基于点激光精确导航的手术机械臂引导系统
Surgical Robotic Arm Guidance System Based on Point Laser Precise Navigation
宋科夫 1汤睿 2郭霏霏 3沈泽鑫 2曾辉雄 2李俊4
作者信息
- 1. 中国科学院福建物质结构研究所,福建 福州 350117;中国科学院大学,北京 100049
- 2. 中国科学院福建物质结构研究所,福建 福州 350117
- 3. 泉州职业技术大学,福建 泉州 362000
- 4. 中国科学院福建物质结构研究所,福建 福州 350117;泉州职业技术大学,福建 泉州 362000
- 折叠
摘要
随着图像检测相关技术的发展以及对手术技术需求的增加,自动化手术引导系统在临床场景中日渐重要.然而该系统需要具备实时性的视觉精确引导,限制了临床手术的应用范围.当视觉信号引导机械臂进行路径规划时,传统算法规划效率低的不足限制了系统实时性.针对上述问题,提出一种基于点激光引导手术机械臂的导航控制系统,视觉部分基于YOLOv5网络,利用超分辨率重建(SRCNN)算法进行预处理,提出融合特征聚合及单尺度识别改进策略,快速精确跟踪点激光.在运动规划方面,提出一种结合目标偏置以及双向扩展的快速随机搜索树(RRT)算法,利用病灶点云信息约束目标点姿态,对生成路径进行碰撞检测和规划决策.通过实验验证了上述方法的有效性和可行性,优化算法在交并比(IoU)阈值0.5下的平均精度均值(AP50)为97.6%,AP75识别精度达83.5%.相比传统视频目标识别的YOLOv5算法提升幅度达7.2百分点,改进RRT*算法能准确快速地规划出最优避障路径.
Abstract
Automated surgical guidance systems are increasingly important in clinical settings,driven by advancements in image detection technologies and the growing demand for surgical procedures.However,the need for the system to have real-time visual precision guidance restricts the range of applications in clinical surgery.When a visual signal guides the robotic arm for path planning,the inefficiency of traditional algorithms in low planning can hinder the real-time capability of the system.To address these problems,a navigation control system based on a point-laser-guided surgical robotic arm is proposed.The visual part is based on the YOLOv5 network and preprocessed using the super-resolution reconstruction algorithm.Fusion feature aggregation and single-scale recognition improvement strategies are proposed to achieve rapid and accurate point-laser tracking.For motion planning,a rapidly-exploring random tree(RRT)algorithm that integrates target bias and bidirectional expansion is proposed to constrain the target point attitude using lesion point cloud information for collision pre-detection and planning decision during path generation.The validity and feasibility of the proposed algorithm were verified through experiments,demonstrating that the optimized algorithm achieves an AP50 recognition accuracy of 97.6%and an AP75 recognition accuracy of 83.5%.Moreover,the improved RRT algorithm accurately and rapidly plans the optimal obstacle avoidance path,achieving a 7.2 percentage points improvement over YOLOv5 in traditional video target recognition.
关键词
YOLOv5/多尺度融合/快速随机搜索树/姿态约束/路径规划Key words
YOLOv5/multi-scale integration/rapidly-exploring random trees/postural restraints/path planning引用本文复制引用
基金项目
国家自然科学基金(62001452)
中国福建光电信息科学与技术创新实验室(闽都创新实验室)(2021ZZ116)
福州市科技计划项目(2022-ZD-001)
出版年
2024
NETL
NSTL
万方数据