7
wowotek
6y

Opening Discussion Here,
I am trying to make a simple zen game that use Neural Network. the game is simple just a square object with a certain Viewing Angle and Viewing Distance with an objective is finding a food in a map with some other non food object as an obstacle.

i am encountered some problem. i am trying to find a way to make "seeing object in certain viewing region" and i am come up with two ideas described in the picture below. the problem is, i don't want to feed the NN with too much information, by that i mean i don't want to tell the AI what object it is, i want it to find out what it is by it self. and i cannot find a way to implement this either because of the framework limitation that i use (p5.js) or simply i cannot find a way how to.

i am on my way there tho, currently here i am (in pseudocode):
https://pastebin.com/7Ae1ZNYa

what do you think ?

Comments
  • 3
    in the picture on problem A there is a typo in the bottom, it supposed to be a viewing range
  • 4
    I thought it was a baseball field at first 🙃😂
  • 2
    @Stuxnet 😥😂😂😂 now i can't unsee it
  • 1
    If you're going for depth perception don't u need 2 cameras a fixed distance apart?
  • 0
    @saltyJeff maybe? i don't know. the point of solving this problem is finding the correct data to feed the NN without providing any information about the type of that object (food or not-food)
  • 0
    @irene my thoughts is to give the nn input with hunger parameter. and yet it only can eat the food
  • 0
    @irene yes i know, it described in edibility (if that even a word)
  • 0
    @irene Exactly 😂😂😂 i just finished implemented a thing with edibility < 0 (toxic)
  • 0
    @irene maybe, i don't know what will came out. i just want to see how it will act
Add Comment