Multi-mode pusher method and experiment based on information fusion

文献类型： 外文期刊

第一作者： Zhang, Qin

作者： Zhang, Qin;Shi, Yangfan;Ren, Hailin;Fan, Changxiang

作者机构：

关键词： Multi-mode; robot; feed delivery method; dairy cow feeding; information fusion

期刊名称：PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE （ 影响因子：1.7； 五年影响因子：1.9 ）

ISSN： 0954-4062

年卷期： 2025 年

页码：

收录情况： SCI

摘要： The regular delivery of feed is an important aspect of the feeding process for dairy cows. Addressing the single-function issue of current feed delivery robots, a multi-mode feed delivery robot structure and delivery method is proposed. Based on the YOLACT instance segmentation model, real-time recognition of dairy cows, feed, and navigation reference objects is conducted. Combined with depth information from binocular cameras, data on feeding demands, location, feed distribution, and navigation is obtained. The robot autonomously selects operating modes according to feeding information, guiding it to perform functions such as feed delivery, collection, distribution, and clearing, meeting the individual needs of dairy cows for free feeding. Research and experimental results demonstrate that the feed delivery robot can autonomously select operating modes in real time based on information collected about grazing dairy cows' location and feed distribution, thereby completing multi-mode feed delivery functions along navigation routes. The positioning accuracy of grazing cows is +/- 0.1 m, while the average accuracy of feed sufficiency judgment is 96.5%. The robot's navigation accuracy is +/- 0.8 cm, and the average accuracy of autonomous mode selection for feed pushing is 97%. Real-time image processing speed during feed delivery reaches 12 frames per second, meeting the real-time operational requirements for multi-mode feed delivery robots in complex environments.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序