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.

Organic farming systems are considered not compatible with conservation tillage mainly because of the reliance of conservative systems on herbicides. In this three-year field experiment, we tested the performances of an innovative vegetable organic and conservative system (ORG+) combining the use of cover crops (exploited as either living or dead mulch) and no-till techniques. This system was compared to “business-as-usual” organic farming (ORG) and integrated farming system (INT) based on the same crop sequence: savoy cabbage (Brassica oleracea var. sabauda L. cv. Famosa), spring lettuce (Lactuca sativa L. cv. Justine), fennel (Foeniculum vulgare Mill. Cv. Montebianco), and summer lettuce (Lactuca sativa L. cv. Ballerina RZ). The results of crop yield parameters and weed abundance contribute to spotlight potentialities and weaknesses of organic-conservative management of field vegetables. In particular, ORG+ caused significant yield depletion for all the crops and revealed suboptimal weed control and N availability. The agroecosystem services provided by the cover crops grown in the ORG+ as dead mulch or living mulch were affected by weather conditions and not always resulted in significant crop gain. Nevertheless, interesting results in terms of P availability and reduced N surplus encourage further development of the system targeting more sustainable organic vegetable production.

Vegetable transplanting is an important and advantageous practice in vegetables production systems. In recent years, the development of vegetable transplanting tools has increased, as well as the interest for automatic and robotic transplanters. However, at present, the feeding of transplanting machines is often still performed by hand. This paper presents the design, development and testing of a needle gripper and a two-finger gripper for vegetable transplanting. Both grippers were self-designed and tested for picking, lifting and transplanting plug seedlings. Tests have been conducted on fennel (Foeniculum vulgare L.), leek (Allium ampeloprasum L.) chicory (Cichorium intybus L.) and lettuce (Lactuca sativa L.) seedlings to determine the impact that gripper typology might have on the further growth of plants after transplanting. The average success rate of the two-finger gripper in the transplanting experiment was 95% and of the needle gripper 81.75%, respectively. Although neither gripper typology affected the growth of the seedlings after transplanting, several design implications were identified in order to improve the performance of both grippers. Furthermore, the two-finger gripper is more reliable for lettuce and chicory, while the needle gripper requires root plugs with higher firmness and cohesion to prevent shattering.

Organic vegetable production is particularly affected by weed pressure and mechanical weeding is the major tactic implemented by growers to keep weeds under economic thresholds. Living mulch (LM) has been shown to provide several environmental services; however, LM management is required to avoid competition between service crops and cash crops. The aim of this trial was to evaluate two innovative LM-based management systems: a system that provided LM growth regulation by means of flaming (LM-FL) and a system where the LM was regularly mowed by an autonomous mower (LM-AM), both compared with a control without LM and based on standard tillage operations (TILL). The three management systems were evaluated in terms of crop production, weed control, and energy consumption on a 2 yr organic crop rotation of cauliflower (Brassica oleracea L. var botrytis) and eggplant (Solanum melongena L.). LM-AM produced an acceptable fresh marketable yield for both vegetable crops. Moreover, the weed dry biomass obtained in LM-AM-managed plots was lower compared to the LM-FL plots and ranged approximately from 200 to 300 kg ha⁻¹. Furthermore, LM-AM management resulted in lower energy consumption (−2330 kWh ha⁻¹ with respect to the TILL system and −7225 kWh ha⁻¹ with respect to the LM-FL system). The results of this trial suggest that autonomous mowers have a great potential to improve LM management and help with implementing sustainable organic vegetable systems.

Synthetic herbicides are commonly used in weed management, however, 70 years of use has led to weed resistance and environmental concerns. These problems have led scientists to consider alternative methods of weed management in order to reduce the inputs and impacts of synthetic herbicides. The aim of this experiment was to test the level of weed control using four weeding methods: glyphosate applied at an ultra-low volume, the organic herbicide nonanoic acid, flaming, and hot foam. The results showed that weed control was effective only when flaming and hot foam were applied (99% and 100% weed control, respectively). Nonanoic acid at a dose of 11 kg a.i. ha⁻¹ diluted in 400 L of water did not control developed plants of Cyperus esculentus (L.), Convolvulus arvensis (L.) and Poa annua (L.). Glyphosate at a dose of 1080 g a.i. ha⁻¹ (pure product) only controlled P. annua (L.), but had no effect on C. esculentus (L.) and C. arvensis (L.). After the aboveground tissues of weeds had died, regrowth began earlier after flaming compared to hot foam. There was no regrowth of P. annua (L.) only after using hot foam and glyphosate. Hot foam was generally better at damaging the meristems of the weeds. In one of the two experiment sites, significantly more time was needed after the hot foam to recover 10% and 50% of the ground compared to flaming. The time needed to recover 90% of the ground was on average 26–27 days for flaming and hot foam, which is the time that is assumed to be required before repeating the application. A total of 29 days after the treatments, weeds were smaller after flaming, glyphosate and hot foam compared to nonanoic acid and the control, where they had more time to grow.