28 July 2025 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Autonomous mobile robotic solutions are increasingly being explored in precision agriculture to aid human workers in labour-intensive or repetitive tasks. Moreover, the emergence of foundation models in vision-based AI domain presents an opportunity to perform automated interpretation of in-field collected data. This study presents a cost-effective mobile robotic research platform designed for autonomous vineyard inspection: it integrates mission planning, real-world navigation and a post-processing pipeline of multimodal data. The system, based on the Leo rover, is equipped with LiDAR, RGB cameras and GNSS-visual-inertial positioning, ensuring reliable operation in GNSS-degraded vineyard environments. We propose a novel methodology for automating several stages of the workflow using various open and in-situ collected data. The robotic platform and processing pipeline were validated through simulation and field experiments, demonstrating its capability for autonomous navigation, 3D reconstruction, AI-based fruit detection and an initial plant health assessment through Large Multimodal Models (LMM). Results show that while 3D mapping provides highresolution spatial data, AI-driven object detection and vision models require further domain adaptation for reaching reliable and trustable operation. The study highlights the feasibility of cost-effective mobile robotic solutions in vineyard monitoring and the potential of integrating AI to enhance agricultural automation.
5 November 2025 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Accurate and robust odometry is critical for mobile mapping and autonomous navigation, particularly in complex environments where single-sensor approaches struggle. While LiDAR and visual odometry each provide valuable motion estimation, they are susceptible to failures in conditions unfavorable for the specific odometry type. Fusing multiple modalities enhances robustness, yet effective integration remains challenging due to differences in heterogenous sensor data representation. This study presents STELVIO, a flexible factor graph-based framework for Stereo LiDAR-Visual-Inertial Odometry. By combining LiDAR-inertial odometry with stereo visual odometry, STELVIO improves trajectory estimation by leveraging the strengths of each modality. The system introduces adaptive fusion strategies, ranging from loose, odometry-only pose graph coupling to an extensive factor graph approach, utilizing visual features and LiDAR-derived range factors. This modular structure allows for balancing computational efficiency with robustness, making it suitable for real-time applications and accuracy-oriented mapping applications. Evaluation is conducted using an in-house mobile mapping system in a challenging indoor environment. Initial results highlight the effectiveness of the fusion approach in reducing drift and improving localization consistency compared to single-sensor methods. The findings demonstrate the potential of multi-sensor integration for robust and scalable mobile mapping solutions.