More Efficient Arm Structures for Construction Robots by Deep Generative Models Based on Topology Optimization

Abstract

To achieve a lightweight and high-stiffness design of robotic arms for construction robots, this paper proposes a novel data-driven generative design framework that integrates topology optimization, 3D generative adversarial networks (GANs), reverse engineering, and additive manufacturing. This paper develops a three-dimensional deep generative model that integrates Topology Optimization (TO) with Generative Adversarial Networks (GANs) to result in more efficient outcomes. A high-fidelity CAD model of a construction robotic arm was first established, from which a diverse geometric dataset containing 350 topology optimized models was generated. Subsequently, a 3D-GAN architecture was trained on this dataset to synthesize high-performance voxelized structural configurations, which were then transformed into smooth solid models via a streamlined reverse engineering workflow. Finally, the representative joint model achieved a mass reduction of approximately 51.67% and 28.93% compared to the initial model and topological model, while maintaining mechanical performance. Furthermore, physical prototypes were successfully fabricated using 3D printing technology, confirming the geometric compliance and manufacturability of the generated models. This work demonstrates the feasibility and effectiveness of combining generative deep learning with computational topology optimization and additive manufacturing for the intelligent design of construction robot components.