This letter describes Fields2Cover, a novel open source library for coverage path planning (CPP) for agricultural vehicles. While there are several CPP solutions nowadays, there have been limited efforts to unify them into an open source library and provide benchmarking tools to compare their performance. Fields2Cover provides a framework for planning coverage paths, developing novel techniques, and benchmarking state-of-the-art algorithms. The library features a modular and extensible architecture that supports various vehicles and can be used for a variety of applications, including farms. Its core modules are: a headland generator, a swath generator, a route planner and a path planner. An interface to the Robot Operating System (ROS) is also supplied as an add-on. In this letter, the functionalities of the library for planning a coverage path in agriculture are demonstrated using 8 state-of-the-art methods and 7 objective functions in simulation and field experiments.

We introduce a methodology for headland coverage planning for autonomous agricultural robot systems, which is a complex problem often overlooked in agricultural robotics. At the corners of the headlands, a robot faces the risk to cross the border of a field while turning. Though potentially dangerous, current papers about corner turns in headlands do not tackle this issue. Moreover, they produce paths with curvature discontinuities, which are not feasible by non‐holonomic robots. This paper presents an approach to strictly adhere to field borders during the headland coverage, and three types of continuous curvature turn planners for convex and concave corners. The turning planners are evaluated in terms of path length and uncovered area to assess their effectiveness in headland corner navigation. Through empirical validation, including extensive tests on a coverage path planning benchmark as well as real‐field experiments with an autonomous robot, the proposed approach demonstrates its practical applicability and effectiveness. In simulations, the mean coverage area of the fields went from 94.73%, using a constant offset around the field, to 97.29% using the proposed approach. Besides providing a solution to the coverage of headlands in agricultural automation, this paper also extends the covered area on the mainland, thus increasing the overall productivity of the field.

Soil compaction caused by heavy agricultural machinery poses a significant challenge to sustainable farming by degrading soil health, reducing crop productivity, and disrupting environmental dynamics. Field traffic optimization can help abate compaction, yet conventional algorithms have mostly focused on minimizing route length while overlooking soil compaction dynamics in their cost function. This study introduces Soil2Cover, an approach that combines controlled traffic farming principles with the SoilFlex model to minimize soil compaction by optimizing machinery paths. Soil2Cover prioritizes the frequency of machinery passes over specific areas, while integrating soil mechanical properties to quantify compaction impacts. Results from tests on 1000 fields demonstrate that our approach achieves a reduction in route length of up to 4-6% while reducing the soil compaction on headlands by up to 30% in both single-crop and intercropping scenarios. The optimized routes improve crop yields whilst reducing operational costs, lowering fuel consumption and decreasing the overall environmental footprint of agricultural production. The implementation code will be released with the third version of Fields2Cover, an open-source library for the coverage path planning problem in agricultural settings.

An acrobot is a planar robot with a passive actuator in its first joint. The main purpose of this system is to make it rise from the rest position to the inverted pendulum position. This control problem can be divided in the swing-up issue, when the robot has to rise itself by swinging up as a human acrobat does, and the balancing issue, when the robot has to maintain itself in the inverted pendulum position. We have developed three controllers for the swing-up problem applied to two types of motors: small and large. For small motors, we used the State-Action-Reward-State-Action (SARSA) controller and the proportional–derivative (PD) controller with a trajectory generator. For large motors, we propose a new controller to control the acrobot—a pulse-width modulation (PWM) controller. All controllers except SARSA are tuned using a genetic algorithm.