DaFoEs

DaFoEs数据集是由中国科学院香港创新研究院人工智能与机器人中心创建，用于视觉状态深度学习力估计的研究。该数据集包含71939条记录，涵盖多种软环境下的视觉和状态数据。创建过程中，使用了定制的商用触觉主设备控制的远程操作腹腔镜钳，以及一个6轴F/T传感器来记录力数据。DaFoEs数据集主要应用于微创机器人手术中的力估计问题，旨在通过混合不同数据集提高模型的泛化能力。

The DaFoEs dataset was developed by the Center for Artificial Intelligence and Robotics, Hong Kong Institute of Innovation, Chinese Academy of Sciences, for research on deep learning-based force estimation using visual states. It contains 71,939 records, covering visual and state data across diverse soft environments. During its construction, a pair of teleoperated laparoscopic forceps controlled by a customized commercial haptic master device along with a 6-axis F/T sensor were employed to collect force data. The DaFoEs dataset is primarily utilized for force estimation tasks in minimally invasive robotic surgery, aiming to enhance model generalization by combining multiple datasets.