导盲犬行走机构运动仿真及其视觉识别算法研究

doi:10.16180/j.cnki.issn1007-7820.2021.09.012

Abstract

Abstract:

In view of problems such as high training cost for guide dogs, this study proposes a walking mechanism with visual recognition function, which can realize a single stepper motor to drive a four-legged mechanism to walk. Through the simulation of the movement of the walking mechanism, the obtained data show that the four feet can alternately rise and fall relative to the ground, and can run smoothly in a more complex non-structural environment. Taking the recognition of the traffic lights on the crosswalk as an example, a visual recognition algorithm for mechanical guide dogs based on YOLO is proposed to determine whether the current signal status is passable. The mechanical guide dog recognizes 87.96% of the green light and 89.38% of the red light, and the detection speed is 23.5 frame·s^-1,indicating that the mechanical guide dog can detect and distinguish the traffic light information of pedestrian crossings in real time.

Key words: Jansen mechanism, motion curve, unstructured environment, bionic degree, deep learning, feature fusion, target detection, loss function

CLC Number:

TP391.41

ZHAO Chong,CHI Mengmeng,CHU Cong,ZHANG Peng. Research on Motion Simulation and Visual Recognition Algorithm of Guide Dog Walking Mechanism[J].Electronic Science and Technology, 2021, 34(9): 66-72.

Figures/Tables 12

Figure 1.

Figure 2.

Table1

Figure 3.

Figure 4.

Table 2

Figure 5.

Figure 6.

Table 3

Figure 7.

Figure 8.

Figure 9.

References 20

[1]	王国彪, 陈殿生, 陈科位, 等. 仿生机器人研究现状与发展趋势[J]. 机械工程学报, 2015, 51(13):27-44.
	Wang Guobiao, Chen Diansheng, Chen Kewei, et al. The current research status and development strategy on biomimetic robot[J]. Journal of Mechanical Engineering, 2015, 51(13):27-44.
[2]	曾婧婧, 杨平, 徐春梅, 等. 机器导盲犬的设计与实现[J]. 机电一体化, 2005, 11(4):22-25.
	Zeng Jingjing, Yang Ping, Xu Chunmei, et al. Design and implementation of a robot guide dog[J]. Mechatronics, 2005, 11(4):22-25.
[3]	花良浩, 杨润贤. 基于双控制技术的智能机器导盲犬的设计与实现[J]. 太原城市职业技术学院学报, 2015(11):194-196.
	Hua Lianghao, Yang Runxian. Design and implementation of intelligent robot guide dog based on dual control technology[J]. Journal of Taiyuan Urban Vocational College, 2015(11):194-196.
[4]	谢济励. 基于IDEO方法的机器导盲犬开发设计流程[J]. 科技创新与生产力, 2017(1):82-84.
	Xie Jili. Development and design process of machine guide dog based on IDEO method[J]. Sci-tech Innovation and Productivity, 2017(1):82-84.
[5]	雷静桃, 张悦文, 饶进军. 四足机器人刚柔耦合仿生脊柱研究进展[J]. 科技导报, 2020, 38(2):35-49.
	Lei Jingtao, Zhang Yuewen, Rao Jinjun. Research progress of rigid-flexible coupling bionic spine of quadruped robot[J]. Science & Technology Review, 2020, 38(2):35-49.
[6]	陈阳, 徐晓丹, 李向攀. 基于Arduino控制的气动软体仿生四足机器人结构设计及步态规划[J]. 液压与气动, 2020(5):86-90.
	Chen Yang, Xu Xiaodan, Li Xiangpan. Structural design and gait planning of pneumatic soft bionic quadruped robot based on arduino control[J]. Chinese Hydraulics & Pneumatics, 2020(5):86-90.
[7]	李潮, 崔承勋. 四足仿生机器人的设计[J]. 南方农机, 2020, 51(7):37-40.
	Li Chao, Cui Chengxun. The design of a bionic four-legged robot[J]. China Southern Agricultural Machinery, 2020, 51(7):37-40.
[8]	赵涓涓, 李强, 任美荣. 六足仿生机器人运动控制系统的设计[J]. 机电工程技术, 2008, 37(12):44-45.
	Zhao Juanjuan, Li Qiang, Ren Meirong. Design for motorial control system of hexapod robot[J]. Mechanical & Electrical Engineering Technology, 2008, 37(12):44-45.
[9]	单东升, 何亚磊. 一种六足军用机器人行走机构的设计与优化[J]. 装甲兵工程学院学报, 2018, 32(3):72-76.
	Shan Dongsheng, He Yalei. Design and optimization of hexapod walking mechanism for military robot[J]. Journal of Academy of Armored Force Engineering, 2018, 32(3):72-76.
[10]	臧红彬, 沈连婠. Theo Jansen仿生腿研究及其机构优化设计[J]. 机械工程学报, 2017, 53(15):101-109.
	Zang Hongbin, Shen Lianguan. Research and optimization design of mechanism for Theo Jansen bionic leg[J]. Journal of Mechanical Engineering, 2017, 53(15):101-109.
[11]	马宏平, 蒋励, 宋竹青, 等. 多方向红外测距新型智能导盲杖[J]. 光学仪器, 2012, 34(5):84-88.
	Ma Hongping, Jiang Li, Song Zhuqing, et al. Study on a new type of intelligent blind-guiding stick[J]. Optical Instruments, 2012, 34(5):84-88.
[12]	孟祥薇, 严锡君, 欧阳星辰, 等. 基于超声波传感器的导盲杖设计[J]. 电子设计工程, 2012, 20(17):11-14.
	Meng Xiangwei, Yan Xijun, Ouyang Xingchen, et al. Design of blind guiding crutch based on ultrasonic sensor[J]. Electronic Design Engineering, 2012, 20(17):11-14.
[13]	张长青, 杨楠. 一种面向交通标志识别系统的图像识别算法[J]. 电子科技, 2019, 32(7):60-64.
	Zhang Changqing, Yang Nan. An image recognition algorithm for traffic sign recognition system[J]. Electronic Science and Technology, 2019, 32(7):60-64.
[14]	张达峰, 刘宇红, 张荣芬. 基于深度学习的智能辅助驾驶系统[J]. 电子科技, 2018, 31(10):60-63.
	Zhang Dafeng, Liu Yuhong, Zhang Rongfen. Intelligent assistant driving system based on deep leaning[J]. Electronic Science and Technology, 2018, 31(10):60-63.
[15]	Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection[C]. Seattle:IEEE Conference on Conputer Vision and Pattern Recognition, 2016.
[16]	Redmon J, Farhadi A. YOLO9000:Better,Faster,Stronger[C]. Honolulu:The Thirtieth International IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2017.
[17]	叶飞, 刘子龙. 基于改进YOLOV3算法的行人检测研究[J]. 电子科技, 2021, 34(1):5-9.
	Ye Fei, Liu Zilong. Pelestrian detection based on improved YOLOV3 algorithm[J]. Electronic Science and Technology, 2021, 34(1):5-9.
[18]	袁小平, 王岗, 王晔枫, 等. 基于改进卷积神经网络的交通标志识别方法[J]. 电子科技, 2019, 32(11):28-32.
	Yuan Xiaoping, Wang Gang, Wang Yefeng, et al. Traffic sign recognition method based on improved convolutional neural network[J]. Electronic Science and Technology, 2019, 32(11):28-32.
[19]	吕铄, 蔡烜, 冯瑞. 基于改进损失函数的YOLOv3网络[J]. 计算机系统应用, 2019, 28(2):1-7.
	Lü Shuo, Cai Xuan, Feng Rui. YOLOv3 network based on improved loss function[J]. Computer Systems & Applications, 2019, 28(2):1-7.
[20]	李珣, 刘瑶, 李鹏飞, 等. 基于Darknet框架下YOLO v2算法的车辆多目标检测方法[J]. 交通运输工程学报, 2018, 18(6):142-158.
	Li Xun, Liu Yao, Li Pengfei, et al. Vehicle multi-target detection method based on YOLO v2 algorithm under darknet framework[J]. Journal of Traffic and Transportation Engineering, 2018, 18(6):142-158.

参数	取值
固定位置	导盲犬机体
电机输出转速	0.1 rad·s^-1
运行时间	10 s
数据采集点	行走机构四肢末端
输出数据结果	相对于地面的高度

测试对象	红灯、绿灯
样本数量/张	493
训练集数量/张	318
验证集数量/张	75
测试集数量/张	100
样本尺寸/像素	416×416

参数	取值
动量	0.9
学习率	0.001
Batch	64
Subdivision	32
迭代次数	7 500

Research on Motion Simulation and Visual Recognition Algorithm of Guide Dog Walking Mechanism

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 20

Related Articles 15

Metrics

Comments

Recommended 10

[1]	CHENG Xiaoya,ZHANG Lei. Research on Occluded Face Recognition Method Based on Deep Learning [J]. Electronic Science and Technology, 2022, 35(1): 35-39.
[2]	ZHAN Yinwei,ZHU Baiwan,YANG Zhuo. Research and Application of Vehicle Face Recognition Algorithm [J]. Electronic Science and Technology, 2021, 34(8): 1-7.
[3]	MA Lixin,DOU Chenfei,SONG Chencan,YANG Tianxiao. Insulator Nondestructive Testing Based on Feature Fusion CNN [J]. Electronic Science and Technology, 2021, 34(7): 26-30.
[4]	XUE Yongjie,JU Zhiyong. Fish Recognition Algorithm Based on Improved AlexNet [J]. Electronic Science and Technology, 2021, 34(4): 12-17.
[5]	SHAO Hang,WANG Yongxiong,QIN Yulong. Digital Image Composition Optimization Based on Salient Feature Algorithm [J]. Electronic Science and Technology, 2021, 34(3): 36-42.
[6]	YAN Chao,SUN Zhanquan,TIAN Engang,ZHAO Yangyang,FAN Xiaoyan. Research Progress of Medical Image Segmentation Based on Deep Learning [J]. Electronic Science and Technology, 2021, 34(2): 7-11.
[7]	PEI Xiaofang, HU Min. Study on the Identification of Various Growth and Monitoring of Pest and Disease of Rhododendron [J]. Electronic Science and Technology, 2021, 34(1): 17-22.
[8]	YE Fei, LIU Zilong. Pedestrian Detection Based on Improved YOLOv3 Algorithm [J]. Electronic Science and Technology, 2021, 34(1): 5-9.
[9]	ZHANG Zechen,JU Zhiyong. Multi-feature Fusion Fruit and Vegetable Image Classification Based on Bag of Feature Model [J]. Electronic Science and Technology, 2020, 33(7): 41-45.
[10]	WANG Chunjiang,LI Peng. Design of Moving Target Detection System Based on ZYNQ [J]. Electronic Science and Technology, 2020, 33(5): 82-86.
[11]	SI Qin,LI Feifei,CHEN Qiu. Face Recognition Algorithm Based on Deep Learning and Feature Fusion [J]. Electronic Science and Technology, 2020, 33(4): 18-22.
[12]	CHENG Junhua,ZENG Guohui,LIU Jin. Research on Complex Background Image Classification Method Based on Deep Learning [J]. Electronic Science and Technology, 2020, 33(12): 59-66.
[13]	GUAN Hongyun,SU Zhentao,WANG Chen. Improved Background Subtraction Based on Feature Fusion [J]. Electronic Science and Technology, 2020, 33(12): 22-27.
[14]	SHAO Yu'e,WANG Jianlai,ZHOU Shenghua,LIU Hongwei,ZHANG Yuehong. Radar Pulse Compression Method Based on LASSO [J]. Electronic Science and Technology, 2020, 33(11): 7-10.
[15]	WU Qian,WU Fei,LUO Lizhi. Human Skeleton-based Action Recognition Based on Deep Learning [J]. Electronic Science and Technology, 2020, 33(11): 79-83.