Apprenticeship learning for robotic control, with application
to autonomous helicopter flight
Abstract
Many problems in control have unknown, stochastic, and highly
non-linear dynamics, and offer significant challenges to classical
control methods. Some of the key difficulties in these problems are
that (i) It is often hard to write down, in closed form, a formal
specification of the control task (for example, what is the objective
function for "driving well"?), (ii) It is difficult to learn good
control---as opposed to merely descriptive---models of the dynamics
(cf. the "exploration problem" in reinforcement learning), and (iii)
It is expensive to find closed-loop controllers for high dimensional,
highly stochastic domains. In this talk, I will present formal
results showing how these problems can be efficiently addressed in the
apprenticeship learning setting, in which expert demonstrations of the
task are available. I will also present an application of our ideas
to autonomous helicopter flight. Our results significantly extend the
state of the art in helicopter control, and include the first
successful completion of the following four aerobatic flight
maneuvers: in-place forward flip and sideways roll, nose-in
funnel, and tail-in funnel.
Bio:
Pieter Abbeel is a PhD student in Prof. Andrew Ng's group at Stanford
University. His research interests include machine learning,
robotics, and control.
Maintained by:
Fei Sha