Feeding the growing global population requires an annual increase in food production. This requirement suggests an increase in the use of pesticides, which represents an unsustainable chemical load for the environment. To reduce pesticide input and preserve the environment while maintaining the necessary level of food production, the efficiency of relevant processes must be drastically improved. Within this context, this research strived to design, develop, test and assess a new generation of automatic and robotic systems for effective weed and pest control aimed at diminishing the use of agricultural chemical inputs, increasing crop quality and improving the health and safety of production operators. To achieve this overall objective, a fleet of heterogeneous ground and aerial robots was developed and equipped with innovative sensors, enhanced end-effectors and improved decision control algorithms to cover a large variety of agricultural situations. This article describes the scientific and technical objectives, challenges and outcomes achieved in three common crops.

Intra-row weed control in organic or low-input cropping systems is more difficult than in conventional agriculture. The various mechanical and thermal devices available for intra-row weed control are reported in this review. Low-tech mechanical devices such as cultivators, finger-weeders, brush weeders, and torsionweeders tend to be used in low density crops, while spring-tine harrows are mainly applied in narrow-row high-density crops. Flame weeding can be used for both narrow and wide-row sown crops, provided that the crop is heat-tolerant. Robotic weeders are the most recent addition to agricultural engineering, and only a few are available on the market. Nowadays, robotic weeders are not yet used in small and medium sized farms. In Europe, highincome niche crops are often cultivated in small farms and farmers cannot invest in high-tech solutions. Irrespectively of the choice of low- or high-tech machines, there are several weeders that can be used to reduce the use of herbicides, making of them a judicious use, or decide to avoid them.

The advancement of computer vision technology has allowed for the easy detection of weeds and other stressors in turfgrasses and agriculture. This study aimed to evaluate the feasibility of single shot object detectors for weed detection in lawns, which represents a difficult task. In this study, four different YOLO (You Only Look Once) object detectors version, along with all their various scales, were trained on a public ‘Weeds’ dataset with 4203 digital images of weeds growing in lawns with a total of 11,385 annotations and tested for weed detection in turfgrasses. Different weed species were considered as one class (‘Weeds’). Trained models were tested on the test subset of the ‘Weeds’ dataset and three additional test datasets. Precision (P), recall (R), and mean average precision (mAP_0.5 and mAP_0.5:0.95) were used to evaluate the different model scales. YOLOv8l obtained the overall highest performance in the ‘Weeds’ test subset resulting in a P (0.9476), mAP_0.5 (0.9795), and mAP_0.5:0.95 (0.8123), while best R was obtained from YOLOv5m (0.9663). Despite YOLOv8l high performances, the outcomes obtained on the additional test datasets have underscored the necessity for further enhancements to address the challenges impeding accurate weed detection.

Climate change and labour shortage are re-shaping farming methods. Agricultural tasks are often hard, tedious and repetitive for operators, and farms struggle to find specialized operators for such works. For this and other reasons (i.e., the increasing costs of agricultural labour) more and more farmers have decided to switch to autonomous (or semi-autonomous) field robots. In the past decade, an increasing number of robots has filled the market of agricultural machines all over the world. These machines can easily cover long and repetitive tasks, while operators can be employed in other jobs inside the farms. This paper reviews the current state-of-the-art of autonomous robots for agricultural operations, dividing them into categories based on main tasks, to analyze their main characteristics and their fields of applications. Seven main tasks were identified: multi-purpose, harvesting, mechanical weeding, pest control and chemical weeding, scouting and monitoring, transplanting and tilling-sowing. Field robots were divided into these categories, and different characteristics were analyzed, such as engine type, traction system, application field, safety sensors, navigation system, country of provenience and presence on the market. The aim of this review is to provide a global view on agricultural platforms developed in the past decade, analyzing their characteristics and providing future perspectives for next robotic platforms. The analysis conducted on 59 field robots, those already available on the market and not, revealed that one fifth of the platforms comes from Asia, and 63% of all of them are powered by electricity (rechargeable batteries, not solar powered) and that numerous platforms base their navigation system on RTK-GPS signal, 28 out of 59, and safety on LiDAR sensor (12 out of 59). This review considered machines of different size, highlighting different possible choices for field operations and tasks. It is difficult to predict market trends as several possibilities exist, like fleets of small robots or bigger size platforms. Future research and policies should focus on improving navigation and safety systems, reducing emissions and improving level of autonomy of robotic platforms.

Agriculture and Forestry are two broad and promising areas demanding technological solutions with the aim of increasing production or accurate inventories for sustainability while the environmental impact is minimized by reducing the application of agro-chemicals and increasing the use of environmental friendly agronomical practices. In addition, the immediate consequence of this “trend” is the reduction of production costs.