NEAT and HyperNEAT based Design for Soft Actuator Controllers

2025-06-05

AI Summary

Soft-bodied actuator controller design heavily relies on manual tuning and struggles to generalize across diverse morphologies. Method: This paper pioneers the systematic application of neuroevolutionary algorithms—specifically NEAT and HyperNEAT—to soft actuator control, integrating Compositional Pattern-Producing Networks (CPPNs) for generating synchronized control policies. A standard genetic algorithm serves as the baseline. Robustness is evaluated across multiple soft-body morphologies and under varying activation function constraints. Results: NEAT consistently achieves superior control performance across all test scenarios, yielding more compact network architectures with fewer parameters—enhancing hardware deployability. It further demonstrates strong adaptability to morphological variations and computational resource constraints. This work establishes a scalable, transferable paradigm for autonomous controller synthesis in soft robotics.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Search and Optimization: Evolutionary Computation
• Machine Learning: Evolutionary Learning

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Since soft robotics are composed of compliant materials, they perform better than conventional rigid robotics in specific fields, such as medical applications. However, the field of soft robotics is fairly new, and the design process of their morphology and their controller strategies has not yet been thoroughly studied. Consequently, here, an automated design method for the controller of soft actuators based on Neuroevolution is proposed. Specifically, the suggested techniques employ Neuroevolution of Augmenting Topologies (NEAT) and Hypercube-based NEAT (HyperNEAT) to generate the synchronization profile of the components of a simulated soft actuator by employing Compositional Pattern Producing Networks (CPPNs). As a baseline methodology, a Standard Genetic Algorithm (SGA) was used. Moreover, to test the robustness of the proposed methodologies, both high- and low-performing morphologies of soft actuators were utilized as testbeds. Moreover, the use of an affluent and a more limited set of activation functions for the Neuroevolution targets was tested throughout the experiments. The results support the hypothesis that Neuroevolution based methodologies are more appropriate for designing controllers that align with both types of morphologies. In specific, NEAT performed better for all different scenarios tested and produced more simplistic networks that are easier to implement in real life applications.

Problem

• Automated design of soft actuator controllers using Neuroevolution
• Comparison of NEAT and HyperNEAT for controller synchronization
• Testing robustness across different actuator morphologies and functions

Innovation

• NEAT and HyperNEAT for soft actuator control
• CPPNs generate synchronization profiles
• Neuroevolution outperforms standard genetic algorithms