Fast and Reliable Autonomous Surgical Debridement with Cable-Driven Robots Using a Two-Phase Calibration Procedure

Abstract

Automating precision subtasks such as debridement (removing dead or diseased tissue fragments) with Robotic Surgical Assistants (RSAs) such as the da Vinci Research Kit (dVRK) is challenging due to inherent non-linearities in cabledriven systems. We propose and evaluate a novel two-phase coarse-to-fine calibration method. In Phase I (coarse), we place a red calibration marker on the end effector and let it randomly move through a set of open-loop trajectories to obtain a large sample set of camera pixels and internal robot end-effector configurations. This coarse data is then used to train a Deep Neural Network (DNN) to learn the coarse transformation bias. In Phase II (fine), the bias from Phase I is applied to move the end-effector toward a small set of specific target points on a printed sheet. For each target, a human operator manually adjusts the end-effector position by direct contact (not through teleoperation) and the residual compensation bias is recorded. This fine data is then used to train a Random Forest (RF) to learn the fine transformation bias. Subsequent experiments suggest that without calibration, position errors average 4.55mm. Phase I can reduce average error to 2.14mm and the combination of Phase I and Phase II can reduces average error to 1.08mm. We apply these results to debridement of raisins and pumpkin seeds as fragment phantoms. Using an endoscopic stereo camera with standard edge detection, experiments with 120 trials achieved average success rates of 94.5%, exceeding prior results with much larger fragments (89.4%) and achieving a speedup of 2.1x, decreasing time per fragment from 15.8 seconds to 7.3 seconds. Source code, data, and videos are available at https://sites.google.com/ view/calib-icra/.

Accelerating Surgical Robotics Research: A Review of 10 Years With the da Vinci Research Kit

“…A lot of the remaining works focused on tissue interaction. This application category includes papers working on cutting and debridement [61], [87], [90], [92], [95], [97] as well as the retraction and dissection of tissues [101], [131], [132], [155], [257], [265] or blood suction [226]. Also included is tissue palpation for locating tumors or vessels and more general tissue manipulation, as in [13]- [15], [17], [82], [83], [86], [98], [99], [154], [164], [225], and [241], with experiments sometimes using just common fabric as a phantom for tissue [94], [100].…”

A Review on Deep Learning in Minimally Invasive Surgery

“…Another task that has been the focus of automation is [95] propose the use of DNNs to automate the debridement task using a dVRK. First, the robot collects data to train a DNN by automatically exploring trajectories in the workspace with random targets.…”

DESK: A Robotic Activity Dataset for Dexterous Surgical Skills Transfer to Medical Robots

“…In surgical data analysis, many state-of-the-art techniques contributions are limited to study-specific data and validation metrics [13]. Recently, several efforts have been made in autonomous classification and execution of surgical tasks using multiple surgical robots and simulation platforms [18]- [20]. However, the obtained models are specific for a given platform and setup, and cannot be directly transferred to other robots/procedures.…”