perogiepro
perogiepro
99 / 13
24th Aug 2015
22nd Dec 2015
We are the SFPI, we are searching for mechanical life that can detect danger and think. essentialy basic AI. Our end goal is to make one that can replicate and change, so it will """evolve"""
machine intelligence experiment neuron life survival challange evolution spfi

Comments

  • Schmolendevice
    Schmolendevice
    26th Aug 2015
    BTW, in terms of neural networks and food searching, would it be a good idea to have the robot possess an 'orientation' so theoretically some neural outputs could make it 'turn' and define which direction is forwards? Either way since I haven't found DTEC to be reliable for directional reasoning, I'll be only using 1D gradient sensing.
  • Schmolendevice
    Schmolendevice
    26th Aug 2015
    @PTuniverse id:1845297 I placed a 'raw' version here with movement wifi coloured and labelled in a yellow/green colour though it's with my own decoration.
  • Schmolendevice
    Schmolendevice
    26th Aug 2015
    If you're talking about why the photon implementation didn't work, they used classic PCLN. Personally I'd try using cray instead to control PHOT's temperature. When it comes to editing the robot, I just use the PROP editor and play aroudn with the types I want after identifying which circuitry pertains to movement..
  • atomic2385
    atomic2385
    26th Aug 2015
    i dont kow. ask perogie pro, schmolendevice and msasterisk for better info. for the raw device ask perogie pro
  • PTuniverse
    PTuniverse
    26th Aug 2015
    What was the method of generation used in the photon test? Also, I need a raw version of the moving creature (no additions besides basic moving parts) to do my own developments.
  • atomic2385
    atomic2385
    26th Aug 2015
    @PTuniverse: yeah sure, its a collective thing. the main problems you can read in the comments. also look at the tests being done by msasterisk and schmolendevice. the most prominent problem is finding plant: photons burn it, so the machine uses dtec instead.
  • PTuniverse
    PTuniverse
    26th Aug 2015
    Seriously. I have a lot of knowledge about Powder Toy electronics. Just tell me the problem and I'd be more than happy to fix it for the project.
  • PTuniverse
    PTuniverse
    26th Aug 2015
    @atomic2385: Cool! Can I contribute? I've a lot of electronic knowledge to utilize, and I want to solve any problems that you guys encounter. It's about 3AM in my place though, so don't expect a response some time till the next 8-10 hours.
  • atomic2385
    atomic2385
    26th Aug 2015
    @PTuniverse: we are trying to make a machine that moves pseudo-randomly using a randomiser(the brain area) that when it detects plant(food) it moves towards it
  • atomic2385
    atomic2385
    26th Aug 2015
    i made a system to stop it self destructing when the dtec activates ID:1845345