Mercurial > cortex

     1 Here I demonstrate the power of using embodied artificial intelligence

     2 to attack the \emph{action recognition} problem, which is the challenge of

     3 recognizing actions performed by a creature given limited data about

     4 the creature's actions, such as a video recording. I solve this

     5 problem in the case of a worm-like creature performing actions such as

     6 curling and wiggling. 

     7 

     8 To attack the action recognition problem, I developed a computational

     9 model of empathy (\texttt{EMPATH}) which allows me to recognize actions using

    10 simple, embodied representations of actions (which require rich

    11 sensory data), even when that sensory data is not actually available.

    12 The missing sense data is imagined by combining previous experiences

    13 gained from unsupervised free play. The worm is a five-segment

    14 creature equipped with touch, proprioception, and muscle tension

    15 senses. It recognizes actions using only proprioception data.

    16 

    17 In order to build this empathic, action-recognizing system, I created

    18 a program called \texttt{CORTEX}, which is a complete platform for embodied

    19 AI research. It provides multiple senses for simulated creatures,

    20 including vision, touch, proprioception, muscle tension, and hearing.

    21 Each of these senses provides a wealth of parameters that are

    22 biologically inspired. \texttt{CORTEX} is able to simulate any number of

    23 creatures and senses, and provides facilities for easily modeling and

    24 creating new creatures. As a research platform it is more complete

    25 than any other system currently available.
author	Robert McIntyre <rlm@mit.edu>
date	Sun, 19 Apr 2015 04:01:53 -0700
parents	202c6d19acad
children