用模块化方法提升机器人抓取复杂物品的鲁棒性
Seg2Grasp: A Robust Modular Suction Grasping in Bin Picking
- 分三步：分割、抓取点定位、物体识别，流程清晰
- 在真实场景中抓取成功率显著优于现有方法
- 适合工业级自动分拣，对陌生物体适应性强
当前依赖端到端学习的抓取方法在非结构化环境中面对陌生或复杂物体时表现不佳。为此，我们提出Seg2Grasp，一种用于动态杂乱料箱场景下稳健吸附抓取的模块化流程。该方法包含三个步骤：分割、抓取与分类。分割模块采用基于Transformer的模型，从RGB-D图像生成与类别无关的物体掩码，实现跨条件精准检测；抓取模块利用表面法向量和掩码提议确定最优吸附点，提升抓取成功率；分类模块则使用微调后的开放词汇Mask-CLIP进行精确物体识别，支持多样化物体处理。真实机器人实验表明，Seg2Grasp在成功率与适应性方面均优于现有方法，为工业自动化分拣提供了强大工具。
原文摘要 · Abstract (English)
Current bin picking methods that rely heavily on end-to-end learning often falter when confronted with unfamiliar or complex objects in unstructured environments. To overcome these limitations, we introduce Seg2Grasp, a modular pipeline designed for robust suction grasping in dynamic and cluttered bin scenarios. Seg2Grasp is built on a three-step process: Segmentation, Grasping, and Classification. The Segmentation module employs a Transformer-based model to generate class-agnostic object masks from RGB-D images, ensuring accurate detection across various conditions. The Grasping module uses surface normals and mask proposals to determine the optimal suction points, enhancing grasp success. Finally, the Classification module leverages fine-tuned open-vocabulary Mask-CLIP for precise object identification, enabling versatile handling of diverse objects. Real-world robotic experiments demonstrate that Seg2Grasp outperforms existing methods in success rates and adaptability, establishing it as a powerful tool for automated bin picking in industrial settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。