rlm@425: #+title: =CORTEX=
rlm@425: #+author: Robert McIntyre
rlm@425: #+email: rlm@mit.edu
rlm@425: #+description: Using embodied AI to facilitate Artificial Imagination.
rlm@425: #+keywords: AI, clojure, embodiment
rlm@422: 
rlm@432: * Vision 
rlm@422: 
rlm@432:   System for understanding what the actors in a video are doing --
rlm@432:   Action Recognition.
rlm@432:   
rlm@432:   Separate action recognition into three components:
rlm@422: 
rlm@432:   - free play
rlm@432:   - embodied action predicates
rlm@432:   - model alignment 
rlm@432:   - sensory imagination
rlm@422: 
rlm@432: * Steps 
rlm@432:   
rlm@432:  - Build cortex, a simulated environment for sensate AI
rlm@432:    - solid bodies w/ joints
rlm@432:    - vision
rlm@432:    - touch
rlm@432:    - vision
rlm@432:    - hearing
rlm@432:    - proprioception
rlm@432:    - muscle contraction
rlm@425: 
rlm@432:  - Build experimental framework for worm-actions
rlm@432:   - embodied stream predicates
rlm@432:   - \phi-space 
rlm@432:   - \phi-scan
rlm@425: 
rlm@432: * News
rlm@432:   
rlm@432:   Experimental results:
rlm@425: 
rlm@432:   - \phi-space actually works very well for the worm!
rlm@432:   - self organizing touch map
rlm@425: 
rlm@425: 
rlm@432: * Contributions
rlm@432:   - Built =CORTEX=, a comprehensive platform for embodied AI
rlm@432:     experiments. Has many new features lacking in other systems, such
rlm@432:     as sound. Easy to model/create new creatures.
rlm@432:   - created a novel concept for action recognition by using artificial
rlm@432:     imagination. 
rlm@426: 
rlm@426: 
rlm@432: 
rlm@432: 
rlm@432: 
rlm@432: 
rlm@432: