Please refrain from posting animated GIFs, memes, joke videos and so on in discussions other than those in the off topic area.

Dismiss this message to confirm your acceptance of this additional forum term of use.
You must be 16 or over to participate in the Brickset Forum. Please read the announcements and rules before you join.

What Do You Guys Think of the FanPlanz Kickstarter?

akunthitaakunthita USAPosts: 913
edited May 14 in Everything else LEGO

I was tweeted about a Kickstarter campaign called FanPlanz. They claim they have the technology to build an app that recognizes individual elements from a pile, and can thus build a database of your LEGO collection, and then tell you what you can build. It sounds great, but I'm doubtful. What do you guys think? They also claim to be working on other things like looking at an object, and the app can tell you how to build it from LEGO. It just sounds too good to be true. But I could be wrong. Here is the link to the Kickstarter: https://www.kickstarter.com/projects/736931231/fanplanz-the-brick-plans-marketplace 

And here is the summary of what they are claiming to do:

FanPlanz uses the very latest in artificial intelligence and object recognition to make building Lego models with your kids an even more exciting experience. Simply take a picture of your Lego and FanPlanz is able to recognise and catalogue the size, shape and colour of every piece in your collection.

Knowing which bricks you have, allows FanPlanz to suggest new models for you to build. If you need extra bricks to complete a model we'll also ship those to you for a small fee.

Pretty soon you'll be able to take a picture of any inanimate, solid object and we'll be able to create a set of instructions to build that model "on-the-fly".

Later on we plan to launch brick robots which will be able to pick out pieces for you to reduce brick rummaging.

Where do the models come from we'll be selling? That’s where you come in. Brick model designers who want to sell their designs will be able to create plans and make them available for sale to the community. We know Lego fans love to develop new models and we’re hoping some of them will be interested in commercialising their hobby.

Comments

  • catwranglercatwrangler Northern IrelandPosts: 1,394
    Here's the link again; it's not working above:
    https://www.kickstarter.com/projects/736931231/fanplanz-the-brick-plans-marketplace

    I feel like it's a nice concept, but it's pretty much smushing together things we have already: Rebrickable, Bricklink... I'm not convinced people will want to pay for a service they're already getting from different websites. 

    I can't speak for how likely they are to succeed on a technical level, which is surely what matters; I just don't know enough about app building or the technologies involved. 
    akunthita
  • EvilTwinEvilTwin UKPosts: 60
    It'll be interesting to see if their app is able to tell the difference between, say, a 2x4 brick and a 2x4 plate, from above
    catwranglerakunthita
  • akunthitaakunthita USAPosts: 913

    EvilTwin said:

    It'll be interesting to see if their app is able to tell the difference between, say, a 2x4 brick and a 2x4 plate, from above



    Yeah, exactly, that's my concern. It make it sounds like the app will be able to recognize parts just being poured out on a table. With some parts I don't see how that would work. And if the app is only so-so, then it will become pretty useless.

    My understanding is that LEGO Fusion failed specifically because they couldn't make the technology work. And that was only with elements that were calibrated into the set, so it should have been much easier.

    I'm still going to watch this technology with curiosity, as it could be very useful. 

  • akunthitaakunthita USAPosts: 913

    @catwrangler, yeah, I also thought that they were mixing up way too many things. If they would just make that part-recognition app work, it would be a huge achievement and major breakthrough. If it works well, they could license the technology to other sites, even collaborate with LEGO, etc.

    But it seems like right now they just want to be the jack-of-all-trades, compete with currently well-established platforms. And the part-recognition app seems to be just a concept right now, with no proof that it would actually work. Because of this, I don't have much faith that they will achieve any of their goals, but we shall see...

    catwrangler
  • madforLEGOmadforLEGO USPosts: 7,720
    edited May 12
    Great, that is how the apocalypse starts.. with A.I. LEGO sorters. First they sort, then wonder why they have to do all the sorting instead of having fun building...
    catwranglerbandit778Galactus
  • catwranglercatwrangler Northern IrelandPosts: 1,394
    "It can't be bargained with. It can't be reasoned with. It doesn't feel pity, or remorse, or fear. And it absolutely will not stop until it can build!"
    bandit778BooTheMightyHamstersid3windrYodalicious
  • bobotechbobotech spokane, wa, usaPosts: 16
    I think the brick recognition could be viable if they try not to do too many things at once.  For example, you choose the colors.  So you choose "medium gray" or whatever and then lay out the bricks you want to be sorted into your database and you only pour out your medium gray bricks.   Maybe categorize the bricks by a type of brick, like slopes or round or square or technic or however most people sort their bricks out.  Then the software will only have to worry about the overall shape since it knows it will only be dealing with round medium gray bricks or square medium gray bricks or whatever.  
  • RogerKirkRogerKirk BrightonPosts: 166
    I would love something that would easily identify bricks. I wouldn't mind having to do basic sorting first, like others have suggested with colours. Or with having to carefully lay them out first, rather than a random pile.

    But it would need to be very accurate and also be very extensive so it could recognise almost all Lego pieces.

    If it fails on those points, it's not worth it.

    The rest of the features of this app, suggesting builds etc, is not something I'd be interested in so long as the parts list could be exported to other services.
  • HuwHuw Brickset Towers, Hampshire, UKPosts: 5,660
    I can't see them raising $250k for something as intangible as software that is unlikely to work fully, particularly given the rewards are equally intangible and pretty much worthless.
    Bumblepants
  • akunthitaakunthita USAPosts: 913

    Huw said:

    I can't see them raising $250k for something as intangible as software that is unlikely to work fully, particularly given the rewards are equally intangible and pretty much worthless.



    Yes, that's a very good point too. I wasn't even paying attention to how much they were trying to raise! :D
Sign In or Register to comment.
Recent discussions Categories Privacy Policy