Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Motion-Coupled Mapping Algorithm for Hybrid Rice Canopy

Huaiqu Feng, Guoyang Zhao, Cheng Liu, Yongwei Wang, Jun Wang

TL;DR

The paper tackles the challenge of accurately mapping hybrid rice canopy contours for Agricultural UGVs operating in complex fields. It introduces a motion-coupled mapping algorithm that fuses real-time RGB-D data with kinematic and inertial measurements to produce grid-based, probabilistic canopy elevation maps with contour estimates. Key contributions include a robust RGB-D vSLAM pipeline with noise mitigation, a multi-frame coordinate fusion framework, a probabilistic height update via Kalman fusion, and a localization-enhanced canopy map that supports autonomous operations like impurity removal. The approach is implemented on a ROS-Jetson platform and validated in outdoor paddies, demonstrating improved mapping accuracy and operational reliability for autonomous agricultural tasks.

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.

Motion-Coupled Mapping Algorithm for Hybrid Rice Canopy

TL;DR

The paper tackles the challenge of accurately mapping hybrid rice canopy contours for Agricultural UGVs operating in complex fields. It introduces a motion-coupled mapping algorithm that fuses real-time RGB-D data with kinematic and inertial measurements to produce grid-based, probabilistic canopy elevation maps with contour estimates. Key contributions include a robust RGB-D vSLAM pipeline with noise mitigation, a multi-frame coordinate fusion framework, a probabilistic height update via Kalman fusion, and a localization-enhanced canopy map that supports autonomous operations like impurity removal. The approach is implemented on a ROS-Jetson platform and validated in outdoor paddies, demonstrating improved mapping accuracy and operational reliability for autonomous agricultural tasks.

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.

Paper Structure

This paper contains 11 sections, 5 equations, 6 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methodology
  3. Data Acquisition
  4. Overall Pipeline
  5. Coordinates Fusion
  6. Map Update from Range Measurements
  7. EXPERIMENTS
  8. Implementation
  9. Mapping Results in Complex Environment
  10. Canopy Contour Map and Path
  11. Conclusion

Figures (6)

  • Figure 1: Robot mapping in hybrid rice field. We set up three different depth camera perspectives and use edge device for real-time computation.
  • Figure 2: Experimental scenario for data acquisition.
  • Figure 3: Pipeline of hybrid rice canopy mapping.
  • Figure 4: Multiple coordinate fusion during robot motion.
  • Figure 5: Canopy mapping in hybrid rice field.
  • ...and 1 more figures