Showing papers presented at "Simulation of Adaptive Behavior in 1996"

Evolution of Plastic Neurocontrollers for Situated Agents

Abstract: In this paper we investigate a novel approach to the evolutionary development of autonomous situated agents based on the assumption that the neural mechanisms underlying ontogenetic learning are themselves developed and shaped by evolutionary process. A genetic algorithm is used to evolve neural structures that can be continuously modified during life according to the mechanisms specified in the genotype. The evolutionary process is carried out on a real mobile robot. The analysis of one of the best evolved individuals shows rapid development of stable behavior mediated by fast-changing synapses which are dynamically stable.

A Study of Territoriality: The Role of Critical Mass in Adaptive Task Division

Abstract: This work demonstrates the application of the behavior-based approach to generating ethologically-inspired adaptive foraging using a division of labor into exclusive spatial territories. First, we use fixed group sizes to evaluate and compare the performance of the two types of adaptive solutions. Second, using a collection of experimental robot data, we empirically derive and demonstrate the critical mass for most effective foraging in our domain, and show the decline of performance of the space division strategy with increased group size.

Robotic “Food” Chains: Externalization of State and Program for Minimal-Agent Foraging

Abstract: This paper describes experiments inspired by theoretical work on information invariants ([Donald 1995], [Donald et al 1994]), a means of comparison and a methodology for design of single- and multi-agent systems. Analysis reveals the environmental information that the systems assume and exploit, while the design methodology seeks to move information and processing into the “physical” environment and task mechanics. The approach raises the issue of agents actively recording information, or even “programs,” into the physical environment. This paper provides an example system that dynamically encodes information and “programs” into its physical environment.The second source of inspiration for this work is the natural phenomenon of ant pheromone trail formation, shown to involve agents with simple, local control that encode information into the environment to arrive at globally complex behavior. Analogously, our robotic system actively encodes information into its physical environment in order to reduce sensing, actuation, and computational requirements. Thus, “minimal” agents with local sensing and action form a system that dynamically and globally adapts to environmental changes. We discuss how moving information and “processing” into the shared physical environment improves our ability to generate complex global behaviors from simple locally interacting agents.

The Engineering of Mind

Abstract: While the mind remains a mysterious and inaccessible phenomenon, many of the components of mind, such as perception, behavior generation, knowledge representation, value judgment, reason, intention, emotion, memory, imagination, recognition, learning, attention, and intelligence are becoming well defined and amenable to analysis. Progress is rapid in the cognitive and neurosciences as well as in artificial intelligence, control theory, and many other fields related to the engineering of mind. A reference model architecture for intelligent systems is suggested to tie together concepts from all these separate fields into a unified framework that includes both biological and machine embodiments of the components of mind. It is argued that such a reference model architecture will facilitate the development of scientific models of mind.

Adaptive animât navigation based on a flexibility model for the environment

Abstract: In this paper we propose a uniied framework for local animat navigation and position local-ization. This framework is based on the use of exibility maps of the environment. Flexibility maps contain both the current knowledge of the animat about the positions of the objects in its environment as well as the information required to calculate its future path. The major beneet of using exibility maps is that several navigation tasks can be incorporated elegantly into a single framework. In addition, we found that the simple control laws derived from this approach generate paths that look very natural in realistic circumstances, adding to the biological plausibil-ity of the approach. We will show that a exibil-ity model increases the adaptivity of an animat to changes in its environment by allowing the use of families of paths instead of single paths, and by allowing the derivation of entirely new paths from the animat's memory of previously learned paths.