Optimizing Autonomous UAV Navigation with D* Algorithm for Sustainable Development

Sustainability, Journal Year: 2024, Volume and Issue: 16(17), P. 7867 - 7867

Published: Sept. 9, 2024

Autonomous navigation for Unmanned Aerial Vehicles (UAVs) has emerged as a critical enabler in various industries, from agriculture, delivery services, and surveillance to search rescue operations. However, navigating UAVs dynamic unknown environments remains formidable challenge. This paper explores the application of D* algorithm, prominent path-planning method rooted artificial intelligence widely used robotics, alongside comparisons with other algorithms, such A* RRT*, augment autonomous capabilities UAVs’ implication sustainability development. The core problem addressed herein revolves around enhancing UAV efficiency, safety, adaptability environments. research methodology involves integration algorithm into system, enabling real-time adjustments path planning that account obstacles evolving terrain conditions. experimentation phase unfolds simulated designed mimic real-world scenarios challenges. Comprehensive data collection, rigorous analysis, performance evaluations paint vivid picture algorithm’s efficacy comparison methods, RRT*. Key findings indicate offers compelling solution, providing efficient, safe, adaptable capabilities. results demonstrate efficiency improvement 92%, 5% reduction collision rates, an increase safety margins by 2.3 m. article addresses certain challenges contributes demonstrating practical effectiveness advancing aerial systems. Specifically, this study provides insights strengths limitations each offering valuable guidance researchers practitioners selecting most suitable approach their applications. implications extend far wide, potential applications industries surveillance, disaster response, more sustainability.

Language: Английский

---

Combining a Standardized Growth Class Assessment, UAV Sensor Data, GIS Processing, and Machine Learning Classification to Derive a Correlation with the Vigour and Canopy Volume of Grapevines

Sensors, Journal Year: 2025, Volume and Issue: 25(2), P. 431 - 431

Published: Jan. 13, 2025

Assessing vines’ vigour is essential for vineyard management and automatization of viticulture machines, including shaking adjustments berry harvesters during grape harvest or leaf pruning applications. To address these problems, based on a standardized growth class assessment, labeled ground truth data precisely located grapevines were predicted with specifically selected Machine Learning (ML) classifiers (Random Forest Classifier (RFC), Support Vector Machines (SVM)), utilizing multispectral UAV (Unmanned Aerial Vehicle) sensor data. The input features ML model training comprise spectral, structural, texture feature types generated from orthomosaics (spectral features), Digital Terrain Surface Models (DTM/DSM- structural Gray-Level Co-occurrence Matrix (GLCM) calculations (texture features). specific extensive literature research, especially the fields precision agri- viticulture. integrate only vine canopy-exclusive into classifications, different extracted spatially aggregated (zonal statistics), combined pixel- object-based image-segmentation-technique-created row mask around each single grapevine position. canopy progressively grouped seven groups training. Model overall performance metrics optimized grid search-based hyperparameter tuning repeated-k-fold-cross-validation. Finally, ML-based prediction results extensively discussed evaluated (accuracy, f1-weighted) specific- classification user- producer accuracy).

Language: Английский

---

Automatic Grape Cluster Detection Combining YOLO Model and Remote Sensing Imagery

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(2), P. 243 - 243

Published: Jan. 11, 2025

Precision agriculture has recently experienced significant advancements through the use of technologies such as unmanned aerial vehicles (UAVs) and satellite imagery, enabling more efficient precise agricultural management. Yield estimation from these is essential for optimizing resource allocation, improving harvest logistics, supporting decision-making sustainable vineyard This study aimed to evaluate grape cluster numbers estimated by using YOLOv7x in combination with images obtained UAVs a vineyard. Additionally, capability several vegetation indices calculated Sentinel-2 PlanetScope satellites estimate clusters was evaluated. The results showed that application model RGB acquired able accurately predict (R2 value RMSE 0.64 0.78 vine−1). On contrary, indexes derived were found not lower than 0.23), probably due fact are related vigor, which always yield parameters (e.g., number). suggests high-resolution UAV images, multispectral advanced detection models like can significantly improve accuracy management, resulting agriculture.

Language: Английский

---

Field heterogeneity of soil texture controls leaf water potential spatial distribution predicted from UAS-based vegetation indices in non-irrigated vineyards

Biogeosciences, Journal Year: 2025, Volume and Issue: 22(2), P. 513 - 534

Published: Jan. 29, 2025

Abstract. Grapevine water status exhibits substantial variability even within a single vineyard. Understanding how edaphic, topographic, and climatic conditions impact grapevine heterogeneity at the field scale, in non-irrigated vineyards, is essential for winemakers as it significantly influences wine quality. This study aimed to quantify spatial distribution of leaf potential (Ψleaf) vineyards assess influence soil property heterogeneity, topography, on intra-field two during viticultural seasons. By combining multilinear vegetation indices from very-high-spatial-resolution multispectral, thermal, lidar imageries collected with uncrewed aerial systems (UASs), we efficiently robustly captured Ψleaf across both different dates. Our results demonstrated that was mainly governed by within-vineyard hydraulic conductivity (R2 up 0.81) particularly marked when evaporative demand deficit increased, since range greater, 0.73 MPa, these conditions. However, topographic attributes (elevation slope) were less related variability. These findings show within-field are primary factors governing observed their effects concomitant.

Language: Английский

---

Application of LiDAR and SLAM Technologies in Autonomous Systems for Precision Grapevine Pruning and Harvesting

SHS Web of Conferences, Journal Year: 2025, Volume and Issue: 216, P. 01064 - 01064

Published: Jan. 1, 2025

Integrating autonomous systems into precision agriculture brings new integrated management in vineyards for operational efficiency and accuracy. This project creates an system grapevine pruning harvesting using LiDAR, SLAM, RGB-D cameras, Convolutional Neural Networks (CNNs), proximity sensors, Wireless Sensor (WSNs). LiDAR produces detailed 3D vineyard maps that integrate with SLAM algorithms accurate navigation, ensuring efficient local global information relay. cameras capture visual depth of grapevines fruits, while CNNs process this data to classify different vines grapes, enabling focused decisions. Proximity sensors provide real-time distance measurement safe operation, allowing obstacle navigation without damaging equipment or vines. WSNs facilitate communication between components through exchange, continuous environmental monitoring adjustments maximize performance. The aims advanced technologies optimize these processes. improves accuracy speed, reducing labor costs enhancing grape yield quality, representing a promising approach management. generates provides localization better than 2 cm. identify fruits 95% ensure avoidance 98%> accuracy, less 50ms latency. has increased by 15% decreased operating 20%o.

Language: Английский

---

Combination of Remote Sensing and Artificial Intelligence in Fruit Growing: Progress, Challenges, and Potential Applications

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(24), P. 4805 - 4805

Published: Dec. 23, 2024

Fruit growing is important in the global agricultural economy, contributing significantly to food security, job creation, and rural development. With advancement of technologies, mapping fruits using remote sensing machine learning (ML) deep (DL) techniques has become an essential tool optimize production, monitor crop health, predict harvests with greater accuracy. This study was developed four main stages. In first stage, a comprehensive review existing literature made from July 2018 (first article found) June 2024, totaling 117 articles. second general analysis data obtained made, such as identification most studied interest. third more in-depth focusing on apples grapes, 27 30 articles, respectively. The included use (orbital proximal) imagery ML/DL algorithms map areas, detect diseases, development, among other analyses. fourth stage shows data’s potential application Southern Brazilian region, known for apple grape production. demonstrates how integration modern technologies can transform fruit farming, promoting sustainable efficient agriculture through artificial intelligence technologies.

Language: Английский

---

Characterisation of Two Vineyards in Mexico Based on Sentinel-2 and Meteorological Data

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(14), P. 2538 - 2538

Published: July 10, 2024

In Mexico, viticulture represents the second source of employment in agricultural area after fruit and vegetable sector. developed countries, remote sensing is widely used for vineyard monitoring; however, this tool barely developing countries Iberoamerica. research, our overall objective to characterise two vineyards state Queretaro (Mexico) using Sentinel-2 meteorological data, specifically spectral thermal indices. Results show that indices obtained from bands have adequately characterised phenological dynamics different varieties vineyards. The Modified Soil-Adjusted Vegetation Index (MSAVI) was discriminate between first stages vineyards, while Normalized Difference (NDVI) useful monitoring during rest Thermal shown best grape are those can adapt both cooler warmer temperatures, a reasonable ripening period, produce wines with balanced acidity flavours. conclusion, combination (including indices) data (NDVI MSAVI) provide information choosing suitable variety region.

Language: Английский

---