基于深度学习的移动机器人自主导航实验平台
投稿时间:2021-09-13  修订日期:2021-09-27  点此下载全文
引用本文:
摘要点击次数: 71
全文下载次数: 0
作者单位邮编
占宏* 华南理工大学自动化科学与工程学院 510640
叶德禧 华南理工大学自动化科学与工程学院 
基金项目:华南理工大学2021年校级教研教改项目(C9213106); 华南理工大学第七批探索性实验项目(C9202240); 华南理工大学2021年学生研究计划(SRP)项目(X202110561738)
中文摘要:随着移动机器人的发展,其应用场景越来越复杂,对自主导航这一关键技术提出了更高要求。本文搭建了移动机器人实验平台,设计了基于深度学习的自主导航方法,将RGB图像作为卷积神经网络模型的输入,即可直接输出导航控制信号,不仅降低硬件成本,而且避免复杂的特征工程和规划策略。实验结果表明该平台具有良好的自主导航性能,对移动机器人适应未知复杂环境作业有着重要参考价值。同时,能够为机器人工程专业实践教学提供实验平台,通过开展相关应用拓展,促进学生创新研究能力的培养。
中文关键词:移动机器人  自主导航  深度学习  卷积神经网络
 
An Experiment Platform for Autonomous Navigation of Mobile Robots based on Deep Learning
Abstract:With the development of mobile robots, application scenarios have become more and more complex, and higher requirements have been put forward for the key technology of autonomous navigation. In this paper, a mobile robot experimental platform is built, and an autonomous navigation method based on deep learning is designed. Given RGM images as the input of the convolutional neural networks, and navigation control signals can be derived directly, which not only reduces the hardware cost, and also avoid complex feature engineering and planning strategies. Experimental results show that the system has good autonomous navigation performances, which has a potential for the application of mobile robots in unknown and complex environments, and also can provide an experimental platform for the practical teaching of robotics engineering to further promote the cultivation of students' innovative research ability through the related application expansions.
keywords:Mobile robots  Autonomous navigation  Deep learning  Convolutional neural networks (CNN)
查看全文   查看/发表评论   下载pdf阅读器