LEARNING APPROACHES APPLIED TO HUMAN-ROBOT INTERACTION FOR SPACE MISSIONS SRAM.H

fencinghuddleAI and Robotics

Nov 14, 2013 (3 years and 8 months ago)

64 views



Intelligent Automation and Soft Computing, Vol. 14, No. 3, pp. 249-262, 2008
Copyright © 2008, TSI
®
Press
Printed in the USA. All rights reserved

249

LEARNING APPROACHES APPLIED TO HUMAN-ROBOT
INTERACTION FOR SPACE MISSIONS

S
EKOU
R
EMY AND
A
YANNA
M.

H
OWARD

Human-Automation Systems (HumAnS) Lab
School of Electrical and Computer Engineering
Georgia Institute of Technology
Atlanta, GA, USA


ABSTRACT—Advances in space science and technology have enabled humanity to
reach a stage where we are able to send manned and unmanned vehicles to explore nearby
planets. However, given key differences between terrestrial and space environments such
as differences in atmospheric content and pressure, acceleration due to gravity among
many others between our planet and those we wish to explore, it is not always easy or
feasible to expect all mission related tasks to be accomplished by astronauts alone. The
presence of robots that specialize in different tasks would greatly enhance our capabilities
and enable better overall performance. In this paper we discuss a methodology for
building a robotic system that can learn to perform tasks via interactive learning. This
learning functionality extends the ability for a robot agent to operate with similar
competence as their human teacher- whether astronaut, mission designer, or engineer. We
provide details on our approach and give representative examples of applying the
different methods in relevant task scenarios.

Key Words: Interactive Learning, Human Robot Collaboration, Machine Learning