Vision-based robot path planning with deep learning
文献类型：会议论文
| 作者 | Cao Y(曹阳) ; Li DC(李德才); He YQ(何玉庆); Wu P(伍平)
|
| 出版日期 | 2017 |
| 会议名称 | 11th International Conference on Computer Vision Systems, ICVS 2017 |
| 会议日期 | July 10-13, 2017 |
| 会议地点 | Shenzhen, China |
| 关键词 | Path planning Convolutional neural network (CNN) Classification |
| 页码 | 101-111 |
| 通讯作者 | He YQ(何玉庆) |
| 中文摘要 | In this paper, a new method based on deep convolutional neural network (CNN) for path planning of robot is proposed, the aim of which is to transform the mission of path planning into a task of environment classification. Firstly, the images of road are collected from cameras installed as required, and then the comprehensive features are abstracted directly from original images through the CNN. Finally, according to the results of classification, the moving direction of robots is exported. In this way, we build an end-to-end recognition system which maps from raw data to motion behavior of robot. Furthermore, experiment has been provided to demonstrate the performance of the proposed method on different roads. |
| 收录类别 | EI |
| 产权排序 | 1 |
| 会议主办者 | City University of Hong Kong Shenzhen Research Institute; et al; Harbin Institute of Technology; Hong Kong University of Science and; Shenzhen Institutes of Advanced Technology, CAS; Technology; TU Wien |
| 会议录 | Computer Vision Systems - 11th International Conference, ICVS 2017, Revised Selected Papers
 |
| 会议录出版者 | Springer Verlag |
| 会议录出版地 | Berlin |
| 语种 | 英语 |
| ISSN号 | 0302-9743 |
| ISBN号 | 978-3-319-68344-7 |
| 源URL | [http://ir.sia.cn/handle/173321/21076]  |
| 专题 | 沈阳自动化研究所_机器人学研究室 |
| 作者单位 | 1.Shenyang Jianzhu University, Shenyang, China 2.Shenyang Institute of Automation Chinese Academy of Sciences, Shenyang, China |
| 推荐引用方式 GB/T 7714 | Cao Y,Li DC,He YQ,et al. Vision-based robot path planning with deep learning[C]. 见:11th International Conference on Computer Vision Systems, ICVS 2017. Shenzhen, China. July 10-13, 2017. |
入库方式： OAI收割
来源：沈阳自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。