深度学习下盲人避撞路径导航方法研究
作者:
中图分类号:

TP273

基金项目:

安徽省自然科学基金(2008085MF201);安徽省高校自然科学重点研究项目(KJ2019A1295);安徽省高校优秀青年人才支持计划(gxyq2020107)


Deep learning-based navigation path planning with collision avoidance for the blind
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • | | |
  • 文章评论
    摘要:

    传统导航方法只能检测出路径上存在的静止障碍物,无法检测出运动障碍物,为此提出基于深度学习的盲人避撞路径导航方法.收集语音信号,利用语音识别模型获取语音特征参数,根据语音特征参数识别出盲人输入的语音序列内容,确定盲人所要到达的目的地.构建障碍物检测模型,检测盲人所在位置与其目的地路径上障碍物的形状特征及其运动方向、速度,并计算初始位置与到达位置的距离.利用深度学习中的卷积神经网络规划出最优避撞路径,实现盲人避撞路径导航.实验结果显示,该方法检测出来的障碍物在x轴和y轴上的径向运动速度相差无几,可以实时跟踪监测障碍物的移动方向及运动速度.本研究方法所得速度与障碍物的实际运动速度基本一致,误差在0.2~0.4 cm/s之间,且在测试时间为50 min时,避障精准度达到96.5%,能够实现最优避撞路径规划及导航.

    Abstract:

    Moving obstacles,unlike stationary ones,cannot be located or avoided by traditional navigation technologies.To address this,a collision avoidance navigation path planning strategy for blind people based on deep learning is proposed.First,a speech recognition system is used to collect speech signal and sort out the speech feature parameters,which is then analyzed to obtain the speech sequence input thus recognize the destination.Second,an obstacle detection model is constructed to detect the edge features as well as moving directions and velocities of the obstacles on the path to destination.Then a convolutional neural network of deep learning is exploited to plan the optimal path with collision avoidance.Finally,experiments are conducted and the results show that the radial velocity of the moving obstacles detected by this model is consistent with actual conditions,specifically,when the actual speed is 33.6 cm/s,the detected speed error is in the range of 0.2-0.4 cm/s,and the accuracy of obstacle avoidance reaches 96.5% when the test time lasts 50 min.It can be concluded that the proposed strategy can realize the optimal path planning and navigation with collision avoidance for the blind people.

    参考文献
    [1] 赵晓艳,王嘉铭,董燕丽,等.四足机器人的障碍检测及躲避系统设计[J].南方农机,2020,51(8):140-142 ZHAO Xiaoyan,WANG Jiaming,DONG Yanli,et al.Design of obstacle detection and avoidance system for quadruped robot[J].China Southern Agricultural Machinery,2020,51(8):140-142
    [2] 倪天,魏瑞轩,赵晓林,等.基于威胁度评估的机器人神经动态避撞策略[J].机器人,2017,39(6):853-859 NI Tian,WEI Ruixuan,ZHAO Xiaolin,et al.Neural dynamic collision-avoidance strategy for robots based on evaluation of threat degree[J].Robot,2017,39(6):853-859
    [3] 霍彦明,姜峰,冯怡林,等.基于波束赋形技术与V290pub语音模块的新型降噪语音识别系统[J].现代电子技术,2020,43(10):46-50 HUO Yanming,JIANG Feng,FENG Yilin,et al.Novel denoising speech recognition system based on beam forming technology and V290pub speech module[J].Modern Electronics Technique,2020,43(10):46-50
    [4] 张瑞珍,韩跃平,张晓通.基于深度LSTM的端到端的语音识别[J].中北大学学报(自然科学版),2020,41(3):244-248 ZHANG Ruizhen,HAN Yueping,ZHANG Xiaotong.End-to-end speech recognition based on depth-gated LSTM[J].Journal of North University of China (Natural Science Edition),2020,41(3):244-248
    [5] 孙伟,宋如意,王宇航.视觉/惯性组合导航中的SWF与MSCKF对比研究[J].中国矿业大学学报,2020,49(1):198-204 SUN Wei,SONG Ruyi,WANG Yuhang.A comparative research of SWF and MSCKF on visual/inertial integrated navigation[J].Journal of China University of Mining&Technology,2020,49(1):198-204
    [6] 刘娟宏,胡彧,黄鹤宇.端到端的深度卷积神经网络语音识别[J].计算机应用与软件,2020,37(4):192-196 LIU Juanhong,HU Yu,HUANG Heyu.End-to-end speech recognition based on deep convolution neural network[J].Computer Applications and Software,2020,37(4):192-196
    [7] 卢洵波,李昕.特征融合的VAD方法在语音识别系统中的应用[J].电子测量技术,2020,43(7):129-136 LU Xunbo,LI Xin.Speech recognition system with combined features of voice activity detection[J].Electronic Measurement Technology,2020,43(7):129-136
    [8] 王建平,马兰兰,孙伟.基于声纹识别的智能照明语音识别算法研究[J].传感器与微系统,2020,39(6):37-40,44 WANG Jianping,MA Lanlan,SUN Wei.Research on intelligent lighting speech recognition algorithm based on voiceprint recognition[J].Transducer and Microsystem Technologies,2020,39(6):37-40,44
    [9] 李云.基于改进K中心点的语音分组识别算法[J].电子设计工程,2020,28(10):152-155 LI Yun.Grouping voice recognition algorithm based on improved K center point[J].Electronic Design Engineering,2020,28(10):152-155
    [10] 姜正伟,李鹏旭,张斌,等.基于车速依赖静态输出反馈的自主汽车路径跟踪控制[J].南京信息工程大学学报(自然科学版),2021,13(1):41-50 JIANG Zhengwei,LI Pengxu,ZHANG Bin,et al.Path-following control of autonomous vehicles based on velocity-dependent static output-feedback strategy[J].Journal of Nanjing University of Information Science&Technology (Natural Science Edition),2021,13(1):41-50
    [11] 宋广虎,冯全,海洋,等.采用深度学习法优化的葡萄园行间路径检测[J].林业机械与木工设备,2019,47(7):23-27 SONG Guanghu,FENG Quan,HAI Yang,et al.Vineyard inter-row path detection based on deep learning[J].Forestry Machinery&Woodworking Equipment,2019,47(7):23-27
    [12] Polvara R,Sharma S,Wan J,et al.Obstacle avoidance approaches for autonomous navigation of unmanned surface vehicles[J].Journal of Navigation,2018,71(1):241-256
    [13] Phan D,Yang J X,Grosu R,et al.Collision avoidance for mobile robots with limited sensing and limited information about moving obstacles[J].Formal Methods in System Design,2017,51(1):62-86
    [14] Fraga-Lamas P,Ramos L,Mondéjar-Guerra V,et al.A review on IoT deep learning UAV systems for autonomous obstacle detection and collision avoidance[J].Remote Sensing,2019,11(18):2144
    [15] Sangiovanni B,Incremona G P,Piastra M,et al.Self-configuring robot path planning with obstacle avoidance via deep reinforcement learning[J].IEEE Control Systems Letters,2021,5(2):397-402
    [16] 王毅,刘波,熊龙烨,等.基于深度学习的果园道路导航线生成算法研究[J].湖南农业大学学报(自然科学版),2019,45(6):674-678 WANG Yi,LIU Bo,XIONG Longye,et al.Research on generating algorithm of orchard road navigation line based on deep learning[J].Journal of Hunan Agricultural University (Natural Sciences),2019,45(6):674-678
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

张海民,程菲.深度学习下盲人避撞路径导航方法研究[J].南京信息工程大学学报(自然科学版),2022,14(2):220-226
ZHANG Haimin, CHENG Fei. Deep learning-based navigation path planning with collision avoidance for the blind[J]. Journal of Nanjing University of Information Science & Technology, 2022,14(2):220-226

复制
分享
文章指标
  • 点击次数:91
  • 下载次数: 1431
  • HTML阅读次数: 85
  • 引用次数: 0
历史
  • 收稿日期:2021-03-27
  • 在线发布日期: 2022-04-27

地址:江苏省南京市宁六路219号    邮编:210044

联系电话:025-58731025    E-mail:nxdxb@nuist.edu.cn

南京信息工程大学学报 ® 2025 版权所有  技术支持:北京勤云科技发展有限公司