Mercurial > cortex

comparison thesis/abstract.org @ 524:8e52a2802821

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
incorporating winston's changes.
author Robert McIntyre <rlm@mit.edu>
date Sun, 20 Apr 2014 21:46:46 -0400
parents c20de2267d39
children d304b2ea7c58
comparison
equal deleted inserted replaced
523:90b236381642 524:8e52a2802821
1 Here I demonstrate the power of using embodied artificial intelligence 1 Here I demonstrate the power of using embodied artificial intelligence
2 to attack the /action recognition/ problem, which is the challenge of 2 to attack the /action recognition/ problem, which is the challenge of
3 recognizing actions performed by a creature given limited data about 3 recognizing actions performed by a creature given limited data about
4 the creature's actions, such as a video recording. I solve this 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 5 problem in the case of a worm-like creature performing actions such as
6 curling and wiggling. 6 curling and wiggling.
7 7
8 To attack the action recognition problem, I developed a computational 8 To attack the action recognition problem, I developed a computational
9 model of empathy (=EMPATH=) which allows me to recognize actions using 9 model of empathy (=EMPATH=) which allows me to recognize actions using
10 simple, embodied representations of actions (which require rich 10 simple, embodied representations of actions (which require rich
11 sensory data), even when that sensory data is not actually 11 sensory data), even when that sensory data is not actually available.
12 available. The missing sense data is ``imagined'' by the system by 12 The missing sense data is ``imagined'' by the system by combining
13 combining previous experiences gained from unsupervised free play. 13 previous experiences gained from unsupervised free play. The worm is a
14 five-segment creature equipped with touch, proprioception, and muscle
15 tension senses. It recognizes actions using only proprioception data.
14 16
15 In order to build this empathic, action-recognizing system, I created 17 In order to build this empathic, action-recognizing system, I created
16 a program called =CORTEX=, which is a complete platform for embodied 18 a program called =CORTEX=, which is a complete platform for embodied
17 AI research. It provides multiple senses for simulated creatures, 19 AI research. It provides multiple senses for simulated creatures,
18 including vision, touch, proprioception, muscle tension, and 20 including vision, touch, proprioception, muscle tension, and hearing.
19 hearing. Each of these senses provides a wealth of parameters that are 21 Each of these senses provides a wealth of parameters that are
20 biologically inspired. =CORTEX= is able to simulate any number of 22 biologically inspired. =CORTEX= is able to simulate any number of
21 creatures and senses, and provides facilities for easily modeling and 23 creatures and senses, and provides facilities for easily modeling and
22 creating new creatures. As a research platform it is more complete 24 creating new creatures. As a research platform it is more complete
23 than any other system currently available. 25 than any other system currently available.