Deep Neural Network Approach in Robot Tool Dynamics Identification for Bilateral Teleoperation

TLDR

Accurate force information is essential for haptic feedback in bilateral teleoperation, and the sensor must capture both tip interaction forces and tool dynamics. This work proposes a model‑free deep convolutional neural network to identify tool dynamics with fast computation and noise robustness. The DCNN identifies tool dynamics from sensor data collected outside the patient’s abdomen, after which calibration is performed and the method is validated in bilateral teleoperation. The DCNN outperforms existing methods, achieving 0.0031 s inference time and superior accuracy on noisy dynamics, demonstrating feasibility for bilateral teleoperation.

Abstract

For bilateral teleoperation, the haptic feedback demands the availability of accurate force information transmitted from the remote site. Nevertheless, due to the limitation of the size, the force sensor is usually attached outside of the patient's abdominal cavity for the surgical operation. Hence, it measures not only the interaction forces on the surgical tip but also the surgical tool dynamics. In this letter, a model-free based deep convolutional neural network (DCNN) structure is proposed for the tool dynamics identification, which features fast computation and noise robustness. After the tool dynamics identification using DCNN, the calibration is performed, and the bilateral teleoperation is demonstrated to verify the proposed method. The comparison results prove that the proposed DCNN model promises prominent performance than other methods. Low computational time (0.0031 seconds) is ensured by the rectified linear unit (ReLU) function, and the DCNN approach provides superior accuracy for predicting the noised dynamics force and enable its feasibility for bilateral teleoperation.