Robots in tomato greenhouses need to perceive the plant and plant parts accurately to automate monitoring, harvesting, and de-leafing tasks. Existing perception systems struggle with the high levels of occlusion in plants and often result in poor perception accuracy. One reason for this is because they use fixed cameras or predefined camera movements. Next-best-view (NBV) planning presents a alternate approach, in which the camera viewpoints are reasoned and strategically planned such that the perception accuracy is improved. However, existing NBV-planning algorithms are agnostic to the task-at-hand and give equal importance to all the plant parts. This strategy is inefficient for greenhouse tasks that require targeted perception of specific plant parts, such as the perception of leaf nodes for de-leafing. To improve targeted perception in complex greenhouse environments, NBV planning algorithms need an attention mechanism to focus on the task-relevant plant parts. In this paper, we investigated the role of attention in improving targeted perception using an attention-driven NBV planning strategy. Through simulation experiments using plants with high levels of occlusion and structural complexity, we showed that focusing attention on task-relevant plant parts can significantly improve the speed and accuracy of 3D reconstruction. Further, with real-world experiments, we showed that these benefits extend to complex greenhouse conditions with natural variation and occlusion, natural illumination, sensor noise, and uncertainty in camera poses. Our results clearly indicate that using attention-driven NBV planning in greenhouses can significantly improve the efficiency of perception and enhance the performance of robotic systems in greenhouse crop production.

翻译：番茄温室中的机器人需要精确感知植物及其部位，以实现监测、收获和去叶任务的自动化。现有感知系统难以应对植物中的严重遮挡问题，常导致感知精度低下。原因之一是它们采用固定摄像头或预设的摄像头运动轨迹。下一最佳视角（NBV）规划提供了一种替代方法，通过推理和策略性地规划摄像头视角来提高感知精度。然而，现有NBV规划算法对具体任务不敏感，对所有植物部位赋予同等重要性。这种策略对于温室中需要定向感知特定植物部位（如用于去叶的叶节点）的任务而言效率低下。为提升复杂温室环境中的定向感知能力，NBV规划算法需要一种注意力机制来聚焦于任务相关的植物部位。本文研究了注意力在通过面向注意力驱动的NBV规划策略改善定向感知中的作用。通过使用具有高度遮挡和结构复杂性的植物模型进行仿真实验，我们证明将注意力聚焦于任务相关植物部位可显著提升三维重建的速度和精度。此外，通过真实世界实验，我们表明这些优势可推广至具有自然变异与遮挡、自然光照、传感器噪声以及相机位姿不确定性的复杂温室条件。结果明确表明，在温室中采用面向注意力驱动的NBV规划能显著提高感知效率，并增强机器人系统在温室作物生产中的性能。