Dear Professor Winston,

 

 I'm ready for you to look through the work that I've done so far. It's

 a sequence of posts describing the different simulated senses I've

 implemented, with videos. 

 

 It's "blocks world reloaded", because like you say, you need multiple

 senses to enable intelligence.

 

 Please look through the videos and skim the text and tell me what

 you think:

 

 Introduction:

 http://aurellem.org/cortex/html/intro.html

 http://aurellem.org/cortex/html/sense.html

 

 http://aurellem.org/cortex/html/body.html  -- simulated physical bodies

 http://aurellem.org/cortex/html/vision.html -- simulated eyes

 http://aurellem.org/cortex/html/hearing.html -- simulated ears

 http://aurellem.org/cortex/html/touch.html   -- simulated skin/hairs

 http://aurellem.org/cortex/html/proprioception.html -- simulated proprioception

 http://aurellem.org/cortex/html/movement.html       -- simulated muscles

 http://aurellem.org/cortex/html/integration.html  -- full demonstration 

 

 In particular, look at the video at

 http://aurellem.org/cortex/html/integration.html.  It shows a

 simulated hand equipped with all of the senses I've built so far.

 

 There's some more background information and full source code at 

 http://aurellem.org

 

 If you can't see a video, let me know and I'll upload it to YouTube so

 you can see it.

 

 

 

 

 Now, I need your help moving forward. Can I use this work as a base

 for a Masters thesis with you when I come back to MIT this coming Fall?

 What critiques and project ideas do you have after looking through

 what I've done so far?

 

 I have some ideas on where I can go with this project but I think you

 will have some better ones.

 

 Here are some possible projects I might do with this as a base that I

 think would be worthy Masters projects.

 

  - HACKER for writing muscle-control programs : Presented with

    low-level muscle control/ sense API, generate higher level programs

    for accomplishing various stated goals. Example goals might be

    "extend all your fingers" or "move your hand into the area with

    blue light" or "decrease the angle of this joint".  It would be

    like Sussman's HACKER, except it would operate with much more data

    in a more realistic world.  Start off with "calisthenics" to

    develop subroutines over the motor control API.  This would be the

    "spinal chord" of a more intelligent creature.

 

  - Create hundreds of small creatures and have them do simple

    simulated swarm tasks.

  

  - A joint that learns what sort of joint it (cone, point-to-point,

    hinge, etc.) is by correlating exploratory muscle movements with

    vision.

 

  - Something with cross-modal clustering using the rich sense

    data. This might prove difficult due to the higher dimensionality

    of my senses.

 

  - Simulated Imagination --- this would involve a creature with an

    effector which creates an /entire new sub-simulation/ where the

    creature has direct control over placement/creation of objects via

    simulated telekinesis. The creature observes this sub-world through

    it's normal senses and uses its observations to make predictions

    about it's top level world.

 

  - Hook it up with Genesis --- I could make a "semantic effector"

    which marks objects/sensory states with semantic information. In

    conjunction with Simulated Imagination, and HACKER-like motor

    control, Genesis might be able to ask simple questions like "stack

    two blocks together and hit the top one with your hand; does the

    bottom block move?" and the system could answer "yes".  This would

    be rather complicated to do and involves many of the above

    projects, but there may be a way to scale it down to Master's

    thesis size.

 

  - Make a virtual computer in the virtual world which with which the

    creature interacts using its fingers to press keys on a virtual

    keyboard. The creature can access the internet, watch videos, take

    over the world, anything it wants. (This is probably not worthy of

    a Masters project, I just thought it was a neat idea. It's possible

    to use videos/etc in the simulated world at any rate.)

 

 

 I can't wait to hear your critiques and ideas.  If you think I

 shouldn't use this system as a base and should instead do something

 else, that's fine too. 

 

 On a related note, can I be considered for the position of TA next

 year for 6.034 or 6.xxx?

 

 sincerely,

 --Robert McIntyre