Evolution of a Subsumption Architecture Neurocontroller

TL;DR

This paper introduces layered evolution in neurocontrollers, combining subsumption architecture with evolutionary robotics, demonstrating improved scalability and performance in robotic tasks compared to traditional methods.

Contribution

It presents a novel layered evolution approach that merges subsumption architecture with evolutionary robotics, enhancing scalability and performance.

Findings

Layered controllers perform at least as well as monolithic ones.

Layered evolution shows superior scalability for complex tasks.

Merged layers maintain effective robot behavior.

Abstract

An approach to robotics called layered evolution and merging features from the subsumption architecture into evolutionary robotics is presented, and its advantages are discussed. This approach is used to construct a layered controller for a simulated robot that learns which light source to approach in an environment with obstacles. The evolvability and performance of layered evolution on this task is compared to (standard) monolithic evolution, incremental and modularised evolution. To corroborate the hypothesis that a layered controller performs at least as well as an integrated one, the evolved layers are merged back into a single network. On the grounds of the test results, it is argued that layered evolution provides a superior approach for many tasks, and it is suggested that this approach may be the key to scaling up evolutionary robotics.