Abstract
To address the insufficient accuracy of traditional single-sensor navigation methods in dense planting environments of pomegranate orchards, this paper proposes a vision and LiDAR fusion-based navigation line extraction method for orchard environments. The proposed method integrates a YOLOv8-ResCBAM trunk detection model, a reverse ray projection fusion algorithm, and geometric constraint-based navigation line fitting techniques. The object detection model enables high-precision real-time detection of pomegranate tree trunks. A reverse ray projection algorithm is proposed to convert pixel coordinates from visual detection into three-dimensional rays and compute their intersections with LiDAR scanning planes, achieving effective association between visual and LiDAR data. Finally, geometric constraints are introduced to improve the RANSAC algorithm for navigation line fitting, combined with Kalman filtering techniques to reduce navigation line fluctuations. Field experiments demonstrate that the proposed fusion-based navigation method improves navigation accuracy over single-sensor methods and semantic-segmentation methods, reducing the average lateral error to 5.2 cm, yielding an average lateral error RMS of 6.6 cm, and achieving a navigation success rate of 95.4%. These results validate the effectiveness of the vision and 2D LiDAR fusion-based approach in complex orchard environments and provide a viable route toward autonomous navigation for orchard robots.