Decentralized control system for autonomous navigation based on an evolved artificial immune network

Abstract

This paper investigates an autonomous control system of a mobile robot based on the immune network theory. The immune network navigates the robot to solve a multiobjective task, namely, garbage collection: the robot must find and collect garbage, while it establishes a trajectory without colliding with obstacles, and return to the base before it runs out of energy. Each network node corresponds to a specific antibody and describes a particular control action fur the robot. The antigens are the current state of the robot, read from a set of internal and external sensors. The network dynamics corresponds to the variation of antibody concentration levels, which change according to both mutual interaction of antibody nodes and of antibodies and antigens. It is proposed an evolutionary mechanism to determine the network configuration, that is, the parameters that define those interactions. Simulation results suggest that the proposal presented i s very promising. 0-7803-7282-4/02/$10.M) 02002 lEEE

Idiotypic Immune Networks in Mobile-Robot Control

“…Watanabe et al [5] and [6] use a genetic algorithm with devised crossover to evolve the idiotopes, the network connections, and the number and types of antibodies. Michelan and Von Zuben [12] solve the same problem, proposing a similar evolutionary mechanism for determining the network connections, but they do not establish the antecedent and consequent parts of the antibodies automatically. Vargas et al [7] also use the garbage example but evolve the network structure with a genetic algorithm and update the attributes that define their antibodies using a learning-classifier system [8].…”

“…Equations (4) and (5) show that the elemental products in (12) and (13) are summed over all the antigens and multiplied by the concentration terms. In this way, an individual antibody may undergo multiple idiotypic suppressions and stimulations.…”

Applying particle swarm optimization to a garbage and recycling collection problem

“…Here the robot should collect the garbage from the environment and avoid the obstacles to reach his goal to deposit this garbage in the base. They achieved their goal by combining the work of [4] and the immune network model of [18] as can be seen from the Fig. 2(d).…”

In Situ Self-Reconfiguration of Hexapod Robot OSCAR Using Biologically Inspired Approaches

“…Therefore main properties of AIS are: recognition, identification, adaptation, self-organization. It has been successfully applied for various domains: pattern recognition (Cao & Dasgupta, 2003), data mining (Nasraoui et al, 2005), network security (Pagnoni & Visconti, 2005), robotics (Michelan & Von Zuben, 2002), (Singh & Nair, 2005), (Sathyanath & Sahin, 2002), (Neal et al, 2006), (Canham et al, 2003), and others. There exist several different approaches (De Castro & Timmis, 2002) for AIS.…”