A biological perspective on autonomous agent design

Search Swinburne Research Bank

Home

List of Titles

Please use this identifier to cite or link to this item: http://hdl.handle.net/1959.3/94953

Check Swinburne's subscriptions for full text availability

Title: A biological perspective on autonomous agent design
Author(s): Beer, Randall D.; Chiel, Hillel J.; Sterling, Leon S.
Abstract: The inability of current 'classical' AI systems to handle unconstrained interaction with the real world has recently lead to a search for new control architectures for autonomous agents. We argue that simpler natural animals already exhibit most of the properties required by an autonomous agent, and suggest that designers of autonomous agents should draw directly upon the neural basis of behavior in these animals. The relevant behavioral and neurobiological literature is briefly reviewed. An artificial nervous system for controlling the behavior of a simulated insect is then developed. The design of this artificial insect is based in part upon specific behaviors and neural circuits from several natural animals. The insect exhibits a number of characteristics which are remarkably reminiscent of natural animal behavior.
Publication type: Journal article
Source: Robotics and Autonomous Systems, Vol. 6, no. 1-2 (Jun 1990), pp. 169-186
Publication year: 1990
FOR Code(s): 0801 Artificial Intelligence and Image Processing; 0906 Electrical and Electronic Engineering; 0913 Mechanical Engineering
Keyword(s): Autonomous behavior; Artificial insects; Artificial intelligence; Artificial nervous system; Behavioral hierarchy; Computational neuroethology; Heterogeneous neural networks; Insect locomotion; Motivated behavior; Situated action
Publisher: Elsevier BV
ISSN: 0921-8890
Publisher URL: http://dx.doi.org/10.1016/S0921-8890(05)80034-X
Peer reviewed