Multi-criteria Evolution of Neural Network Topologies: Balancing Experience and Performance in Autonomous Systems

TL;DR

This paper introduces a multi-objective neuro-evolution algorithm that balances performance and experience-gain to improve neural network generalization in autonomous systems, especially for small-robot path planning.

Contribution

It develops a novel multi-objective neuro-evolution method based on NEAT, incorporating experience-gain to enhance exploration and generalization in autonomous robot applications.

Findings

Multi-objective neuro-evolution outperforms single-objective in unseen scenarios.

Experience-gain criterion promotes exploration and diversity.

Enhanced generalization with fewer training scenarios.

Abstract

Majority of Artificial Neural Network (ANN) implementations in autonomous systems use a fixed/user-prescribed network topology, leading to sub-optimal performance and low portability. The existing neuro-evolution of augmenting topology or NEAT paradigm offers a powerful alternative by allowing the network topology and the connection weights to be simultaneously optimized through an evolutionary process. However, most NEAT implementations allow the consideration of only a single objective. There also persists the question of how to tractably introduce topological diversification that mitigates overfitting to training scenarios. To address these gaps, this paper develops a multi-objective neuro-evolution algorithm. While adopting the basic elements of NEAT, important modifications are made to the selection, speciation, and mutation processes. With the backdrop of small-robot path-planning applications, an experience-gain criterion is derived to encapsulate the amount of diverse local environment encountered by the system. This criterion facilitates the evolution of genes that support exploration, thereby seeking to generalize from a smaller set of mission scenarios than possible with performance maximization alone. The effectiveness of the single-objective (optimizing performance) and the multi-objective (optimizing performance and experience-gain) neuro-evolution approaches are evaluated on two different small-robot cases, with ANNs obtained by the multi-objective optimization observed to provide superior performance in unseen scenarios.