Mercurial > cortex

     1 #+title: =CORTEX=

     2 #+author: Robert McIntyre

     3 #+email: rlm@mit.edu

     4 #+description: Using embodied AI to facilitate Artificial Imagination.

     5 #+keywords: AI, clojure, embodiment

     6 

     7 -- show hand

     8 

     9 * Embodiment is a critical component to Intelligence

    10 

    11 * To explore embodiment, we need a world, body, and senses

    12 

    13 * Because of Time, simulation is perferable to reality

    14 

    15 * Video game engines are a great starting point

    16 

    17 * Bodies are composed of segments connected by joints

    18 

    19 * Eyes reuse standard video game components

    20 

    21 * Hearing is hard; =CORTEX= does it right

    22 

    23 * Touch uses hundreds of hair-like elements

    24 

    25 * Proprioception is the force that makes everything ``real''

    26 

    27 * Muscles are both effectors and sensors

    28 

    29 * =CORTEX= brings complex creatures to life!

    30 

    31 * =CORTEX= enables many possiblities for further research

    32 

    33 * =CORTEX= User Guide

    34 

    35 * Empathy in a simulated worm

    36 

    37 * Embodiment factors action recognition into managable parts

    38 

    39 * Action recognition is easy with a full gamut of senses

    40 

    41 * Digression: bootstrapping with multiple senses

    42 

    43 * \Phi-space describes the worm's experiences

    44 

    45 * Empathy is the process of tracing though \Phi-space 

    46   

    47 * Efficient action recognition via empathy

    48 

    49 * Contributions

    50 

    51 

    52 * Vision 

    53 

    54   System for understanding what the actors in a video are doing --

    55   Action Recognition.

    56   

    57   Separate action recognition into three components:

    58 

    59   - free play

    60   - embodied action predicates

    61   - model alignment 

    62   - sensory imagination

    63 

    64 * Steps 

    65   

    66  - Build cortex, a simulated environment for sensate AI

    67    - solid bodies w/ joints

    68    - vision

    69    - touch

    70    - vision

    71    - hearing

    72    - proprioception

    73    - muscle contraction

    74 

    75  - Build experimental framework for worm-actions

    76   - embodied stream predicates

    77   - \phi-space 

    78   - \phi-scan

    79 

    80 * News

    81   

    82   Experimental results:

    83 

    84   - \phi-space actually works very well for the worm!

    85   - self organizing touch map

    86 

    87 

    88 * Contributions

    89   - Built =CORTEX=, a comprehensive platform for embodied AI

    90     experiments. Has many new features lacking in other systems, such

    91     as sound. Easy to model/create new creatures.

    92   - created a novel concept for action recognition by using artificial

    93     imagination. 

    94 

    95 

    96 

    97 

    98 

    99 

   100
author	Robert McIntyre <rlm@mit.edu>
date	Sun, 23 Mar 2014 17:59:16 -0400
parents	1e5ea711857d
children	853377051f1e