Designing morphologies of soft medical devices using cooperative neuro coevolution

2025-06-04

AI Summary

Manual design of soft medical devices—particularly drug delivery systems—is hampered by severe material nonlinearity and strong morphology–control coupling, leading to large design errors and inefficient optimization. Method: We propose the first collaborative neural coevolutionary framework tailored for morphology design of soft medical devices, integrating NEAT-based compositional pattern encoding with a multi-strategy individual collaboration mechanism, and benchmarking against Age-Fitness Pareto Optimization (AFPO). Contribution/Results: The evolved actuators achieve significantly improved upward bending displacement (+32.7%) and cross-controller robustness (+41.5% stability gain) over AFPO. This work pioneers the application of collaborative coevolution to joint morphology–control optimization of soft medical devices, establishing a scalable, data-efficient design paradigm for clinically adaptable soft drug delivery systems.

Technology Category

• Search and Optimization: Evolutionary Computation
• Machine Learning: Evolutionary Learning
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Soft robots have proven to outperform traditional robots in applications related to propagation in geometrically constrained environments. Designing these robots and their controllers is an intricate task, since their building materials exhibit non-linear properties. Human designs may be biased; hence, alternative designing processes should be considered. We present a cooperative neuro coevolution approach to designing the morphologies of soft actuators and their controllers for applications in drug delivery apparatus. Morphologies and controllers are encoded as compositional pattern-producing networks evolved by Neuroevolution of Augmented Topologies (NEAT) and in cooperative coevolution methodology, taking into account different collaboration methods. Four collaboration methods are studied: n best individuals, n worst individuals, n best and worst individuals, and n random individuals. As a performance baseline, the results from the implementation of Age-Fitness Pareto Optimisation (AFPO) are considered. The metrics used are the maximum displacement in upward bending and the robustness of the devices in terms of applying to the same evolved morphology a diverse set of controllers. Results suggest that the cooperative neuro coevolution approach can produce more suitable morphologies for the intended devices than AFPO.

Problem

• Designing soft robot morphologies for constrained environments
• Optimizing controllers for non-linear soft materials
• Comparing coevolution methods for medical device performance

Innovation

• Cooperative neuro coevolution for soft actuator design
• NEAT for evolving morphologies and controllers
• Four collaboration methods optimize performance