Half a croissant, on a plate, with a sign in front of it saying '50c'
h a l f b a k e r y
Naturally, seismology provides the answer.

idea: add, search, annotate, link, view, overview, recent, by name, random

meta: news, help, about, links, report a problem

account: browse anonymously, or get an account and write.




Social network that teaches virtual bots preparing them to become real ones
  [vote for,

New!!! Butler II now released. See it in action.
[Discuss with team] | [Buy Now] | [Join next version]

Welcome to DotBot.com the website game where you can teach robots a task, and give them feedback on how well they're doing. Rate other people's robots or join a group. Test them or race them against each other.

<placeholder for gallery of fantastic animated robots doing different things>

Currently we have over 7000 robots in 20 categories.

Sports | _Domestic_ | Security | Industrial | more...
:Domestic /Kitchen / Dish washing / Two Handed / Delicate

[Start discussion] [See plan versions] [Urgent!] [Filter] [Action]
::Left Hand:: ::Right Hand:: ::Eyes:: ::[DEFINE NEW PART]::
<hot water> | <cold water> | <towel> | <[DEFINE NEW OBJECT]>

Alice: At [5:47] you shouldn't touch anything besides the shelf when you are checking for dust
Bot: could you show me?
Charley: Requesting urgent interruption!
Alice: Granted.
Charley: ...

Share on [FB] [YouTube] [Twitter] [Pinterest] [Instagram] [Whatsapp]


On the back-end, each robot is a 3d animation controlled by an "API" which slowly evolves as people propose more "building blocks" of the commands needed to get the "virtual robot" to "understand" the human instructions.

The animations are created by the DotBot staff and are expected in the future to be replaced with actual parts that can interact with the public and do their designated jobs in the real world. Connected together these DotBotParts create a large foundation base for many different types shapes and sizes of robots.

So we are building on several layers of Artificial Intelligence here: Including fuzzy logic, networking, semantic webs, translation, multi-agent swarm intelligence, emergence and dynamic-learning systems.

At the user level, you will be telling the robot what you want it to do, and see it respond in animation. It has a listed goal and you are to teach it how to accomplish this.

There may be mentors and experts and monitoring staff, checking out that all goes well.

The instructions will be gathered up in "rules", "guidelines", "hints" and "recipes", so that for instance a chess playing robot would know to move the pieces only when its their turn, only their pieces and only to the permitted locations, and at the same time would know that it must defend the king, and that a rook is more important than a pawn. It would also use external programs such as algorithms just like a human can use a calculator for figuring the math (when appropriate).

pashute, Jun 03 2015


MaxwellBuchanan, Jun 04 2015

       sooooo... testing ?
FlyingToaster, Jun 04 2015


back: main index

business  computer  culture  fashion  food  halfbakery  home  other  product  public  science  sport  vehicle