Learning to Improve Operational Efficiency from Pose Error Estimation in Robotic Pollination
文献类型：期刊论文
| 作者 | Chen, Jinlong1; Xiao, Jun1; Yang, Minghao2 ; Pan, Hang3
|
| 刊名 | ELECTRONICS
 |
| 出版日期 | 2024-08-01 |
| 卷号 | 13期号:15页码:14 |
| 关键词 | pollination robot transformer offset errors |
| DOI | 10.3390/electronics13153070 |
| 通讯作者 | Xiao, Jun(22032303110@mails.guet.edu.cn) |
| 英文摘要 | Autonomous pollination robots have been widely discussed in recent years. However, the accurate estimation of flower poses in complex agricultural environments remains a challenge. To this end, this work proposes the implementation of a transformer-based architecture to learn the translational and rotational errors between the pollination robot's end effector and the target object with the aim of enhancing robotic pollination efficiency in cross-breeding tasks. The contributions are as follows: (1) We have developed a transformer architecture model, equipped with two feedforward neural networks that directly regress the translational and rotational errors between the robot's end effector and the pollination target. (2) Additionally, we have designed a regression loss function that is guided by the translational and rotational errors between the robot's end effector and the pollination targets. This enables the robot arm to rapidly and accurately identify the pollination target from the current position. (3) Furthermore, we have designed a strategy to readily acquire a substantial number of training samples from eye-in-hand observation, which can be utilized as inputs for the model. Meanwhile, the translational and rotational errors identified in the end-manipulator Cartesian coordinate system are designated as loss targets simultaneously. This helps to optimize the training of the model. We conducted experiments on a realistic robotic pollination system. The results demonstrate that the proposed method outperforms the state-of-the-art method, in terms of both accuracy and efficiency. |
| 资助项目 | Guangxi Key RD Plan Project[AB24010164] ; Guangxi Key RD Plan Project[AB21220038] |
| WOS研究方向 | Computer Science ; Engineering ; Physics |
| 语种 | 英语 |
| WOS记录号 | WOS:001286963200001 |
| 出版者 | MDPI |
| 资助机构 | Guangxi Key RD Plan Project |
| 源URL | [http://ir.ia.ac.cn/handle/173211/59306]  |
| 专题 | 类脑智能研究中心_微观重建与智能分析 |
| 通讯作者 | Xiao, Jun |
| 作者单位 | 1.Guilin Univ Elect Technol, Sch Comp Sci & Informat Secur, Guilin 541000, Peoples R China 2.Chinese Acad Sci CASIA, Inst Automat, Res Ctr Brain Inspired Intelligence BII, Beijing 100190, Peoples R China 3.Changzhi Univ, Dept Comp Sci, Changzhi 046011, Peoples R China |
| 推荐引用方式 GB/T 7714 | Chen, Jinlong,Xiao, Jun,Yang, Minghao,et al. Learning to Improve Operational Efficiency from Pose Error Estimation in Robotic Pollination[J]. ELECTRONICS,2024,13(15):14. |
| APA | Chen, Jinlong,Xiao, Jun,Yang, Minghao,&Pan, Hang.(2024).Learning to Improve Operational Efficiency from Pose Error Estimation in Robotic Pollination.ELECTRONICS,13(15),14. |
| MLA | Chen, Jinlong,et al."Learning to Improve Operational Efficiency from Pose Error Estimation in Robotic Pollination".ELECTRONICS 13.15(2024):14. |
入库方式： OAI收割
来源：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。