Estimating Tip Contact Forces for Concentric Tube Continuum Robots Based on Backbone Deflection
Estimating Tip Contact Forces for Concentric Tube Continuum Robots Based on Backbone Deflection
复制标题
DOI：
10.1109/tmrb.2020.3034258
复制
发表时间：
2020-11-01
期刊：
影响因子：
--
通讯作者：
Steil, Jochen J.
中科院分区：
文献类型：
--
作者：
Donat, Heiko;Lilge, Sven;Steil, Jochen J.
同心管连续机器人是目前正在开发的用于微创手术的最小、最灵活的器械之一，因此可以在人体难以到达的区域进行手术。不幸的是，由于这些机器人的外形小，集成最先进的力传感器是一项挑战，尽管接触力是外科手术过程中必不可少的信息。在这项工作中，我们提出了一种基于深度直接级联学习（DDCL）的新颖数据驱动方法，以创建一个用于计算同心管连续体机器人尖端接触力的虚拟传感器。利用机器人骨架的固有弹性，利用挠度来估计各自的外尖端接触力。我们对单个管的不同数据表示进行了评估，并随后将其应用于三段同心管连续机器人。此外，我们设计了一种新的迁移学习方法，通过使用模拟数据预训练级联网络来提高估计精度。随后，我们根据从物理机器人记录的小的真实世界数据集对网络进行微调。
Concentric Tube Continuum Robots are among the smallest and most flexible instruments in development for minimally invasive surgery, thereby enabling operations in areas within the human body that are difficult to reach. Unfortunately, integrating state-of-the-art force sensors is challenging for these robots due to their small form factor, although contact forces are essential information in surgical procedures. In this work, we propose a novel data-driven approach based on Deep Direct Cascade Learning (DDCL) to create a virtual sensor for computing the tip contact force of Concentric Tube Continuum Robots. By exploiting the robot's backbone's inherent elasticity, deflection is used to estimate the respective external tip contact force. We evaluate our approach on different data representations for a single tube and apply it subsequently on a three-segment Concentric Tube Continuum Robot. Furthermore, we devise a novel transfer learning approach through DDCL to improve the estimation accuracy by pre-training a cascaded network with simulated data. Subsequently, we fine-tune the network based on a small real-world data set recorded from the physical robot.