Robot Force Estimation with Learned Intraoperative Correction
Robot Force Estimation with Learned Intraoperative Correction
复制标题
通过学习的术中校正进行机器人力估计
DOI：
10.1109/ismr48346.2021.9661568
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Kazanzides, Peter
中科院分区：
文献类型：
--
作者：
Wu, Jie Ying;Yilmaz, Nural;Tumerdem, Ugur;Kazanzides, Peter
在机器人微创手术中测量环境相互作用力将使触觉反馈给外科医生，从而解决一个长期存在的限制。从现有的传感器数据估计这种力，避免了用力传感器改造系统的挑战，但由于机器人机构中的摩擦和顺应性等机械效应，这是困难的。我们之前已经证明，神经网络可以被训练来估计机器人内部关节扭矩，从而能够估计达芬奇研究套件（dVRK）上的外力。在这项工作中，我们扩展了该方法来估计外部笛卡尔力和扭矩，并提出了一种两步方法，通过补偿由于器械轴与套管密封之间以及套管针与患者身体之间的相互作用而产生的力来适应特定的手术设置。实验表明，该方法在平均均方根误差（RMSE）分别为1.8N和0.1Nm的范围内提供了外力和扭矩的估计。此外，两步方法只会增加5分钟的手术准备时间，其中约4分钟用于收集术中训练数据，1分钟用于训练第二步网络。
Measurement of environment interaction forces during robotic minimally-invasive surgery would enable haptic feedback to the surgeon, thereby solving one long-standing limitation. Estimating this force from existing sensor data avoids the challenge of retrofitting systems with force sensors, but is difficult due to mechanical effects such as friction and compliance in the robot mechanism. We have previously shown that neural networks can be trained to estimate the internal robot joint torques, thereby enabling estimation of external forces on the da Vinci Research Kit (dVRK). In this work, we extend the method to estimate external Cartesian forces and torques, and also present a two-step approach to adapt to the specific surgical setup by compensating for forces due to the interactions between the instrument shaft and cannula seal and between the trocar and patient body. Experiments show that this approach provides estimates of external forces and torques within a mean root-mean-square error (RMSE) of 1.8N and 0.1Nm, respectively. Furthermore, the two-step approach can add as little as 5 minutes to the surgery setup time, with about 4 minutes to collect intraoperative training data and 1 minute to train the second-step network.