融合目标检测与DWA算法的AGV路径

doi:10.16180/j.cnki.issn1007-7820.2024.07.005

摘要/Abstract

摘要：

针对AGV(Automated Guided Vehicle)叉车处于环境信息未知或环境动态变化情况下的路径规划及导航问题,文中提出了一种由YOLOv5(You Only Look Once version 5)目标检测算法获取目标位置。根据目标位置规划出全局基础路径,再融合DWA(Dynamic Window Approach)局部动态路径规划算法进行AGV路径规划与导航,使AGV叉车在未知环境或局部环境信息未知的环境中能快速识别目标位置并完成路径规划到达目标位置。实验结果表明,相较于改进前方法,文中所提方法在路径长度、耗费时间以及AGV叉车航向误差方面均有良好表现,路径长度平均减少12%,耗费时间平均减少约5%且AGV航向与目标航向的平均误差在5°以内。所提方法提高了AGV叉车在未知环境中的工作效率以及工作灵活性。

关键词: AGV, YOLOv5, DWA算法, 全局路径规划, 局部路径规划, 目标检测, 导航, 自动导引

Abstract:

In view of the path planning and navigation problem when the AGV forklift is in the situation of unknown environment information or dynamic change of environment, a method is proposed to obtain the target position by YOLOv5(You Only Look Once version 5) target detection algorithm. The global basic path is planned according to the target location, and the method of AGV path planning and navigation is integrated with DWA(Dynamic Window Approach) local dynamic path planning algorithm, so that the AGV forklift can quickly identify the target location and complete the path planning to reach the target location in the unknown environment or the environment with unknown local environment information. The experimental results show that compared with the previous method, the proposed method has good performance in terms of path length, time consumption and heading error of AGV forklift truck. The average path length is reduced by 12%, the average time consumption is reduced by about 5%, and the average error between the AGV heading and the target heading is within 5°. The proposed method can improve the working efficiency and flexibility of AGV forklift in unknown environment.

Key words: AGV, YOLOv5, DWA algorithm, global path planning, local path planning, target detection, navigation, automatic guidance

中图分类号:

TP242.6

李筠, 刘虎, 杨海马, 王原, 徐文成, 黄宏欣. 融合目标检测与DWA算法的AGV路径[J]. 电子科技, 2024, 37(7): 33-42.

LI Jun, LIU Hu, YANG Haima, WANG Yuan, XU Wencheng, HUANG Hongxin. Research on AGV Path Fusion of Object Detection and DWA Algorithm[J]. Electronic Science and Technology, 2024, 37(7): 33-42.

图/表 21

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

图13

表1

图14

表2

表3

表4

表5

表6

表7

参考文献 18

[1]	杨海兰, 祁永强, 荣丹. 仓储环境下基于忆阻强化学习的AGV路径规划[J]. 计算机工程与应用, 2023, 59(17):318-327. doi: 10.3778/j.issn.1002-8331.2204-0491
	Yang Hailan, Qi Yongqiang, Rong Dan. AGV path planning based on memristor reinforcement learning in warehouse environment[J]. Computer Engineering and Applications, 2023, 59(17):318-327. doi: 10.3778/j.issn.1002-8331.2204-0491
[2]	张辰贝西, 黄志球. 自动导航车(AGV)发展综述[J]. 中国制造业信息化, 2010, 39(1):53-59.
	Zhang Chenbeixi, Huang Zhiqiu. Evolution summarization of automated guided vehicles(AGV)[J]. Machine Design and Manufacturing Engineering, 2010, 39(1):53-59.
[3]	赵晓, 王铮, 黄程侃, 等. 基于改进A*算法的移动机器人路径规划[J]. 机器人, 2018, 40(6):903-910. doi: 10.13973/j.cnki.robot.170591
	Zhao Xiao, Wang Zheng, Huang Chengkan, et al. Mobile robot path planning based on improved A* algorithm[J]. Robot, 2018, 40(6):903-910.
[4]	Zuo L, Guo Q, Xu X, et al. A hierarchical path planning approach based on A and least-squares policy iteration for mobile robots[J]. Neurocomputing, 2015, 170(6):257-266.
[5]	Yong D, Chen Y, Zhang Y, et al. Fuzzy Dijkstra algorithm for shortest path problem under uncertain environment[J]. Applied Soft Computing, 2012, 12(3):1231-1237.
[6]	Liu J, Yang J, Liu H, et al. An improved ant colony algorithm for robot path planning[J]. Soft Computing, 2017, 21(19):5829-5839.
[7]	Tao Q, Sang H, Guo H, et al. Improved particle swarm optimization algorithm for AGV path planning[J]. IEEE Access, 2021(9):33522-33531.
[8]	Chen X, Gao P. Path planning and control of soccer robot based on genetic algorithm[J]. Journal of Ambient Intelligence and Humanized Computing, 2019(1):1-10.
[9]	Bai X, Jiang H, Cui J, et al. UAV path planning based on improved A * and DWA algorithms[J]. International Journal of Aerospace Engineering, 2021(3):1-12.
[10]	Szczepanski R, Bereit A, Tarczewski T. Efficient local path planning algorithm using artificial potential field supported by augmented reality[J]. Energies, 2021, 14(20):6642-6650.
[11]	Seelinger M, Yoder J D. Automatic pallet engagement by a vision guided forklift[C]. Montreal: Proceedings of the IEEE International Conference on Robotics and Automation, 2005:902-908.
[12]	陈显宝, 金隼, 罗磊, 等. 基于视觉定位的AGV定位精度提高方法[J]. 机械设计与研究, 2021, 37(1):36-40.
	Chen Xianbao, Jin Sun, Luo Lei, et al. AGV parking accuracy improvement method based on visual positioning[J]. Machine Design and Research, 2021, 37(1):36-40.
[13]	梁礼明, 邓广宏, 卢明建, 等. 基于改进YOLOv3的有遮挡行人检测[J]. 传感器与微系统, 2020, 39(5):148-151.
	Liang Liming, Deng Guanghong, Lu Mingjian, et al. Blocked pedestrian detection based on improved YOLOv3[J]. Transducer and Microsystem Technologies, 2020, 39(5):148-151.
[14]	潘卫国, 刘博, 陈英昊, 等. 基于YOLOv3的交通标志牌检测识别[J]. 传感器与微系统, 2019, 38(11):147-150.
	Pan Weiguo, Liu Bo, Chen Yinghao, et al. Traffic sign detection and recognition based on YOLOv3[J]. Transducer and Microsystem Technologies, 2019, 38(11):147-150.
[15]	孔繁望. 基于不同型式AGV的建模及轨迹跟踪控制方法的设计和应用[D]. 杭州: 浙江大学, 2018:63-66.
	Kong Fanwang. Research on modeling and trajectory of AGVs of different typesand design and application racking control methods of different types of AGV[D]. Hangzhou: Zhejiang University, 2018:63-66.
[16]	Tao W, Daichuan Y, Weifeng L, et al. A novel integrated path planning algorithm for warehouse AGVs[J]. Chinese Journal of Electronics, 2021, 30(2):331-338.
[17]	程长文, 陈玮, 陈劲宏, 等. 改进YOLO的口罩佩戴实时检测方法[J]. 电子科技, 2023, 36(2):73-80.
	Chen Changwen, Chen Wei, Chen Jinhong, et al. YOLO-improve detection method of real-time mask wearing[J]. Electronic Science and Technology, 2023, 36(2):73-80.
[18]	张伟, 刘娜, 江洋, 等. 基于YOLO神经网络的垃圾检测与分类[J]. 电子科技, 2022, 35(10):45-50.
	Zhang Wei, Liu Na, Jiang Yang, et al. Garbage detectionand classification based on YOLO neural network[J]. Electronic Science and Technology, 2022, 35(10):45-50.

网络模型	精度/%	FPS/frame·s^-1
改进YOLOv5s	90	30
原YOLOv5s	85	31
YOLOv5m	83	25
YOLOv5l	87	26
Faster RCNN	92	19
SSD	75	26

	路径长度/m	耗费时间/s	航向角度/(°)
基础DWA路径	15.268	27.2	-7
融合DWA路径	13.221	25.8	2
提升效果	减少13%	减少5%	-

	路径长度/m	耗费时间/s	航向角度/(°)
基础DWA路径	20.586	30.8	1
融合DWA路径	13.924	26.2	5
提升效果	减少32%	减少13%	-

	路径长度/m	耗费时间/s	航向角度/(°)
基础DWA路径	-	-	-
融合DWA路径	16.852	29.5	1
提升效果	-	-	-

	路径长度/m	耗费时间/s	航向角度/(°)
基础DWA路径	14.515	26.2	-50
融合DWA路径	13.235	25.6	0
提升效果	减少7%	减少2%	-