计算机与现代化 ›› 2025, Vol. 0 ›› Issue (09): 20-26.doi: 10.3969/j.issn.1006-2475.2025.09.003

• 人工智能 • 上一篇    下一篇

配网旁路作业机器人目标位姿估计方法

  


  1. (1.国网江苏省电力有限公司常州供电分公司,江苏 常州 213000; 2.南京理工大学自动化学院,江苏 南京 210094)
  • 出版日期:2025-09-24 发布日期:2025-09-24
  • 作者简介: 作者简介:姚杰(1992—),男,江苏常州人,工程师,本科,研究方向:配网不停电作业,E-mail: 979024503@qq.com; 殷洪海,男,高级工程师,本科,研究方向:配网不停电作业; 汪大海,男,工程师,硕士,研究方向:配网不停电作业; 通信作者:李润梓(1998—),男,江苏镇江人,硕士研究生,研究方向:机器视觉,E-mail: 1260058586@qq.com; 张茜雯,女,硕士,研究方向:机器视觉; 郭毓,女,教授,博士,研究方向:复杂系统控制与优化,自适应控制。
  • 基金资助:
      基金项目:国家电网有限公司科技项目(J2023016); 国家自然科学基金面上项目(61973167)
       

Target Pose Estimation Methods for Distribution Network Bypass Operation Robots


  1. (1. Changzhou Power Supply Branch, State Grid Jiangsu Electric Power Co. Ltd., Changzhou 213000, China; 
    2. School of Automation, Nanjing University of Science and Technology, Nanjing 210094, China)
  • Online:2025-09-24 Published:2025-09-24

摘要:
摘要:机器人代替人工完成旁路作业任务,需要其在复杂的作业场景下具有自主估计目标物体位姿的能力。针对旁路作业机器人在复杂背景和不同光照条件下目标位姿的实时估计问题,提出一种基于改进YOLO-6D且融合Transformer模型的6D位姿估计算法(RTFT6D),改进YOLOv8主干网络以提升推理速度,设计一种融合Transformer模型的特征加强网络,提升位姿估计的鲁棒性。实验结果表明,该算法在LINEMOD数据集上的精度超过了大多数基于RGB图像输入的位姿估计算法,并且针对不同光照条件下的配网旁路作业目标具有很好的位姿估计效果。


关键词: 关键词:配网旁路作业机器人, 位姿估计, YOLO-6D, YOLOv8, Transformer

Abstract:
Abstract: To replace humans in bypass operation tasks, robots need the ability to autonomously estimate the pose of target objects in complex work environments. Addressing the problem of real-time pose estimation of targets by bypass operation robots under complex backgrounds and varying lighting conditions, this proposes a 6D pose estimation algorithm (RTFT6D) based on improved YOLO-6D integrated with Transformer model. The YOLOv8 backbone network is modified to enhance inference speed, and a feature enhancement network incorporating the Transformer model is designed to improve the robustness of pose estimation. The experimental results show that the proposed algorithm surpasses most RGB image-based pose estimation algorithms in accuracy on the LINEMOD dataset, and it achieves excellent pose estimation performance for bypass operation targets under different lighting conditions.

Key words: Key words: distribution network bypass operation robot, pose estimation, YOLO-6D, YOLOv8, Transformer

中图分类号: