design assembly fixtures

This study addresses the bottleneck in CAD-to-assembly planning, which traditionally relies on manual intervention and supplementary metadata, by proposing an end-to-end automated framework that takes mesh models as its sole input. Methodologically, the approach generates optimal assembly sequences through physics-based disassembly simulation and Design for Assembly (DfA) cost function ranking, eliminating the need for joint or fastener annotations. Furthermore, a multimodal large language model is incorporated to automatically synthesize assembly manuals and recommend appropriate tools. Experimental results demonstrate that the proposed method reduces simulated assembly time by 35% and achieves a tool selection accuracy of 88.6%, significantly enhancing both the efficiency and intelligence of manufacturing planning processes.

Manufacturing SMEs face critical bottlenecks in visual assembly quality control—including scarce real-image acquisition, high annotation costs, and insufficient training data. To address these challenges, this paper proposes a CAD model–driven fully synthetic data framework. It establishes an end-to-end virtual generation pipeline integrating parametric CAD modeling, physics-based rendering, and YOLO-family object detection, enabling efficient simulation-to-reality transfer learning. This work represents the first systematic deployment of a purely synthetic data approach to industrial inspection of planetary gear assemblies. Experiments demonstrate a 99.5% mAP@0.5:0.95 on synthetic data; after domain adaptation, detection accuracy remains at 93% on real-world images. The framework significantly reduces dependence on manual annotation and physical image collection, validating its feasibility for lightweight, reusable, and low-cost industrial deployment.

Robots struggle to autonomously perform complex maintenance tasks—such as disassembly and assembly—in unstructured environments due to environmental uncertainties, particularly discrepancies between CAD models and real-world scenes. Method: This paper proposes a closed-loop autonomous execution framework integrating symbolic task planning with multimodal perception. It introduces the first approach that jointly leverages CAD prior models and real-time RGB-D sensory data to dynamically refine the symbolic planner. The framework unifies task parsing, executable instruction generation, and adaptive closed-loop control to enable end-to-end mapping from high-level intent to low-level robot actions. Results: Experimental validation in realistic maintenance scenarios demonstrates robust performance under ±5 mm pose deviations between model and reality. The system successfully executes fully autonomous disassembly and assembly operations, significantly improving reliability and generalization capability for maintenance tasks in non-structured environments.

为解决机器人拆卸不规则形状产品时的稳定支撑问题，本文提出一种模块化真空夹具系统，并通过去噪扩散概率模型和贝叶斯优化规划整个拆卸序列的共享支撑配置。

This study addresses the bottleneck of months-long manual tuning required to translate digital designs into robotic assembly by proposing an end-to-end autonomous pipeline. Methodologically, it integrates generative AI with natural language processing to automate the design of customized timber structures. Furthermore, it introduces a novel gradient backpropagation mechanism via a graph attention network surrogate, enabling hardware-level corrections through differentiable geometry repair to drive collaborative UR5e robotic assembly. Experimental results demonstrate that 86.7% of novel inputs achieve automated screw driving, yielding a tenfold efficiency improvement over conventional methods. The proposed framework is further validated through the successful physical assembly of ten distinct structures.

This work addresses the limitation of existing CAD model evaluation methods, which predominantly emphasize visual fidelity while neglecting engineering functionality. To bridge this gap, the authors propose CADEngBench, a dual-track benchmark that systematically incorporates engineering behavior validation—including finite element analysis (FEA) alignment, design-for-manufacturing (DFM) checks, and kinematic joint dynamics—into the assessment framework, covering both parametric parts and assemblies. The benchmark employs techniques such as B-Rep validity verification, parameter perturbation tests, functional editing tasks, and linear static simulations using CalculiX to comprehensively evaluate the engineering-grade capabilities of generated and edited models. Experimental results reveal that while current multimodal models outperform in CAD editing over generation, they still struggle with complex edits, FEA consistency, and accurately reconstructing real-world assembly mating relationships.

This study addresses the challenge of coupling discrete operation planning with continuous toolpath generation in CNC machining of B-rep models by proposing the CNCGEN framework. This framework introduces a novel "persistent manufacturing object" modeling mechanism that, combined with a learned agent verifier providing material removal feedback, dynamically correlates local predictions with geometric evolution to enable stepwise generation and state updating of operations and toolpaths. The approach integrates deep learning for three-axis machining, B-rep representations, and parametric toolpath algorithms, supported by a synthetically generated dataset incorporating geometric verification. Experimental results demonstrate that, compared to baseline methods, the proposed framework significantly improves workpiece geometric accuracy while effectively mitigating residual material and overcutting phenomena.

为应对多样化生产带来的挑战，本文提出一种基于CAD模型的编程和执行系统，通过动态参数化的行为树控制结构实现人-机器人-起重机协同任务。

This work addresses the challenges of low efficiency, poor trajectory quality, and difficulty in feasible pose search when single-arm robots perform precise interference-fit assembly in confined spaces. We propose the first end-to-end dual-arm collaborative assembly framework that automatically generates high-quality assembly strategies using only part CAD models and the target assembly pose. Our approach integrates multi-robot motion planning, CAD-driven modeling, collaborative trajectory optimization, and physics-based simulation. We theoretically demonstrate for the first time that dual-arm collaboration significantly enhances assembly performance, providing formal guarantees on execution time and trajectory accuracy, and derive theoretical bounds on robot cell dimensions. Experiments show that, compared to single-arm baselines, our method reduces average execution time by over 50%, substantially improves trajectory quality, and accelerates feasible pose discovery, with results validated through both simulation and physical experiments.

This study investigates whether general-purpose agents can perform precise 3D assembly solely through visual interaction without fine-tuning. To this end, we introduce AssemblyWorld, an interactive 3D environment and evaluation benchmark, along with the first assessment framework for general-purpose agent-based 3D assembly relying exclusively on visual perception. Within this framework, agents perceive geometry from 2D views and manipulate rigid components, enabling a systematic evaluation of their assembly capabilities. Our analysis reveals a significant gap between approximate structure recovery and precise reconstruction. Experimental results demonstrate that the best-performing system achieves a component accuracy of 80.9% and a complete assembly success rate of 59.4%. Furthermore, open-source models exhibit substantially inferior performance compared to their closed-source counterparts.