In this study, we further investigate the robustness and generalization ability of an neural network (NN) based force estimation method, using the da Vinci Research Kit Si (dVRK-Si). To evaluate our method's performance, we compare the force estimation accuracy with several baseline methods. We conduct comparative studies between the dVRK classic and dVRK-Si systems to benchmark the effectiveness of these approaches. We conclude that the NN-based method provides comparable force estimation accuracy across the two systems, as the average root mean square error (RMSE) over the average range of force ratio is approximately 3.07% for the dVRK classic, and 5.27% for the dVRK-Si. On the dVRK-Si, the force estimation RMSEs for all the baseline methods are 2 to 4 times larger than the NN-based method in all directions. One possible reason is, we made assumptions in the baseline methods that static forces remain the same or dynamics is time-invariant. These assumptions may hold for the dVRK Classic, as it has pre-loaded weight and maintains horizontal self balance. Since the dVRK-Si configuration does not have this property, assumptions do not hold anymore, therefore the NN-based method significantly outperforms.

翻译：在本研究中，我们进一步探讨了基于神经网络（NN）的力估计方法在达芬奇研究套件Si（dVRK-Si）系统上的鲁棒性与泛化能力。为评估所提方法的性能，我们将其力估计精度与若干基线方法进行了比较。我们通过对比dVRK经典系统与dVRK-Si系统，以基准化这些方法的有效性。研究结论表明，基于神经网络的方法在两个系统上均可提供相当的力估计精度：对于dVRK经典系统，力估计的平均均方根误差（RMSE）与平均力范围之比约为3.07%；而对于dVRK-Si系统，该比值约为5.27%。在dVRK-Si系统上，所有基线方法的力估计RMSE在各个方向上均为基于神经网络方法的2至4倍。可能的原因之一是，我们在基线方法中假设静态力保持不变或动力学是时不变的。这些假设可能适用于dVRK经典系统，因其具有预加载重量并保持水平自平衡。由于dVRK-Si系统不具备这一特性，假设不再成立，因此基于神经网络的方法显著优于基线方法。