Research Papers

A Study of the Continuous Optimization Problem Using a Wood Robot Controlled by a Biologically Motivated System

[+] Author and Article Information
Jong-Chen Chen

Information Management Department,
National Yunlin University of Science and Technology,
123 University Road,
Section 3,
Douliu 64002, Taiwan
e-mail: jcchen@yuntech.edu.tw

Contributed by the Dynamic Systems Division of ASME for publication in the JOURNAL OF DYNAMIC SYSTEMS, MEASUREMENT, AND CONTROL. Manuscript received September 22, 2013; final manuscript received January 21, 2015; published online March 23, 2015. Assoc. Editor: Sergey Nersesov.

J. Dyn. Sys., Meas., Control 137(7), 071008 (Jul 01, 2015) (11 pages) Paper No: DS-13-1389; doi: 10.1115/1.4029718 History: Received September 22, 2013; Revised January 21, 2015; Online March 23, 2015

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.

Copyright © 2015 by ASME
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Fig. 1

Architecture of an ANM system

Grahic Jump Location
Fig. 2

Central processing component

Grahic Jump Location
Fig. 3

Cytoskeleton of cytoskeletal neurons

Grahic Jump Location
Fig. 5

Interface between a subnet and Miky

Grahic Jump Location
Fig. 6

All possible movement angles of a front leg

Grahic Jump Location
Fig. 7

All possible movement angles of a hind leg

Grahic Jump Location
Fig. 8

Evolutionary learning at the cytoskeletal neuron level

Grahic Jump Location
Fig. 9

Evolutionary learning at the reference neuron level: (a) evaluate/select, (b) copy, and (c) vary

Grahic Jump Location
Fig. 10

Learning to walk with a minimum degree of pitching, rolling, and yawing altogether

Grahic Jump Location
Fig. 11

Learning to walk with a minimizing degree of pitching, rolling, or yawing, separately

Grahic Jump Location
Fig. 12

TA movement and ET

Grahic Jump Location
Fig. 13

Making a turn with four normal legs

Grahic Jump Location
Fig. 14

Learning to walk with a minimizing degree of pitching and rolling

Grahic Jump Location
Fig. 15

System's learning capability dealing with some permanent change in its structure

Grahic Jump Location
Fig. 16

Coordination of Miky's four legs in terms of TA and ET values




Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In