If I was to serve long and fast, that service return feed from the robot is so delayed and I will be sipping coffee waiting for the return, thus making the whole training out of sync.
Hence, I feel it will be a unsmart move to be using that robot for any proper training (don't need to be formal training schools like where I am at with good quality multiball feeders, it could just be club members training with each other will add more value than this robot serve return feature).

Owner argues robot "game changing features" - I agree to the delayness and unrealness and will change to the worse.
He argues data, I state, data is more important in game play than training drills.
I guess it is still some time until AI can take over us humans. for now, Humans, 11, robot 0

Just to be clear to others who don't misunderstand, when I meant smart I do not mean the coaches who use this are smart , what I meant is the coaches who are able to think deeply and understand in what cases at what levels this can be useful and suggest it in those cases.

As far as delay, the the way smart coaches think will be you would be curious, saying ok what is the actual delay? Can I get some numbers? Can we compare it with an actual match scenario for different levels, get an idea, and then decide and not make decisions based on the first video of the product.

There are a lot of cases in which this does not make sense but cases where it is being used today,

For example, our city is known for it's horrible traffic and for a lot of people it is hard to take their kids to the club each day so what the coaches suggest is that they give them drills to train on the robot on days they are not able to come to the club, and then they focus on the other things when they are able to make it to the club.

 

[palguay]

Since TT is filled with conditions, it would be interesting to create a Bayesian model to analyze a person's serve and predict the likelihood of what the server will give. Something like this paper for tennis, but applied to table tennis would be interesting: https://summit.sfu.ca/item/34899

From there, it would get rather complicated because you're coming up with a lot of situational context.

Granted, the system would be entirely different that what was proposed. Would need more of a grid sensor system or a computer vision system to get that going, so that just adds on to the expense. Even when practicing something like a Backspin Pendulum, it would be helpful to understand where the placement ends up going when drilling. The output can even be represented as a heatmap.

Great suggestion but realistically this takes time and effort and might be a longer goal but the shorter version can be to say record personal matches and analyse say one kind of serve, say pre 2200 rating level. At this level people are not good at doing a banana flick and dropping the ball close to the net, so if you do a backspin with a lots of sidespin that does not go out of the table for them to attack, then the options are limited and can be mapped with the technology today and might be first step before going further

 

[palguay]

nah, not part of my queues at the moment

what does serve practice video have anything to do with your robot?
its different market segments
if you trying to justify that high level players should be using robots, then, its really talking apple vs oranges

Not really, I have something in mind and wanted to use it as an example to show it as an example but I plan to do another video on how this relates to the pad.

 

[palguay]

Stroke technique, sure.

But the things that happen in random play where a player gets put out of position and has a habit that limits their ability to create certain shots....seeing the flaws that are brought out in game strategy, not sure there is a robot that can read that stuff and help a player fix it yet.

But the biggest issue is, seeing the opponent and what he does with the racket and how he creates shots, you don't get to read that stuff from a robot.

They are good for some things as people have pointed out. I definitely used a robot as part of what helped fix a broken FH stroke. But it did not help me read the opponent and it did not help me turn open to my FH better when I was locked in on my BH in a rally with a person.

exactly, the point is that these tools are to be used as an enhancement not replacement, once you understand what this will help with then it becomes easier to use it when required or make a decision to say it does or does not work for me

 

[palguay]

Oh I can see a lot of game reading landmines. The ball coming from a location where the serve did not go, the spin and speed on the returned ball not bring determined by the serve, no visual cue to read spin on the turn etc.

But maybe there are some benefits. I find that people csn improve with these things in ways I can't imagine but I think the negatives don't make it a reasonable substitute for real third ball drills.

Ok how about this case, the pad can be used when doing drills to track your consistency, it can show you how often you hit a target at a particular speed and frequence, or while doing drills at known places and randomized drills. Now as a player wouldn't it be helpful to realise where your consistency start declining and will help you to start working on that with something to measure with?

 

[Tony's Table Tennis]

As far as delay, the the way smart coaches think will be you would be curious, saying ok what is the actual delay? Can I get some numbers?

The ball already got behind the robot and busy dipping down and then your robot decides to feed it.
if you can't see that... than i'm not sure how else to tell you there is a massive delay.

you can do your own number crunching, since i'm not smart

 

[palguay]

Yes, but it is easy add a timer so the rattling around of the incoming ball is ignored for a period of time. In industrial controls we call this "debouncing" ... REALY! This is a common problem in many controls situations.

https://www.digikey.com/en/articles/how-to-implement-hardware-debounce-for-switches-and-relays

An accelerometer could be mounted to the table. It could detect when the ball bounces easily. Determining where the ball bounces on the table is much more difficult. Also, the computer would need to be able to tell if the bounce is the first bonce of a serve. This isn't hard because there is a long time interval before the next serve.

Determining were the ball bounces or where the ball is gets to be very expensive because it involves vision systems.

Thanks for the link. We did think of the accelerometer but in terms of getting something out in a short time without making significant changes to hardware this was a simple for us to deliver, hopefully that will be something to look into over a longer time once we can gather enough data about the usefulness of the tool

 

[palguay]

The ball already got behind the robot and busy dipping down and then your robot decides to feed it.
if you can't see that... than i'm not sure how else to tell you there is a massive delay.

you can do your own number crunching, since i'm not smart

The point is we chose the clips after filtering out the times where the players were hitting the ball to the net or missing them. in some cases there were others in the video frame and a lot of things to consider. In some cases when the balls were placed on the other side they were slow to reach.

This is an introduction to a new product the first thing we want the players to understand an idea of how it works.

We need to get those numbers to see how much is the delay when comparing it with a match scenario, sometimes a player might receive as soon as the ball bounces, sometimes they might wait for it to come closer to them, there are other cases wherein the players are using long pips or short pips what happens in those cases. only when such things are known a decision can be made on what delay means in different scenarios.

if we consider pro level sure there is a massive delay but what about cases where the rating is between 1000 to 2000?