Mercurial > cortex
changeset 461:b345650a0baa
complete first draft of final chapter.
author | Robert McIntyre <rlm@mit.edu> |
---|---|
date | Thu, 27 Mar 2014 18:17:23 -0400 |
parents | 763d13f77e03 |
children | bb81cef09ad7 |
files | thesis/cortex.org |
diffstat | 1 files changed, 26 insertions(+), 9 deletions(-) [+] |
line wrap: on
line diff
1.1 --- a/thesis/cortex.org Thu Mar 27 17:57:01 2014 -0400 1.2 +++ b/thesis/cortex.org Thu Mar 27 18:17:23 2014 -0400 1.3 @@ -1135,17 +1135,34 @@ 1.4 1.5 * Contributions 1.6 1.7 - I created =CORTEX=, a complete environment for creating simulated 1.8 - creatures. Creatures can use biologically inspired senses including 1.9 - touch, proprioception, hearing, vision, and muscle tension. Each 1.10 - sense has a uniform API that is well documented. =CORTEX= comes with 1.11 - multiple example creatures and a large test suite. You can create 1.12 - new creatures using blender, a free 3D modeling tool. I hope that 1.13 - =CORTEX= will prove useful for research ranging from distributed 1.14 - swarm creature simulation to further research in sensory 1.15 - integration. 1.16 + In this thesis you have seen the =CORTEX= system, a complete 1.17 + environment for creating simulated creatures. You have seen how to 1.18 + implement five senses including touch, proprioception, hearing, 1.19 + vision, and muscle tension. You have seen how to create new creatues 1.20 + using blender, a 3D modeling tool. I hope that =CORTEX= will be 1.21 + useful in further research projects. To this end I have included the 1.22 + full source to =CORTEX= along with a large suite of tests and 1.23 + examples. I have also created a user guide for =CORTEX= which is 1.24 + inculded in an appendix to this thesis. 1.25 1.26 + You have also seen how I used =CORTEX= as a platform to attach the 1.27 + /action recognition/ problem, which is the problem of recognizing 1.28 + actions in video. You saw a simple system called =EMPATH= which 1.29 + ientifies actions by first describing actions in a body-centerd, 1.30 + rich sense language, then infering a full range of sensory 1.31 + experience from limited data using previous experience gained from 1.32 + free play. 1.33 1.34 + As a minor digression, you also saw how I used =CORTEX= to enable a 1.35 + tiny worm to discover the topology of its skin simply by rolling on 1.36 + the ground. 1.37 + 1.38 + In conclusion, the main contributions of this thesis are: 1.39 + 1.40 + - =CORTEX=, a system for creating simulated creatures with rich 1.41 + senses. 1.42 + - =EMPATH=, a program for recognizing actions by imagining sensory 1.43 + experience. 1.44 1.45 # An anatomical joke: 1.46 # - Training