In this study, a comprehensive overview of the available autonomous ground platforms developed by universities and research groups that were specifically designed to handle agricultural tasks was performed. As cost reduction and safety improvements are two of the most critical aspects for farmers, the development of autonomous vehicles can be of major interest, especially for those applications that are lacking in terms of mechanization improvements. This review aimed to provide a literature evaluation of present and historical research contributions toward designing and prototyping agricultural ground unmanned vehicles. The review was motivated by the intent to disseminate to the scientific community the main features of the autonomous tractor named BOPS-1960, which was conceived in the 1960s at the Alma Mater Studiorum University of Bologna (UNIBO). Jointly, the main characteristics of the modern DEDALO unmanned ground vehicle (UGV) for orchard and vineyard operations that was designed recently were evaluated. The basic principles, technology and sensors used in the two UNIBO prototypes are described in detail, together with an analysis of UGVs for agriculture conceived in recent years by research centers all around the world.

Fruit size is crucial for growers as it influences consumer willingness to buy and the price of the fruit. Fruit size and growth along the seasons are two parameters that can lead to more precise orchard management favoring production sustainability. In this study, a Python-based computer vision system (CVS) for sizing apples directly on the tree was developed to ease fruit sizing tasks. The system is made of a consumer-grade depth camera and was tested at two distances among 17 timings throughout the season, in a Fuji apple orchard. The CVS exploited a specifically trained YOLOv5 detection algorithm, a circle detection algorithm, and a trigonometric approach based on depth information to size the fruits. Comparisons with standard-trained YOLOv5 models and with spherical objects were carried out. The algorithm showed good fruit detection and circle detection performance, with a sizing rate of 92%. Good correlations (r > 0.8) between estimated and actual fruit size were found. The sizing performance showed an overall mean error (mE) and RMSE of + 5.7 mm (9%) and 10 mm (15%). The best results of mE were always found at 1.0 m, compared to 1.5 m. Key factors for the presented methodology were: the fruit detectors customization; the HoughCircle parameters adaptability to object size, camera distance, and color; and the issue of field natural illumination. The study also highlighted the uncertainty of human operators in the reference data collection (5–6%) and the effect of random subsampling on the statistical analysis of fruit size estimation. Despite the high error values, the CVS shows potential for fruit sizing at the orchard scale. Future research will focus on improving and testing the CVS on a large scale, as well as investigating other image analysis methods and the ability to estimate fruit growth.

Precision agriculture is a reality in agriculture and is playing a key role as the industry comes to terms with the environment, market forces, quality requirements, traceability, vehicle guidance ...

Understanding the complex interplay between environmental factors and fruit quality development requires sophisticated analytical approaches linking cellular architecture to environmental conditions. This study introduces a novel application of dual-resolution X-ray computed tomography (CT) for the non-destructive characterization of apple internal tissue architecture in relation to fruit growth, thereby advancing beyond traditional methods that are primarily focused on postharvest analysis. By extracting detailed three-dimensional structural parameters, we reveal tissue porosity and heterogeneity influenced by crop load, maturity timing and canopy position, offering insights into internal quality attributes. Employing correlation analysis, Principal Component Analysis, Canonical Correlation Analysis, and Structural Equation Modeling, we identify temperature as the primary environmental driver, particularly during early developmental stages (45 Days After Full Bloom, DAFB), and uncover nonlinear, hierarchical effects of preharvest environmental factors such as vapor pressure deficit, relative humidity, and light on quality traits. Machine learning models (Multiple Linear Regression, Random Forest, XGBoost) achieve high predictive accuracy (R² > 0.99 for Multiple Linear Regression), with temperature as the key predictor. These baseline results represent findings from a single growing season and require validation across multiple seasons and cultivars before operational application. Temporal analysis highlights the importance of early-stage environmental conditions. Integrating structural and environmental data through innovative visualization tools, such as anatomy-based radar charts, facilitates comprehensive interpretation of complex interactions. This multidisciplinary framework enhances predictive precision and provides a baseline methodology to support precision orchard management under typical agricultural variability.

Accurate in-field non-destructive fruit sizing is a fundamental requirement for yield estimation and harvest logistics, yet it remains challenging due to complex fruit morphology and real-time processing constraints. This study investigates the allometric relationships of Fuji (cv. FujiKO) apples and their impact on computer vision performance. Morphological analysis reveals that fruits are generally wider than they are tall, with fruit height and minimum equatorial diameter acting as the primary sources of size underestimation. The results identify an intrinsic morphological uncertainty—or "geometric noise"—ranging from 8.8% to 10.5% of the reference equatorial diameter, below which further sizing precision is limited by fruit geometry rather than sensor/algorithm accuracy. To address this issue, a Mean Thresholded Absolute Error (MTAE) is proposed as an evaluation metric that accounts for fruit geometric variability when assessing remote fruit sizing computer vision algorithms.Evaluation of three algorithm versions demonstrates that, while image resizing and local entropy improve visual fruit fitting, they impose significant computational overhead. An optimized pipeline achieves a processing speed of 1.0 ± 0.7 ms per fruit detected on the CPU, enabling a near-real-time analysis of up to 63 fruits per frame. Despite intrinsic geometric variability, all algorithms achieve an MTAE below 0.5 mm, confirming that a high-throughput, statistically representative sampling approach is more advantageous than pursuing sub-millimeter precision on individual, randomly oriented fruits.

Accurate in-field non-destructive fruit sizing is a fundamental requirement for yield estimation and harvest logistics, yet it remains challenging due to complex fruit morphology and real-time processing constraints. This study investigates the allometric relationships of Fuji (cv. FujiKO) apples and their impact on computer vision performance. Morphological analysis reveals that fruits are generally wider than they are tall, with fruit height and minimum equatorial diameter acting as the primary sources of size underestimation. The results identify an intrinsic morphological uncertainty—or "geometric noise"—ranging from 8.8% to 10.5% of the reference equatorial diameter, below which further sizing precision is limited by fruit geometry rather than sensor/algorithm accuracy. To address this issue, a Mean Thresholded Absolute Error (MTAE) is proposed as an evaluation metric that accounts for fruit geometric variability when assessing remote fruit sizing computer vision algorithms.Evaluation of three algorithm versions demonstrates that, while image resizing and local entropy improve visual fruit fitting, they impose significant computational overhead. An optimized pipeline achieves a processing speed of 1.0 ± 0.7 ms per fruit detected on the CPU, enabling a near-real-time analysis of up to 63 fruits per frame. Despite intrinsic geometric variability, all algorithms achieve an MTAE below 0.5 mm, confirming that a high-throughput, statistically representative sampling approach is more advantageous than pursuing sub-millimeter precision on individual, randomly oriented fruits.