objective and then selecting actions or motions to
achieve the objective. In particularly, using our
proposed framework, identifying an objective can be
described as identifying a goal state, while selecting
actions or motions can be described as selecting a
sequence of transitions from the current state to the goal
state.
Using our proposed framework, the underlining model
is a non-deterministic finite state machine. From one
state, there may be several transitions to follow to other
states. Choosing one transitions or the other is why we
call this a trial and error approach and is why it is non-
deterministic. To achieve the objective is to find a
sequence of transitions from the current state to the goal
state. As soon as a sequence of transitions is found, it
can be stored for future use.
3.1.2 Learning by Macro Approach
Macro approach can be used in a supervised learning
environment. After a humanoid robot is repeatedly
instructed to perform certain task, the robot can store
the sequence of motions to associate with a name of the
task. After which, the robot can be commanded to
perform the sequence by simply specifying the name of
the task. This is a simple record and play back
approach.
A more sophisticated approach is provided by the first
author [Choi 98], in which a robot can build a non-
deterministic finite state machine based on the
repeatedly instructions to perform certain task. The
resulting non-deterministic finite state machine can then
be used for other purposes such as for learning from
trial and error as discussed above.
4. Developing Cybele
We are developing a humanoid motion description
language, called Cybele, based on our proposed
framework. Our development process in turn enhances
the strength of our framework. More detail description
of our new language will be provided in our future
papers.
5. Conclusion and Future Research
We described our proposed description language and
framework for specifying motions for humanoid robots
and for allowing humanoid robots to learn motor skills
through interacting with the environments. The
proposed language and framework are unique and
encompassing many areas of research interesting to
researchers in epigenetic robots. This paper can also
serve as an outline of strategies for future research
programs in humanoid motion description and motor
skill acquisition. Much work remains to be done in this
exciting new area of research.
Reference
[Adamson 87] A. Adamson, “Calaban”, Demonstration
at Birmingham University, England, June 1987.
[Badler 94] Badler, N. I., Bindiganavale, R., Granieri, J.
P., Wei, S., and Zhao, X. “Posture Interpolation
with Collision Avoidance,” In Proc. Computer
Animation, pp13-20, 1994.
[Badler79] Badler, N. I., and Smoliar, S. W. “Digital
Representation of Human Movement”, Computer
Surveys, Vol. 11, No 1, March 1979.
[Brooks 98] R. A. Brooks, C. Breazeal, M. Marjanovic,
B. Scassellati, and M. M. Williamson, “The Cog
Project: Building a Humanoid Robot,” in IARP
First International Workshop on Humanoid and
Human Friendly Robotics, (Tsukuba, Japan), pp. I-
1, October 26-27 1998.
[Calvert 93] Tom W. Calvert, Armin Bruderlin, Sang
Mah, Thecla Schiphorst, and Chris Welman, “The
Evolution of an Interface for Choreographers”,
Interchi, pp. 24-29, 1993.
[Causley 80] Marguerite Causley, An introduction to
Benesh Movement Notation, ISBN: 0836992806,
1980.
[Choi 98] Ben Choi, “Automata for Learning Sequential
Tasks,” New Generation Computing: Computing
Paradigms and Computational Intelligence, Vol.
16, No. 1, pp. 23-54, 1998.
[EW] Eshkol-Wachman Movement Notation, http://
ww2.mcgill.ca/Biology/perspage/ew_page.htm
[Honda] Honda Humanoid robot: http://
world.honda.com/robot/
[Hutchinson 87] Ann Hutchinson and G. Balanchine,
Labanotation: The System of Analyzing and
Recording Movement, ISBN: 0878305270, 1987.
[Perlin 96] Perlin, K, Gikdberg, A, “Improv: A System
for Scripting Interactive Actors in Virtual Worlds”,
Computer Graphics Proceeding, pp.205-216, 1996.
[Schiphorst 92] Schiphorst, T. “LifeForms: Design
Tools for Choreography”, Dance and Technology
I: Moving Toward the Future, pp. 46-52, 1992.
[Singh 84] Ryman, R., Singh, B., Beatty, J., and Booth,
K. “A Computerized Editor of Benesh Movement
Notation,” Dance Research Journal, 16(1): 27-34,
1984.