Next: A Model for Control
Up: Mathematical Framework
Previous: The Inverse Observation Model
Models of Purposeful Motion
Figure 2.3:
Modeling tracking data of circular hand motion.
Passive physics alone leaves significant structure in the innovations
process. Top Left: Smoothing the innovations reveals unexplained
structure. Top Right: Plotting the Innovations along the path makes
the purposeful aspect of the action clear. Bottom: In
this example, using a learned control model to improve predictions leaves
only white process noise in the innovations process. The smoothed
innovations stay near zero.

[height=40mm]figs/circle-innovations-A
[height=40mm]figs/circle-innovations-B

[height=40mm]figs/circle-controlled-A
[height=40mm]figs/circle-controlled-B |
Observations of the human body reveal an interplay between the passive
evolution of a physical system (the human body) and the influences of a an
active, complex controller (the nervous system). Section 2.2.1
explains how, with a bit of work, it is possible to model the physical
aspects of the system. However, it is very difficult to explicitly
model the human nervous and muscular systems, so the approach of using
observed data to estimate probability distributions over control space is
very appealing.
Next: A Model for Control
Up: Mathematical Framework
Previous: The Inverse Observation Model
1999-06-15