Continuous optimization plays an increasingly significant role in everyday decision-making situations. Our group had previously developed a multilevel system called the artificial neuromolecular system (ANM) that possessed structure richness allowing variation and/or selection operators to act on it in order to generate a broad range of dynamic behaviors. In this paper, we used the ANM system to control the motions of a wooden walking robot named Miky. The robot was used to investigate the ANM system's capability to deal with continuous optimization problems through self-organized learning. Evolutionary learning algorithm was used to train the system and generate appropriate control. The experimental results showed that Miky was capable of learning in a continued manner in a physical environment. A further experiment was conducted by making some changes to Miky's physical structure in order to observe the system's capability to deal with the change. Detailed analysis of the experimental results showed that Miky responded to the change by appropriately adjusting its leg movements in space and time. The results showed that the ANM system possessed continuous optimization capability in coping with the change. Our findings from the empirical experiments might provide us another dimension of information of how to design an intelligent system comparatively friendlier than the traditional systems in assisting humans to walk.

References

1.
May
,
R. M.
,
1973
,
Stability and Complexity in Model Eco-Systems
,
Princeton University Press
,
Princeton, NJ
.
2.
Horgan
,
J.
,
2004
, “
The End of Science Revisited
,”
Computer
,
37
(
1
), pp.
37
43
.10.1109/MC.2004.1260723
3.
Conrad
,
M.
,
1983
,
Adaptability: The Significance of Variability From Molecule to Ecosystem
,
Plenum Press
,
New York
.
4.
Miller
,
J. F.
,
2002
, “
Evolution in Materio: Looking Beyond the Silicon Box
,”
Proceedings of the 2002 NASA/DoD Conference on Evolvable Hardware
, Washington, DC, July 15–18, pp.
167
176
.
5.
Higuchi
,
T.
,
Iwata
,
M.
,
Keymeulen
,
D.
,
Sakanashi
,
H.
,
Murakawa
,
M.
,
Kajitani
,
I.
,
Takahashi
,
E.
,
Toda
,
K.
,
Salami
,
N.
,
Kajihara
,
N.
, and
Otsu
,
N.
,
1999
, “
Real-World Applications of Analog and Digital Evolvable Hardware
,”
IEEE Trans. Evol. Comput.
,
3
(
3
), pp.
220
235
.10.1109/4235.788492
6.
Vassilev
,
V. K.
,
Job
,
D.
, and
Miller
,
J. F.
,
2000
, “
Towards the Automatic Design of More Efficient Digital Circuits
,”
Proceedings of the Second NASA/DoD Workshop on Evolvable Hardware
, Palo Alto, CA, July 13–15, pp.
151
160
.
7.
Thompson
,
A.
, and
Layzell
,
P.
,
1999
, “
Analysis of Unconventional Evolved Electronics
,”
Commun. ACM.
,
42
(
4
), pp.
71
79
.10.1145/299157.299174
8.
Lipson
,
H.
, and
Pollack
,
J. B.
,
2000
, “
Automatic Design and Manufacture of Robotic Lifeforms
,”
Nature
,
406
, pp.
974
987
.10.1038/35023115
9.
Zhou
,
Z.
,
Ong
,
Y. S.
,
Lim
,
M. H.
, and
Lee
,
B. S.
,
2007
, “
Memetic Algorithm Using Multi-Surrogates for Computationally Expensive Optimization Problems
,”
Soft Comput.
,
11
(
10
), pp.
957
971
.10.1007/s00500-006-0145-8
10.
Ong
,
Y.-S.
,
Lim
,
M. H.
, and
Chen
,
X.
,
2010
, “
Research Frontier: Memetic Computation—Past, Present & Future
,”
Comput. Intell. Mag.
,
5
(
2
), pp.
24
31
.10.1109/MCI.2010.936309
11.
Chen
,
J.-C.
, and
Conrad
,
M.
,
1994
, “
A Multilevel Neuromolecular Architecture That Uses the Extradimensional Bypass Principle to Facilitate Evolutionary Learning
,”
Phys. D
,
75
(
1–3
), pp.
417
437
.10.1016/0167-2789(94)90295-X
12.
Chen
,
J.-C.
, and
Conrad
,
M.
,
1994
, “
Learning Synergy in a Multilevel Neuronal Architecture
,”
BioSystems
,
32
(
2
), pp.
111
142
.10.1016/0303-2647(94)90036-1
13.
Chen
,
J.-C.
,
1998
, “
Problem Solving With a Perpetual Evolutionary Learning Architecture
,”
Appl. Intell.
,
8
(
1
), pp.
53
71
.10.1023/A:1008220631455
You do not currently have access to this content.