正骨机器人术前视觉导航方法与实验验证

Preoperative Visual Navigation Method of Orthopedic Robots and Its Experimental Verification

针对足踝正骨机器人在手术前获取患者脚部目标位姿参数用于机器人引导的需求,提出了一种针对患者脚部目标点云的位姿估计方法。该算法利用主成分分析法获取脚部目标点云的中心点和点云数据最大分布的方向向量,并结合方向包围框对参数进行修正,将最终目标位姿参数用于机器人的视觉引导。开展基于UR5协作机器人的视觉引导实验,验证方法有效性。实验结果表明,利用本文方法得到的结果准确可靠,操作简单方便,可满足正骨手术机器人目标定位的临床需求,为中医正骨的进一步智能化和实际应用提供了理论参考与实践基础。

The ankle orthopedic robot need to obtain the target posture parameters of the patient’s foot for robot guidance before surgery. To solve this problem, a method was proposed to estimate the posture of the target point cloud. Principal component analysis was used to obtain the center position and the direction vector of the maximum distribution of the foot target point cloud, then the orientation bounding box was combined to correct the parameters, the final target posture parameters were used for the visual guidance of the robot. Furthermore, a visual guidance experiment based on the UR5 collaborative robot was carried out to verify the accuracy and reliability of the results. Experimental results show that the results obtained by using this method are accurate and reliable, and the method is simply operate and convenient, which can meet the clinical needs of robot target positioning in orthopedic surgery, and provide a theoretical and practical basis for the practical application of Chinese medicine orthopedic bone combined with robots.