UTCS Colloquium/AI: Chad Jenkins/Brown University: Learning in Human-Robot Teams TAY 3.128 Thursday September 11 2008 3:00 p.m.

Contact Name: 
Jenna Whitney
Date: 
Sep 11, 2008 3:00pm - 4:00pm

There is a signup schedule for this event (UT EID required).

Ty

pe of Talk: UTCS Colloquium/AI

Speaker/Affiliation: Chad Jenkins/Br

own University

Date/Time: Thursday September11 2008 3:00 p.m.

Location: TAY 3.128

Host: Bejamin Kuipers

Talk Title:
Learning in Human-Robot Teams

Talk Abstract:
A principal goal of
robotics is to realize embodied
systems that are effective collaborato

rs for human
endeavors in the physical world. Human-robot
collabora

tions can occur in a variety of forms
including autonomous robotic ass

istants mixed-
initiative robot explorers and augmentations of the
human body. For these collaborations to be effective
human users must
have the ability to realize their
intended behavior into actual robot

control policies.
At run-time robots should be able to manipulate an <

br>environment and engage in two-way communication
in a manner suitable
to their human users. Further the
tools for programming communicatin

g with and
manipulating using robots should be accessible to the
d

iverse sets of technical abilities present in society.

Towards the g

oal of effective human-robot collaboration
our research has pursued th

e use of learning and data-
driven approaches to robot programming comm

unication
and manipulation. Learning from demonstration (LfD) has

emerged as a central theme of our efforts towards natural
instruct of a

utonomous robots by human users. In robot
LfD the desired robot contro

l policy is implicit in human
demonstration rather than explicitly code

d in a computer
program.

In this talk I will describe our LfD-b

ased work in policy learning
using Gaussian Process Regression and huma

noid imitation
learning through spatio-temporal dimension reduction. Th

is work
is supported by our efforts in markerless inertial-based and

physics-based human kinematic tracking notably our indoor-
outdoor

person following system developed in collaboration with
iRobot Research

. I will additionally argue that collaboration in
human-robot teams can
be modeled by Markov Random Fields
(MRFs) allowing for unification of
existing multi-robot algorithms
application of belief propagation an

d faithful modeling of
experimental findings from cognitive science. Ti

me permitting
I will also discuss our work learning tactile and force

signatures
to distinguish successful versus unsuccessful grasping on th

e
NASA Robonaut.

Speaker Bio:
Odest Chadwicke Jenkins Ph.D.
is an Assistant Professor of
Computer Science at Brown University. Pro

f. Jenkins earned
his B.S. in Computer Science and Mathematics at Alma

College
(1996) M.S. in Computer Science at Georgia Tech (1998) and Ph.D. in Computer Science at the University of Southern California
(2

003). In 2007 he received Young Investigator funding from the
Office o

f Naval Research and the Presidential Early Career Award
for Scientists
and Engineers (PECASE) for his work in learning
primitive models of hu

man motion for humanoid robot control and
kinematic tracking.