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.

翻译：在机器人辅助微创手术（RAMIS）中，手术机器人基座的最优布局对手术成功至关重要。不当的布局会因机械臂的约束限制和不可达工作空间而影响操作性能。传统上，受过训练的医疗人员依赖经验进行基座定位，但这种方式缺乏客观性。本文提出一种基于术者个人工作模式确定最优基座位姿的新方法。该方法采用基于机器学习的聚类技术分析记录的末端执行器位姿，识别术者偏好的关键位置和姿态。针对关节限位和奇异点问题，我们引入两种评分指标：关节裕度评分和可操作度评分。随后训练多层感知器（MLP）回归器，基于这些评分预测最优基座位姿。在采用达芬奇研究套件（dVRK）的仿真环境中进行的评估显示，四位受试者呈现出独特的基座位姿-评分映射，突显了工作模式的个体差异。对采用本文方法确定的基座位姿进行测试后，确认其在我们定义的评分指标上比随机放置机器人时高出约28.2%。这强调了RAMIS基座布局中需进行操作者特异性优化的必要性。