谢意林,燕必希,王君,孙鹏

• 1:北京信息科技大学仪器科学与光电工程学院

摘要(Abstract)：

针对类人足球机器人在图像模糊、小目标检测与资源受限条件下的交叉点检测与全局定位问题，提出了一种融合深度学习与粒子滤波的定位方法。在YOLOv11中引入空间与通道协同注意力（spatial and channel synergetic attention,SCSA）和多尺度卷积模块（multi-scale convolutional block,MSCB），提升场地线交叉点检测精度与鲁棒性。结合机器人坐标系下的交叉点定位模型构建观测输入，并在粒子滤波算法中引入观测置信约束、自适应采样与遗传优化重采样策略，提升粒子多样性与状态估计精度。实验结果表明，改进YOLOv11模型的mAP_(50)达97.3%，计算量降至19.8 GFLOPs；实机定位误差最大为45.9 mm，算法在不同区域均保持稳定性能，整体精度满足机器人世界杯（robot world cup,RoboCup）类人组比赛对全局定位的需求。

关键词(KeyWords)： 机器人;目标检测;YOLOv11;粒子滤波;全局定位

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 谢意林,燕必希,王君,孙鹏

DOI: 10.16508/j.cnki.11-5866/n.2025.03.011

参考文献(References)：

• [1] KHAN S,ALI S,IQBAL K F,et al. Active interception of moving ball:a multi-player strategy for humanoid soccer robots[J].Multimedia Tools and Applications,2024:1-17.
• [2]白晓遥，燕必希，王君，等.类人足球机器人场地线检测及定位[J].北京信息科技大学学报（自然科学版），2021,36(5):63-67.BAI X Y,YAN B X,WANG J,et al. Detection and location of humanoid robot soccer field line[J]. Journal of Beijing Information Science&Technology University,2021,36(5):63-67.(in Chinese)
• [3] ROSSI A,PAETZEL-PRüSMANN M,KEIJSERS M,et al. The human in the loop perspectives and challenges for RoboCup 2050[J]. Autonomous Robots,2024,48(2):8.
• [4] R?FER T,LAUE T,HASSELBRING A,et al. B-Human 2021-playing soccer out of the box[C]//RoboCup 2021:Robot World Cup XXIV. Berlin,Germany:Springer Science and Business Media Deutschland GmbH,2022:302-313.
• [5] XIAO L. Soccer robot localization detection model based on Monte Carlo particle filter and template matching algorithm[J].IEEE Access,2023,11:128473-128483.
• [6]熊干，陈慈发，张上.基于QMDF-YOLO11的复杂场景下水稻害虫的检测[J/OL].计算机工程与应用，1-15(2025-03-17)[2025-03-27]. http：//kns. cnki. net/kcms/detail/11. 2127. tp.20250315. 1503. 002. html.XIONG G,CHEN C F,ZHANG S. Detection of rice pests in complex scenes based on QMDF-YOLO11[J/OL]. Computer Engineering and Applications,1-15(2025-03-17)[2025-03-27]. http：//kns. cnki. net/kcms/detail/11. 2127. tp. 20250315.1503. 002. html.(in Chinese)
• [7] EDER M,REIP M,STEINBAUER G. Creating a robot localization monitor using particle filter and machine learning approaches[J]. Applied Intelligence,2022,52(6):6955-6969.
• [8] WIESMANN L,GUADAGNINO T,VIZZO I,et al. LocNDF:neural distance field mapping for robot localization[J]. IEEE Robotics and Automation Letters,2023,8(8):4999-5006.
• [9] YU Z H,SI Z J,LI X B,et al. A novel hybrid particle swarm optimization algorithm for path planning of UAVs[J]. IEEE Internet of Things Journal,2022,9(22):22547-22558.
• [10] SI Y Z,XU H Y,ZHU X Z,et al. SCSA:exploring the synergistic effects between spatial and channel attention[J].Neurocomputing,2025,634:129866.
• [11] LIU J J,HOU Q B,CHENG M M,et al. Improving convolutional networks with self-calibrated convolutions[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Los Alamitos,CA,USA:IEEE Computer Society,2020:10093-10102.
• [12] DOSOVITSKIY A,BEYER L,KOLESNIKOV A,et al. An image is worth 16×16 words:Transformers for image recognition at scale[C]//9th International Conference on Learning Representations. Washington,DC,USA:ICLR,2021:1-22.
• [13] HUANG H J,CHEN Z G,ZOU Y,et al. Channel prior convolutional attention for medical image segmentation[J].Computers in Biology and Medicine,2024,178:108784.
• [14] RAHMAN M M,MUNIR M,MARCULESCU R. EMCAD:efficient multi-scale convolutional attention decoding for medical image segmentation[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Los Alamitos, CA, USA:IEEE Computer Society,2024:11769-11779.
• [15] SANDLER M,HOWARD A,ZHU M L,et al. MobileNetV2:inverted residuals and linear bottlenecks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York, USA:IEEE,2018:4510-4520.
• [16]燕必希，朱立夫，董明利，等.卡尔曼滤波单目相机运动目标定位研究[J].仪器仪表学报，2018,39(8):220-229.YAN B X,ZHU L F,DONG M L,et al. Research on Kalman filtering in moving target location with monocular camera[J].Chinese Journal of Scientific Instrument,2018,39(8):220-229.(in Chinese)
• [17] ROZSYPáLEK Z, ROU?EK T, VINTR T, et al.Multidimensional particle filter for long-term visual teach and repeat in changing environments[J]. IEEE Robotics and Automation Letters,2023,8(4):1951-1958.
• [18]焦传佳，江明，徐劲松，等.基于激光信息的移动机器人定位研究[J].电子测量与仪器学报，2021,35(9):1-9.JIAO C J,JIANG M,XU J S,et al. Research on positioning of mobile robot based on laser information[J]. Journal of Electronic Measurement and Instrumentation,2021,35(9):1-9.(in Chinese)
• [19]刘海涛，林艳明，陈永华，等.基于遗传算法的智能粒子滤波重采样策略研究[J].电子与信息学报，2021,43(12):3459-3466.LIU H T,LIN Y M,CHEN Y H,et al. A study on resampling strategy of intelligent particle filter based on genetic algorithm[J]. Journal of Electronics&Information Technology,2021,43(12):3459-3466.(in Chinese)
• [20]徐彦威，李军，董元方，等. YOLO系列目标检测算法综述[J].计算机科学与探索，2024,18(9):2221-2238.XU Y W,LI J,DONG Y F,et al. Survey of development of YOLO object detection algorithms[J]. Journal of Frontiers of Computer Science&Technology,2024,18(9):2221-2238.(in Chinese)
• [21]胡欢，邓晗，杨扬，等.基于YOLOv8的足球机器人定位跟踪系统[J].北京信息科技大学学报（自然科学版），2024,39(6):88-95.HU H,DENG H,YANG Y,et al. A YOLOv8-based soccer robot positioning and tracking system[J]. Journal of Beijing Information Science&Technology University(Science and Technology Edition),2024,39(6):88-95.(in Chinese)