用NeRF+形状先验，让机器人稳准抓取透明物体
NeRF-Based Transparent Object Grasping Enhanced by Shape Priors
- 基于NeRF建模透明物体空间密度，结合形状先验补全缺失3D信息
- 在杂乱场景中实现对多种透明物体的可靠3D重建与稳定抓取
- 适合需要精准抓取透明物的工业机器人、服务机器人应用
透明物体抓取在机器人领域仍是难题，主要源于难以获取精确的3D信息。传统光学3D传感器难以捕捉透明物体，而机器学习方法常受限于高质量数据集。本文利用NeRF在连续空间中建模不透明度的能力，提出一种基于NeRF的透明物体3D重建方法。尽管如此，重建结果仍可能存在部分缺失。为此，我们引入形状先验驱动的补全机制，并结合自研的几何位姿估计方法，进一步优化重建结果，获得完整可靠的3D信息。基于此优化数据，进行场景级抓取预测，并在真实机器人系统中部署。实验验证表明，该方法能有效捕获杂乱场景中多种透明物体的3D信息，实现高质量、稳定且可执行的抓取预测。
原文摘要 · Abstract (English)
Transparent object grasping remains a persistent challenge in robotics, largely due to the difficulty of acquiring precise 3D information. Conventional optical 3D sensors struggle to capture transparent objects, and machine learning methods are often hindered by their reliance on high-quality datasets. Leveraging NeRF's capability for continuous spatial opacity modeling, our proposed architecture integrates a NeRF-based approach for reconstructing the 3D information of transparent objects. Despite this, certain portions of the reconstructed 3D information may remain incomplete. To address these deficiencies, we introduce a shape-prior-driven completion mechanism, further refined by a geometric pose estimation method we have developed. This allows us to obtain a complete and reliable 3D information of transparent objects. Utilizing this refined data, we perform scene-level grasp prediction and deploy the results in real-world robotic systems. Experimental validation demonstrates the efficacy of our architecture, showcasing its capability to reliably capture 3D information of various transparent objects in cluttered scenes, and correspondingly, achieve high-quality, stables, and executable grasp predictions.
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。