AI-Guided Human-In-the-Loop Inverse Design of High Performance Engineering Structures

2026-01-15

AI Summary

This study addresses the high computational cost and limited human–computer interaction efficiency of traditional topology optimization, as well as the cumbersome region-selection procedures in existing human-in-the-loop approaches. To overcome these limitations, the authors propose a novel human-in-the-loop optimization framework integrated with artificial intelligence, which employs a U-Net image segmentation model to predict regions where users prefer structural modifications, thereby enabling intelligent guidance of design iterations. Trained on synthetic data, the model demonstrates cross-task generalization and exhibits emergent behavior surpassing that achievable with single-region training data. Experimental results show that, with only a 15-second increase in user interaction time, the method significantly enhances structural manufacturability or improves linear buckling load capacity by up to 39%.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Inverse design tools such as Topology Optimization (TO) can achieve new levels of improvement for high-performance engineered structures. However, widespread use is hindered by high computational times and a black-box nature that inhibits user interaction. Human-in-the-loop TO approaches are emerging that integrate human intuition into the design generation process. However, these rely on the time-consuming bottleneck of iterative region selection for design modifications. To reduce the number of iterative trials, this contribution presents an AI co-pilot that uses machine learning to predict the user's preferred regions. The prediction model is configured as an image segmentation task with a U-Net architecture. It is trained on synthetic datasets where human preferences either identify the longest topological member or the most complex structural connection. The model successfully predicts plausible regions for modification and presents them to the user as AI recommendations. The human preference model demonstrates generalization across diverse and non-standard TO problems and exhibits emergent behavior outside the single-region selection training data. Demonstration examples show that the new human-in-the-loop TO approach that integrates the AI co-pilot can improve manufacturability or improve the linear buckling load by 39% while only increasing the total design time by 15 sec compared to conventional simplistic TO.

Problem

• inverse design
• human-in-the-loop
• topology optimization
• computational efficiency
• user interaction

Innovation

• AI-guided design
• human-in-the-loop
• topology optimization
• U-Net
• inverse design