Optimizing Base Placement of Surgical Robot: Kinematics Data-Driven Approach by Analyzing Working Pattern

In robot-assisted minimally invasive surgery (RAMIS), optimal placement of the surgical robot's base is crucial for successful surgery. Improper placement can hinder performance due to manipulator limitations and inaccessible workspaces. Traditionally, trained medical staff rely on experience for base placement, but this approach lacks objectivity. This paper proposes a novel method to determine the optimal base pose based on the individual surgeon's working pattern. The proposed method analyzes recorded end-effector poses using machine-learning based clustering technique to identify key positions and orientations preferred by the surgeon. To address joint limits and singularities problems, we introduce two scoring metrics: joint margin score and manipulability score. We then train a multi-layer perceptron (MLP) regressor to predict the optimal base pose based on these scores. Evaluation in a simulated environment using the da Vinci Research Kit (dVRK) showed unique base pose-score maps for four volunteers, highlighting the individuality of working patterns. After conducting tests on the base poses identified using the proposed method, we confirmed that they have a score approximately 28.2\% higher than when the robots were placed randomly, with respect to the score we defined. This emphasizes the need for operator-specific optimization in RAMIS base placement.

Hysteresis Compensation of Flexible Continuum Manipulator using RGBD Sensing and Temporal Convolutional Network

Flexible continuum manipulators are valued for minimally invasive surgery, offering access to confined spaces through nonlinear paths. However, cable-driven manipulators face control difficulties due to hysteresis from cabling effects such as friction, elongation, and coupling. These effects are difficult to model due to nonlinearity and the difficulties become even more evident when dealing with long and multi-segmented manipulator. This paper proposes a data-driven approach based on recurrent neural networks to capture these nonlinear and previous states-dependent characteristics of cable actuation. We design customized fiducial markers to collect physical joint configurations as a dataset. Result on a study comparing the learning performance of four Deep Neural Network (DNN) models show that the Temporal Convolution Network (TCN) demonstrates the highest predictive capability. Leveraging trained TCNs, we build a control algorithm to compensate for hysteresis. Tracking tests in task space using unseen trajectories show that the best controller reduces the mean position and orientation error by 61.39% (from 13.7 mm to 5.29 mm) and 64.04% (from 31.17{\deg} to 11.21{\deg}), respectively.