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.

Robotic mowing equipment has rapidly increased in availability worldwide, but the first developed concepts for automating the mowing process are nearly 100 years old. The first attempt to commercialize a robotic mower was in the 1950s, with continued attempts to launch commercial products over subsequent decades. The two factors that most limited the evolution of robotic mowers over time were positioning (precise localization in space) and sensing (identification of objects surrounding the working robot). In the United States until 2023, technology was largely limited to wire‐bound random movement robotic mowers. In 2023, global positioning system–real‐time kinematic (GPS‐RTK)‐based positioning was launched in the United States, which was launched months earlier in Europe, allowing for precise positioning of robots and systematic movement within a work area, which increased efficiency. The addition of computer vision‐based or light detection and ranging positioning and sensing that is currently being launched by new companies in 2024 will allow for simultaneous positioning and sensing, referred to as simultaneous localization and mapping (SLAM). The near future of positioning and sensing will likely be a combination of GPS‐RTK merged with vision‐based SLAM to improve accuracy when GPS‐RTK signal is limited.

Autonomous mowers’ navigation pattern plays a crucial role in turfgrass quality, influencing both esthetic and functional performance. However, despite extensive research on mowing efficiency, the effects of different navigation patterns on turfgrass damage and visual quality remain inadequately investigated. This study aimed to evaluate the impact of three different autonomous mower navigation patterns (random, vertical, and chessboard) on operational performance and the effect of trampling activity on turfgrass. Each pattern was tested in terms of data on the number of passages, distance traveled (m), number of intersections and the percentage of area mowed using a remote sensing system and an updated custom-built software. Green coverage percentage was assessed weekly using image analysis (Canopeo app) to evaluate the turfgrass green coverage. The green coverage percentage, together with the number of passages, is analyzed and correlated. The random pattern generated the highest number of passages and intersections, leading to lower average green coverage (64%) compared with the chessboard (80%) and vertical (81%) patterns. Data of the green coverage percentage in the function of the average number of passages recorded using the custom-built software for each pattern fit the asymptotic regression model. The effective number of passages to reach 60% green cover (EP60) was 56.26, 87.30, and 155.32 for random, vertical, and chessboard, respectively. The model could be integrated into DSS, useful for the end user in turf management in order to maintain a high quality. Future studies should extend this approach to other species and environmental conditions, integrating the effective dose (in terms of passages) method for smart mowing management.

Soil degradation in vineyards represents an increasing concern. Among vineyard management practices, under-row weed control is often performed through mechanical methods relying on equipment that may negatively affect soil health, highlighting the need to evaluate more sustainable solutions for soil preservation. This study, conducted during the 2024 growing season in Palaia (Pisa, Italy), aimed to evaluate and compare three under-row weed management strategies, each characterized by the implementation of two weed control interventions. One strategy was based on low-impact soil tillage, consisting of two operations: a first intervention performed with a rollhacke and a second one with a blade weeder. The other two strategies relied on weed cutting without soil disturbance from the implements: one involved two interventions with an under-vine mower, while the other included two interventions with a wire mulcher. No significant differences were observed in terms of weed biomass among the tested strategies, although the tillage-based solution generally resulted in greater weed height (41.31 cm), yet always below the cluster zone. In terms of total weed cover, the mowing-based strategy achieved the highest value (28.33%). The mowing-based strategy also showed higher species richness (2.17) compared with the mulching-based strategy, and a higher Shannon index (0.25) than both other strategies, highlighting the potential ecological value of this approach. However, from an operational perspective, the tillage- and mulching-based strategies proved to be the most efficient, both in terms of operating time (2.54 and 2.02 h ha⁻¹, respectively) and fuel consumption (10.63 and 11.47 kg ha⁻¹, respectively). On average, these two strategies reduced operating time and fuel consumption by 73.79% and 74.39%, respectively, compared with the mowing-based strategy.