annotate thesis/cortex.org @ 445:47cfbe84f00e

complete images in first third of first chapter.
author Robert McIntyre <rlm@mit.edu>
date Tue, 25 Mar 2014 03:18:04 -0400
parents d3c5f9b70574
children 3e91585b2a1c
rev   line source
rlm@425 1 #+title: =CORTEX=
rlm@425 2 #+author: Robert McIntyre
rlm@425 3 #+email: rlm@mit.edu
rlm@425 4 #+description: Using embodied AI to facilitate Artificial Imagination.
rlm@425 5 #+keywords: AI, clojure, embodiment
rlm@422 6
rlm@437 7
rlm@439 8 * Empathy and Embodiment as problem solving strategies
rlm@437 9
rlm@437 10 By the end of this thesis, you will have seen a novel approach to
rlm@437 11 interpreting video using embodiment and empathy. You will have also
rlm@437 12 seen one way to efficiently implement empathy for embodied
rlm@441 13 creatures. Finally, you will become familiar with =CORTEX=, a
rlm@441 14 system for designing and simulating creatures with rich senses,
rlm@441 15 which you may choose to use in your own research.
rlm@437 16
rlm@441 17 This is the core vision of my thesis: That one of the important ways
rlm@441 18 in which we understand others is by imagining ourselves in their
rlm@441 19 position and emphatically feeling experiences relative to our own
rlm@441 20 bodies. By understanding events in terms of our own previous
rlm@441 21 corporeal experience, we greatly constrain the possibilities of what
rlm@441 22 would otherwise be an unwieldy exponential search. This extra
rlm@441 23 constraint can be the difference between easily understanding what
rlm@441 24 is happening in a video and being completely lost in a sea of
rlm@441 25 incomprehensible color and movement.
rlm@435 26
rlm@436 27 ** Recognizing actions in video is extremely difficult
rlm@437 28
rlm@441 29 Consider for example the problem of determining what is happening in
rlm@441 30 a video of which this is one frame:
rlm@437 31
rlm@441 32 #+caption: A cat drinking some water. Identifying this action is
rlm@441 33 #+caption: beyond the state of the art for computers.
rlm@441 34 #+ATTR_LaTeX: :width 7cm
rlm@441 35 [[./images/cat-drinking.jpg]]
rlm@441 36
rlm@441 37 It is currently impossible for any computer program to reliably
rlm@442 38 label such a video as "drinking". And rightly so -- it is a very
rlm@441 39 hard problem! What features can you describe in terms of low level
rlm@441 40 functions of pixels that can even begin to describe at a high level
rlm@441 41 what is happening here?
rlm@437 42
rlm@441 43 Or suppose that you are building a program that recognizes
rlm@441 44 chairs. How could you ``see'' the chair in figure
rlm@441 45 \ref{invisible-chair} and figure \ref{hidden-chair}?
rlm@441 46
rlm@441 47 #+caption: When you look at this, do you think ``chair''? I certainly do.
rlm@441 48 #+name: invisible-chair
rlm@441 49 #+ATTR_LaTeX: :width 10cm
rlm@441 50 [[./images/invisible-chair.png]]
rlm@441 51
rlm@441 52 #+caption: The chair in this image is quite obvious to humans, but I
rlm@441 53 #+caption: doubt that any computer program can find it.
rlm@441 54 #+name: hidden-chair
rlm@441 55 #+ATTR_LaTeX: :width 10cm
rlm@441 56 [[./images/fat-person-sitting-at-desk.jpg]]
rlm@441 57
rlm@441 58 Finally, how is it that you can easily tell the difference between
rlm@441 59 how the girls /muscles/ are working in figure \ref{girl}?
rlm@441 60
rlm@441 61 #+caption: The mysterious ``common sense'' appears here as you are able
rlm@441 62 #+caption: to discern the difference in how the girl's arm muscles
rlm@441 63 #+caption: are activated between the two images.
rlm@441 64 #+name: girl
rlm@441 65 #+ATTR_LaTeX: :width 10cm
rlm@441 66 [[./images/wall-push.png]]
rlm@437 67
rlm@441 68 Each of these examples tells us something about what might be going
rlm@441 69 on in our minds as we easily solve these recognition problems.
rlm@441 70
rlm@441 71 The hidden chairs show us that we are strongly triggered by cues
rlm@441 72 relating to the position of human bodies, and that we can
rlm@441 73 determine the overall physical configuration of a human body even
rlm@441 74 if much of that body is occluded.
rlm@437 75
rlm@441 76 The picture of the girl pushing against the wall tells us that we
rlm@441 77 have common sense knowledge about the kinetics of our own bodies.
rlm@441 78 We know well how our muscles would have to work to maintain us in
rlm@441 79 most positions, and we can easily project this self-knowledge to
rlm@441 80 imagined positions triggered by images of the human body.
rlm@441 81
rlm@441 82 ** =EMPATH= neatly solves recognition problems
rlm@441 83
rlm@441 84 I propose a system that can express the types of recognition
rlm@441 85 problems above in a form amenable to computation. It is split into
rlm@441 86 four parts:
rlm@441 87
rlm@441 88 - Free/Guided Play :: The creature moves around and experiences the
rlm@441 89 world through its unique perspective. Many otherwise
rlm@441 90 complicated actions are easily described in the language of a
rlm@441 91 full suite of body-centered, rich senses. For example,
rlm@441 92 drinking is the feeling of water sliding down your throat, and
rlm@441 93 cooling your insides. It's often accompanied by bringing your
rlm@441 94 hand close to your face, or bringing your face close to
rlm@441 95 water. Sitting down is the feeling of bending your knees,
rlm@441 96 activating your quadriceps, then feeling a surface with your
rlm@441 97 bottom and relaxing your legs. These body-centered action
rlm@441 98 descriptions can be either learned or hard coded.
rlm@441 99 - Alignment :: When trying to interpret a video or image, the
rlm@441 100 creature takes a model of itself and aligns it with
rlm@441 101 whatever it sees. This can be a rather loose
rlm@441 102 alignment that can cross species, as when humans try
rlm@441 103 to align themselves with things like ponies, dogs,
rlm@441 104 or other humans with a different body type.
rlm@441 105 - Empathy :: The alignment triggers the memories of previous
rlm@441 106 experience. For example, the alignment itself easily
rlm@441 107 maps to proprioceptive data. Any sounds or obvious
rlm@441 108 skin contact in the video can to a lesser extent
rlm@441 109 trigger previous experience. The creatures previous
rlm@441 110 experience is chained together in short bursts to
rlm@441 111 coherently describe the new scene.
rlm@441 112 - Recognition :: With the scene now described in terms of past
rlm@441 113 experience, the creature can now run its
rlm@441 114 action-identification programs on this synthesized
rlm@441 115 sensory data, just as it would if it were actually
rlm@441 116 experiencing the scene first-hand. If previous
rlm@441 117 experience has been accurately retrieved, and if
rlm@441 118 it is analogous enough to the scene, then the
rlm@441 119 creature will correctly identify the action in the
rlm@441 120 scene.
rlm@441 121
rlm@441 122
rlm@441 123 For example, I think humans are able to label the cat video as
rlm@441 124 "drinking" because they imagine /themselves/ as the cat, and
rlm@441 125 imagine putting their face up against a stream of water and
rlm@441 126 sticking out their tongue. In that imagined world, they can feel
rlm@441 127 the cool water hitting their tongue, and feel the water entering
rlm@441 128 their body, and are able to recognize that /feeling/ as
rlm@441 129 drinking. So, the label of the action is not really in the pixels
rlm@441 130 of the image, but is found clearly in a simulation inspired by
rlm@441 131 those pixels. An imaginative system, having been trained on
rlm@441 132 drinking and non-drinking examples and learning that the most
rlm@441 133 important component of drinking is the feeling of water sliding
rlm@441 134 down one's throat, would analyze a video of a cat drinking in the
rlm@441 135 following manner:
rlm@441 136
rlm@441 137 1. Create a physical model of the video by putting a "fuzzy" model
rlm@441 138 of its own body in place of the cat. Possibly also create a
rlm@441 139 simulation of the stream of water.
rlm@441 140
rlm@441 141 2. Play out this simulated scene and generate imagined sensory
rlm@441 142 experience. This will include relevant muscle contractions, a
rlm@441 143 close up view of the stream from the cat's perspective, and most
rlm@441 144 importantly, the imagined feeling of water entering the
rlm@443 145 mouth. The imagined sensory experience can come from a
rlm@441 146 simulation of the event, but can also be pattern-matched from
rlm@441 147 previous, similar embodied experience.
rlm@441 148
rlm@441 149 3. The action is now easily identified as drinking by the sense of
rlm@441 150 taste alone. The other senses (such as the tongue moving in and
rlm@441 151 out) help to give plausibility to the simulated action. Note that
rlm@441 152 the sense of vision, while critical in creating the simulation,
rlm@441 153 is not critical for identifying the action from the simulation.
rlm@441 154
rlm@441 155 For the chair examples, the process is even easier:
rlm@441 156
rlm@441 157 1. Align a model of your body to the person in the image.
rlm@441 158
rlm@441 159 2. Generate proprioceptive sensory data from this alignment.
rlm@437 160
rlm@441 161 3. Use the imagined proprioceptive data as a key to lookup related
rlm@441 162 sensory experience associated with that particular proproceptive
rlm@441 163 feeling.
rlm@437 164
rlm@443 165 4. Retrieve the feeling of your bottom resting on a surface, your
rlm@443 166 knees bent, and your leg muscles relaxed.
rlm@437 167
rlm@441 168 5. This sensory information is consistent with the =sitting?=
rlm@441 169 sensory predicate, so you (and the entity in the image) must be
rlm@441 170 sitting.
rlm@440 171
rlm@441 172 6. There must be a chair-like object since you are sitting.
rlm@440 173
rlm@441 174 Empathy offers yet another alternative to the age-old AI
rlm@441 175 representation question: ``What is a chair?'' --- A chair is the
rlm@441 176 feeling of sitting.
rlm@441 177
rlm@441 178 My program, =EMPATH= uses this empathic problem solving technique
rlm@441 179 to interpret the actions of a simple, worm-like creature.
rlm@437 180
rlm@441 181 #+caption: The worm performs many actions during free play such as
rlm@441 182 #+caption: curling, wiggling, and resting.
rlm@441 183 #+name: worm-intro
rlm@443 184 #+ATTR_LaTeX: :width 13cm
rlm@445 185 [[./images/worm-intro-white.png]]
rlm@437 186
rlm@437 187
rlm@441 188 #+caption: Body-centerd actions are best expressed in a body-centered
rlm@441 189 #+caption: language. This code detects when the worm has curled into a
rlm@441 190 #+caption: full circle. Imagine how you would replicate this functionality
rlm@441 191 #+caption: using low-level pixel features such as HOG filters!
rlm@441 192 #+name: grand-circle-intro
rlm@441 193 #+begin_listing clojure
rlm@441 194 #+begin_src clojure
rlm@441 195 (defn grand-circle?
rlm@441 196 "Does the worm form a majestic circle (one end touching the other)?"
rlm@441 197 [experiences]
rlm@441 198 (and (curled? experiences)
rlm@441 199 (let [worm-touch (:touch (peek experiences))
rlm@441 200 tail-touch (worm-touch 0)
rlm@441 201 head-touch (worm-touch 4)]
rlm@441 202 (and (< 0.55 (contact worm-segment-bottom-tip tail-touch))
rlm@441 203 (< 0.55 (contact worm-segment-top-tip head-touch))))))
rlm@441 204 #+end_src
rlm@441 205 #+end_listing
rlm@437 206
rlm@441 207 #+caption: The actions of a worm in a video can be recognized by
rlm@441 208 #+caption: proprioceptive data and sentory predicates by filling
rlm@441 209 #+caption: in the missing sensory detail with previous experience.
rlm@441 210 #+name: worm-recognition-intro
rlm@441 211 #+ATTR_LaTeX: :width 10cm
rlm@445 212 [[./images/worm-poses.png]]
rlm@437 213
rlm@441 214
rlm@441 215 One powerful advantage of empathic problem solving is that it
rlm@441 216 factors the action recognition problem into two easier problems. To
rlm@441 217 use empathy, you need an /aligner/, which takes the video and a
rlm@441 218 model of your body, and aligns the model with the video. Then, you
rlm@441 219 need a /recognizer/, which uses the aligned model to interpret the
rlm@441 220 action. The power in this method lies in the fact that you describe
rlm@441 221 all actions form a body-centered, rich viewpoint. This way, if you
rlm@441 222 teach the system what ``running'' is, and you have a good enough
rlm@441 223 aligner, the system will from then on be able to recognize running
rlm@441 224 from any point of view, even strange points of view like above or
rlm@441 225 underneath the runner. This is in contrast to action recognition
rlm@441 226 schemes that try to identify actions using a non-embodied approach
rlm@441 227 such as TODO:REFERENCE. If these systems learn about running as viewed
rlm@441 228 from the side, they will not automatically be able to recognize
rlm@441 229 running from any other viewpoint.
rlm@441 230
rlm@441 231 Another powerful advantage is that using the language of multiple
rlm@441 232 body-centered rich senses to describe body-centerd actions offers a
rlm@441 233 massive boost in descriptive capability. Consider how difficult it
rlm@441 234 would be to compose a set of HOG filters to describe the action of
rlm@441 235 a simple worm-creature "curling" so that its head touches its tail,
rlm@441 236 and then behold the simplicity of describing thus action in a
rlm@441 237 language designed for the task (listing \ref{grand-circle-intro}):
rlm@441 238
rlm@435 239
rlm@437 240 ** =CORTEX= is a toolkit for building sensate creatures
rlm@435 241
rlm@436 242 Hand integration demo
rlm@435 243
rlm@437 244 ** Contributions
rlm@435 245
rlm@436 246 * Building =CORTEX=
rlm@435 247
rlm@436 248 ** To explore embodiment, we need a world, body, and senses
rlm@435 249
rlm@436 250 ** Because of Time, simulation is perferable to reality
rlm@435 251
rlm@436 252 ** Video game engines are a great starting point
rlm@435 253
rlm@436 254 ** Bodies are composed of segments connected by joints
rlm@435 255
rlm@436 256 ** Eyes reuse standard video game components
rlm@436 257
rlm@436 258 ** Hearing is hard; =CORTEX= does it right
rlm@436 259
rlm@436 260 ** Touch uses hundreds of hair-like elements
rlm@436 261
rlm@440 262 ** Proprioception is the sense that makes everything ``real''
rlm@436 263
rlm@436 264 ** Muscles are both effectors and sensors
rlm@436 265
rlm@436 266 ** =CORTEX= brings complex creatures to life!
rlm@436 267
rlm@436 268 ** =CORTEX= enables many possiblities for further research
rlm@435 269
rlm@435 270 * Empathy in a simulated worm
rlm@435 271
rlm@436 272 ** Embodiment factors action recognition into managable parts
rlm@435 273
rlm@436 274 ** Action recognition is easy with a full gamut of senses
rlm@435 275
rlm@437 276 ** Digression: bootstrapping touch using free exploration
rlm@435 277
rlm@436 278 ** \Phi-space describes the worm's experiences
rlm@435 279
rlm@436 280 ** Empathy is the process of tracing though \Phi-space
rlm@435 281
rlm@441 282 ** Efficient action recognition with =EMPATH=
rlm@425 283
rlm@432 284 * Contributions
rlm@432 285 - Built =CORTEX=, a comprehensive platform for embodied AI
rlm@432 286 experiments. Has many new features lacking in other systems, such
rlm@432 287 as sound. Easy to model/create new creatures.
rlm@432 288 - created a novel concept for action recognition by using artificial
rlm@432 289 imagination.
rlm@426 290
rlm@436 291 In the second half of the thesis I develop a computational model of
rlm@436 292 empathy, using =CORTEX= as a base. Empathy in this context is the
rlm@436 293 ability to observe another creature and infer what sorts of sensations
rlm@436 294 that creature is feeling. My empathy algorithm involves multiple
rlm@436 295 phases. First is free-play, where the creature moves around and gains
rlm@436 296 sensory experience. From this experience I construct a representation
rlm@436 297 of the creature's sensory state space, which I call \phi-space. Using
rlm@436 298 \phi-space, I construct an efficient function for enriching the
rlm@436 299 limited data that comes from observing another creature with a full
rlm@436 300 compliment of imagined sensory data based on previous experience. I
rlm@436 301 can then use the imagined sensory data to recognize what the observed
rlm@436 302 creature is doing and feeling, using straightforward embodied action
rlm@436 303 predicates. This is all demonstrated with using a simple worm-like
rlm@436 304 creature, and recognizing worm-actions based on limited data.
rlm@432 305
rlm@436 306 Embodied representation using multiple senses such as touch,
rlm@436 307 proprioception, and muscle tension turns out be be exceedingly
rlm@436 308 efficient at describing body-centered actions. It is the ``right
rlm@436 309 language for the job''. For example, it takes only around 5 lines of
rlm@436 310 LISP code to describe the action of ``curling'' using embodied
rlm@436 311 primitives. It takes about 8 lines to describe the seemingly
rlm@436 312 complicated action of wiggling.
rlm@432 313
rlm@437 314
rlm@437 315
rlm@437 316 * COMMENT names for cortex
rlm@437 317 - bioland