A Navigation Architecture for Ackermann Vehicles in Precision Farming

Abstract

In this letter, inspired by the needs of the European H2020 Project PANTHEON 1 , we propose a full navigation stack purposely designed for the autonomous navigation of Ackermann steering vehicles in precision farming settings. The proposed stack is composed of a local planner and a pose regulation controller, both implemented in ROS. The local planner generates, in real-time, optimal trajectories described by a sequence of successive poses. The planning problem is formulated as a real-time cost-function minimization problem over a finite time horizon where the Ackermann kinematics and the presence of obstacles are encoded as constraints. The control law ensures the convergence toward each of these poses. To do so, in this paper we propose a novel non-smooth control law designed to ensure the solvability of the pose regulation problem for the Ackermann vehicle. Theoretical characterization of the convergence property of the proposed pose regulation controller is provided. Numerical simulations along with real-world experiments are provided to corroborate the effectiveness of the proposed navigation strategy.

Integration of Remote Sensing Data into a Composite Voxel Model for Environmental Performance Analysis of Terraced Vineyards in Tuscany, Italy

“…Both terrestrial and aerial autonomous robotic platforms are constantly collecting large quantities of geospatial data, which are centrally processed to support the execution of common orchard maintenance tasks, such as irrigation. The need for interdisciplinary data integration resulted in the publication of a pyoints python library [31], which bridges different representations of geometric point-based data, including point clouds and geo-referenced rasters, as well as the voxels required by the prototype of farming robots aimed at precision agriculture applications [32].…”

A Generic ROS-Based Control Architecture for Pest Inspection and Treatment in Greenhouses Using a Mobile Manipulator

“…Nowadays, robotic solutions combined with computer vision can be used to automate this repetitive inspection task, increasing the reliability, maximizing the health of crops and optimizing the use of pesticides to as little as 5%-10% [6]. For that purpose, robots need to implement plenty of different tasks such as localize themselves [7] and navigate inside greenhouses [8]- [9]; acquire quality pictures to identify pests and their locations [10]; or process the obtained results to generate efficient highlevel instructions to command the robot according to an Integrated Pest Management (IPM) system [11]. However, most research works focus on individual problems neglecting its integration within a single complete solution.…”

Experimental Evaluation of a Hierarchical Operating Framework for Ground Robots in Agriculture

“…Additionally, to achieve robust autonomy, the robot must be able to adapt any mission level plan in response to the presence of both unknown and dynamic elements in these unstructured environments. Currently, autonomous field robots are limited to use in more structured environments, including row crops [1] or orchards [2], where dynamic elements such as moving individuals are not a critical consideration. These approaches generally make use of reactive planners, which can adapt to unforeseen static obstacles.…”