BP神经网络在无人车避障中的应用

宋建辉; 樊思萌; 刘砚菊; 邹波

doi:10.3788/OPE.20172513.0274

您当前的位置：

首页 >

文章列表页 >

BP神经网络在无人车避障中的应用

信息科学 | 更新时间：2020-08-13

- BP神经网络在无人车避障中的应用
- Application of BP neural network in obstacle avoidance of driverless car
- 光学精密工程 2017年25卷第10s期页码：274-280
- 作者机构：
  
  沈阳理工大学自动化与电气工程学院, 辽宁沈阳 110159
- 作者简介：
- 基金信息：
  
  辽宁省教育厅一般资助项目（No.2014079）();沈阳理工大学重点实验室开放基金资助项目（No.4771004kfs53）()
- DOI：10.3788/OPE.20172513.0274
  中图分类号： TP24;U463.67
- 收稿日期：2017-06-30，
  
  修回日期：2017-07-10，
  
  纸质出版日期：2017-11-25
- 稿件说明：
移动端阅览
宋建辉, 樊思萌, 刘砚菊等. BP神经网络在无人车避障中的应用[J]. 光学精密工程, 2017,25(10s): 274-280

SONG Jian-hui, FAN Si-meng, LIU Yan-ju etc. Application of BP neural network in obstacle avoidance of driverless car[J]. Editorial Office of Optics and Precision Engineering, 2017,25(10s): 274-280
宋建辉, 樊思萌, 刘砚菊等. BP神经网络在无人车避障中的应用[J]. 光学精密工程, 2017,25(10s): 274-280 DOI： 10.3788/OPE.20172513.0274.

SONG Jian-hui, FAN Si-meng, LIU Yan-ju etc. Application of BP neural network in obstacle avoidance of driverless car[J]. Editorial Office of Optics and Precision Engineering, 2017,25(10s): 274-280 DOI： 10.3788/OPE.20172513.0274.

摘要

为了实现无人车环境障碍信息与执行动作模式指令之间的合理匹配，提出了一种基于BP（Back Propagation）神经网络的无人车避障技术。建立了BP神经网络环境信息识别模型，将单线激光雷达所探测到无人车前方180°的平面区域分成8个子区域，每个子区域的扫描范围为22.5°，将8个子区域内的环境障碍物信息作为BP神经网络系统的输入特征向量，将标识控制无人车的动作指令作为BP神经网络系统的输出向量，通过BP神经网络对输入的环境编码信息与执行的动作指令之间进行匹配。实验结果表明，基于BP神经网络的无人车避障模型得出的结果与期望的目标值之间误差控制在0.001内，实现了环境编码信息与执行的动作指令之间的准确快速分类匹配，达到了无人车合理有效躲避障碍物的目的。

Abstract

In order to achieve the reasonable matching of the environmental obstacle information of driverless car and the performed action command mode

the BP neural network applied to the obstacle avoidance of driverless car in the article and technology of obstacle avoidance of driverless car based on BP neural network was researched. The environmental information identification model of BP neural network was established. The 180° planar domain detected by single line laser radar in front of the driverless car was divided into 8 sub-domains and the scan range of each sub-domain was 22.5°. The information of environmental obstacles of the 8 sub-domains was taken as the input feature vector of BP neural network system and the action command of the driverless car controlled by identification was taken as the output vector of BP neural network system. The input environmental coding information matched with the performed action command by using BP neural network. The experimental result shows that the error between the obtained result of the obstacle avoidance model of driverless car based on BP neural network and expected target value is controlled within the range of 0.001 and the accurate and quick classification matching between environmental coding information and the performed action command is achieved

and the aim of driverless car reasonably and effectively avoiding obstacles is achieved.

关键词

Keywords

references

NILS G, PAUL B, SERGIO M. Obstacle detection and collision avoidance for a UAV with complementary low-cost sensors[J]. IEEE Journals & Magazines, 2015, 3:599-609.

赵海,陈星池,王家亮,等. 基于四轴飞行器的单目视觉避障算法[J]. 光学精密工程, 2014,22(8):2232-2241. ZHAO H, CHEN X CH, WANG J L, et al.. Obstacle avoidance algorithm based on monocular vision for quad-rotor helicopter[J]. Opt. Precision Eng., 2014, 22(8):2232-2241.(in Chinese)

GAYATRI A, ANUJA D, JOYCE F, et al.. Virtual reality-based navigation task to reveal obstacle avoidance performance in individuals with visuospatial neglect[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2015, 23(2):179-188.

SOUHILA K, KARIM A. Optical flow based robot obstacle avoidance[J]. International Journal of Advanced Robotic Systems, 2007, 4(1):13-16.

王浩,谭振文,王治彪,等. 基于STM32的分体式超声测距与目标定位系统[J]. 仪表技术与传感器, 2017, (2):58-61. WANG H, TAN ZH W, WANG ZH B, et al.. Separated ultrasonic ranging and targeting system based on STM32[J]. Instrument Technique and sensor, 2017,(2):58-61.(in Chinese)

李庆, 郑力新,潘书万,等. 使用单目视觉的移动机器人导航方法[J]. 计算机工程与应用, 2017, 53(4):223-227. LI Q, ZHENG L X, PAN SH W, et al.. Method of mobile robot navigation using monocular vision[J]. Computer Engineering and Applications, 2017,53(4):223-227.(in Chinese)

张启彬,王鹏,陈宗海. 基于速度空间的移动机器人同时避障和轨迹跟踪方法[J]. 控制与决策,2017, 32(2):358-362. ZHANG Q B, WANG P, CHEN Z H. Velocity space based concurrent obstacle avoidance and trajectory tracking for mobile robots[J]. Control and Decision, 2017, 32(2):358-362.(in Chinese)

蔡卓凡. 基于多超声波传感器避障机器人小车的设计[J]. 自动化技术与应用, 2014, 33(5):85-89. CAI ZH F. Design of obstacle-avoiding robot car based on multi-ultrasonic sensors[J]. Techniques of Automation & Applications, 2014,33(5):85-89. (in Chinese)

陈奕君. 基于多传感器信息融合的机器人避障研究[D].黑龙江:东北石油大学, 2014. CHEN Y J. Research on obstacle avoidance of mobile robot based on multi-sensor information fusion[D].Heilongjiang:Northeast Petroleum University, 2014. (in Chinese)

易礼智. 基于机器视觉的避障智能小车系统研究[D]. 长沙:中南大学, 2012. YIN L ZH. Research on obstacle avoidance smart car system based on machine vision[D]. Changsha:Central South University, 2012. (in Chinese)

杨斐, 王坤明, 马欣, 等. 应用BP神经网络分类器识别交通标志[J]. 计算机工程, 2003, 29(10):120-121. YANG F, WANG K M, MA X, et al.. Application of BP neural network classifier for road traffic sign recognition[J]. Computer Engineering, 2003, 29(10):120-121. (in Chinese)

秦国华, 谢文斌, 王华敏. 基于神经网络与遗传算法的刀具磨损检测与控制[J]. 光学精密工程, 2015, 23(5):1314-1321. QIN G H, XIE W B, WANG H M. Detection and control for tool wear based on neural network and genetic algorithm[J]. Opt. Precision Eng., 2015, 23(5):1314-1321. (in Chinese)

周求湛, 王聪香, 李亚强. 基于小波包和BP神经网络的周界入侵防御系统目标识别[J]. 光学精密工程, 2015,23(10z):806-813. ZHOU Q ZH, WANG C X, LI Y Q. Target recognition of perimeter intrusion defense system based on wavelet packet and BP neural network[J]. Opt. Precision Eng., 2015,23(10z):806-813. (in Chinese)

浏览量

535

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

高频磁致伸缩换能器输出特性测试与优化控制

精密减速器检测仪测角误差补偿

基于Pearson关联度BP神经网络的时间序列预测

精密加工实验台热误差建模与补偿方法的对比分析

基于小波包和BP神经网络的周界入侵防御系统目标识别