Group 3
Getting a robot to tie a shoe
We study in this report , what seems to
be a simple task of tying a shoelace. In part A + B we break this process into
smaller functions so they could be programmed into a robot with fingers and
cameras. As it turns out, in part C, it is extremely difficult to express what
goes on in the mind in form of language we use to speak. Most of our action result from thoughts which are implicit in terms of
discrete actions. In D we compare connectionist model with symbolic considering
that we have already expressed basic functions in A + B. In F we explore
various situations such as tension in string, length which has crossed
fingers, light, stability of ground, density of sensors in fingers(if we are
wearing gloves this effectively reduces).In part G we find out that seemingly
easy process of tying the shoes is a million dimensional problem when
considered in its raw form. This clarifies clear limitations of our language in
expressing our thoughts. After breaking it into smaller basic functions from B,
dimensionality reduces. These basic functions are created as a result of
practice. Then in I we propose a symbolic and
connectionist model to express this process or any physical process in general.
Videos:
Link to video of the robot performing Part 1 (first knot) of the
process (with step-wise instructions): http://www.youtube.com/watch?v=hi-6bCYpGYM
Link to video of the robot performing Part 2 (full bow knot) of
the process (with step-wise instructions): http://www.youtube.com/watch?v=v6eGFups1DA
Answers:
PPT: SE367.pptx