The Use of Probabilistic Systems to Mimic the Behaviour of Idiotypic AIS Robot Controllers

TL;DR

This paper explores probabilistic control schemes to emulate idiotypic immune network-based robot controllers, aiming to understand their behavior selection mechanisms and improve navigation performance in simulated robots.

Contribution

It introduces probabilistic schemes to mimic idiotypic dynamics, providing insights into their behavior selection and performance in robot navigation tasks.

Findings

A probabilistic scheme with 50% bias towards high-ranked behaviors best mimics idiotypic dynamics.

The scheme improves behavior selection but does not fully match idiotypic system performance.

Simulated experiments demonstrate the potential and limitations of probabilistic mimicry.

Abstract

Previous work has shown that robot navigation systems that employ an architecture based upon the idiotypic network theory of the immune system have an advantage over control techniques that rely on reinforcement learning only. This is thought to be a result of intelligent behaviour selection on the part of the idiotypic robot. In this paper an attempt is made to imitate idiotypic dynamics by creating controllers that use reinforcement with a number of different probabilistic schemes to select robot behaviour. The aims are to show that the idiotypic system is not merely performing some kind of periodic random behaviour selection, and to try to gain further insight into the processes that govern the idiotypic mechanism. Trials are carried out using simulated Pioneer robots that undertake navigation exercises. Results show that a scheme that boosts the probability of selecting highly-ranked alternative behaviours to 50% during stall conditions comes closest to achieving the properties of the idiotypic system, but remains unable to match it in terms of all round performance.