Abstract
This paper presents a motion-coupled mapping algorithm for contour mapping of hybrid rice canopies, specifically designed for Agricultural Unmanned Ground Vehicles (Agri-UGV) navigating complex and unknown rice fields. Precise canopy mapping is essential for Agri-UGVs to plan efficient routes and avoid protected zones. The motion control of Agri-UGVs, tasked with impurity removal and other operations, depends heavily on accurate estimation of rice canopy height and structure. To achieve this, the proposed algorithm integrates real-time RGB-D sensor data with kinematic and inertial measurements, enabling efficient mapping and proprioceptive localization. The algorithm produces grid-based elevation maps that reflect the probabilistic distribution of canopy contours, accounting for motion-induced uncertainties. It is implemented on a high-clearance Agri-UGV platform and tested in various environments, including both controlled and dynamic rice field settings. This approach significantly enhances the mapping accuracy and operational reliability of Agri-UGVs, contributing to more efficient autonomous agricultural operations.
Abstract (translated)
本文提出了一种针对杂交水稻冠层轮廓绘制的运动耦合映射算法，专门设计用于在复杂且未知的稻田中导航的农业无人地面车辆（Agri-UGV）。精确的冠层地图对于Agri-UGVs规划高效路线和避开保护区至关重要。负责清除杂质和其他操作的Agri-UGVs的运动控制严重依赖于准确估计水稻冠层高度和结构的能力。为了实现这一目标，所提出的算法将实时RGB-D传感器数据与运动学和惯性测量相结合，从而能够进行高效的映射并实现自我定位。该算法生成基于网格的高度地图，反映了冠层轮廓的概率分布，并考虑了由运动引起的不确定性。此算法已在高通过性的Agri-UGV平台上实施，并在各种环境（包括受控和动态稻田设置）中进行了测试。这种方法显著提高了Agri-UGVs的映射精度和操作可靠性，有助于实现更高效的自主农业作业。
URL
https://arxiv.org/abs/2502.16134
