构建真实变形物体的3D动态数据集，助力机器人抓取柔性物品
PokeFlex: Towards a Real-World Dataset of Deformable Objects for Robotic Manipulation
- 用机械臂轻戳方式采集五种不同材质物体的形变数据
- 每组数据包含360度完整三维网格与对应力矩信息
- 适合研究机器人感知、控制与实时重建的学者使用
提升机器人对柔性物体的操作能力，可实现食品加工、纺织和医疗等多个行业的自动化。然而，柔性物体的高维性和复杂动态使机器人难以应对。尽管数据驱动方法有潜力解决该问题，但其应用受限于缺乏高质量数据。为此，我们提出PokeFlex，一个基于真实世界机械臂轻戳操作的3D形变数据集，包含五种不同刚度与形状的柔性物体的完整360°三维网格数据，以及对应的力与力矩记录。数据通过专业体素捕捉系统获取，确保全视角重建精度。此外，我们利用该数据集训练了一个视觉模型，可从单张图像和模板网格实现在线3D网格重建。更多演示与示例请见补充材料及官网（https://pokeflex-dataset.github.io/）。
原文摘要 · Abstract (English)
Advancing robotic manipulation of deformable objects can enable automation of repetitive tasks across multiple industries, from food processing to textiles and healthcare. Yet robots struggle with the high dimensionality of deformable objects and their complex dynamics. While data-driven methods have shown potential for solving manipulation tasks, their application in the domain of deformable objects has been constrained by the lack of data. To address this, we propose PokeFlex, a pilot dataset featuring real-world 3D mesh data of actively deformed objects, together with the corresponding forces and torques applied by a robotic arm, using a simple poking strategy. Deformations are captured with a professional volumetric capture system that allows for complete 360-degree reconstruction. The PokeFlex dataset consists of five deformable objects with varying stiffness and shapes. Additionally, we leverage the PokeFlex dataset to train a vision model for online 3D mesh reconstruction from a single image and a template mesh. We refer readers to the supplementary material and to our website ( https://pokeflex-dataset.github.io/ ) for demos and examples of our dataset.
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。