A Hybrid Cable-Driven Robot for Non-Destructive Leafy Plant Monitoring and Mass Estimation using Structure from Motion
A Hybrid Cable-Driven Robot for Non-Destructive Leafy Plant Monitoring and Mass Estimation using Structure from Motion
复制标题
DOI：
10.1109/icra48891.2023.10161045
复制
发表时间：
2022-09
期刊：
影响因子：
--
通讯作者：
Gerry Chen;Venkata Harsh Suhith Muriki;Cédric Pradalier;Yongsheng Chen;F. Dellaert
中科院分区：
文献类型：
--
作者：
Gerry Chen;Venkata Harsh Suhith Muriki;Cédric Pradalier;Yongsheng Chen;F. Dellaert
我们提出了一种新的混合电缆为基础的机器人与机械手和摄像头的高精度，中等吞吐量的植物监测在垂直水培农场，并作为一个应用程序的例子，展示了非破坏性的植物质量估计。具有高时空分辨率的植物监测对于农民和研究人员检测异常和开发植物生长预测模型都很重要。高质量、现成的运动恢复结构（SfM）和摄影测量软件包的可用性使一个充满活力的机器人专家社区能够将计算机视觉应用于非破坏性工厂监测。虽然现有的方法往往集中在高吞吐量（例如，卫星，无人机（UAV），车载，走廊带图像）或高精度/鲁棒性闭塞（例如，转台扫描仪或机器人手臂），我们提出了一个中间地带，实现高精度与中等吞吐量，高度自动化的机器人。我们的设计对电缆驱动的并联机器人（CDPR）的工作空间的可扩展性与4自由度（DoF）的机器人手臂的灵活性，从各种角度自主成像许多植物。我们描述了我们的机器人设计，并通过每天收集54种植物的照片，从64个角度进行实验。我们表明，我们的方法可以产生科学上有用的测量，在初始校准后完全自主操作，并产生更好的重建和植物属性估计比那些在冠层的方法（例如无人机）。作为示例应用程序，我们表明，我们的系统可以成功地估计植物质量的平均绝对误差（MAE）为0.586克，当用于进行假设检验的质量和年龄之间的关系，产生的p值与地面实况数据（p=0.0020和p=0.0016，分别）。
We propose a novel hybrid cable-based robot with manipulator and camera for high-accuracy, medium-throughput plant monitoring in a vertical hydroponic farm and, as an example application, demonstrate non-destructive plant mass estimation. Plant monitoring with high temporal and spatial resolution is important to both farmers and researchers to detect anomalies and develop predictive models for plant growth. The availability of high-quality, off-the-shelf structure-from-motion (SfM) and photogrammetry packages has enabled a vibrant community of roboticists to apply computer vision for non-destructive plant monitoring. While existing approaches tend to focus on either high-throughput (e.g. satellite, unmanned aerial vehicle (UAV), vehicle-mounted, conveyor-belt imagery) or high-accuracy/robustness to occlusions (e.g. turn-table scanner or robot arm), we propose a middle-ground that achieves high accuracy with a medium-throughput, highly automated robot. Our design pairs the workspace scalability of a cable-driven parallel robot (CDPR) with the dexterity of a 4 degree-of-freedom (DoF) robot arm to autonomously image many plants from a variety of viewpoints. We describe our robot design and demonstrate it experimentally by collecting daily photographs of 54 plants from 64 viewpoints each. We show that our approach can produce scientifically useful measurements, operate fully autonomously after initial calibration, and produce better reconstructions and plant property estimates than those of over-canopy methods (e.g. UAV). As example applications, we show that our system can successfully estimate plant mass with a Mean Absolute Error (MAE) of 0.586g and, when used to perform hypothesis testing on the relationship between mass and age, produces p-values comparable to ground-truth data (p=0.0020 and p=0.0016, respectively).