Autonomous driving is greatly impacting intensive and precise agriculture. Matter-of-factly, the first commercial applications of autonomous driving were in autonomous navigation of agricultural tractors in open fields. As the technology improves, the possibility of using autonomous or semi-autonomous tractors in orchards and vineyards is becoming commercially profitable. These scenarios offer more challenges as the vehicle needs to position itself with respect to a more cluttered environment. This paper presents an adaptive localization system for (semi-) autonomous navigation of agricultural tractors in vineyards that is based on ultrasonic automotive sensors. The system estimates the distance from the left vineyard row and the incidence angle. The paper shows that a single tuning of the localization algorithm does not provide robust performance in all vegetation scenarios. We solve this issue by implementing an Extended Kalman Filter (EKF) and by introducing an adaptive data selection stage that automatically adapts to the vegetation conditions and discards invalid measurements. An extensive experimental campaign validates the main features of the localization algorithm. In particular, we show that the Root Mean Square Error (RMSE) of the distance is 16 cm, while the angular RMSE is 2.6 degrees.

No abstract

Advanced Driver Assistance Systems (ADAS) and autonomous driving systems are relevant in the agricultural field, since they can ease personnel of demanding and repetitive tasks while increasing precision and productivity. This is particularly true in constrained environments represented by intensive and high value cultivations, like vineyards and orchards. Anyway, these contexts present numerous challenges: positioning accuracy in the range of centimeters is required in a environment with continuously-changing vegetation, reduced maneuvering space and unstable terrain.This paper presents an ADAS of level 3 for an agricultural tractor in a vineyard, focusing on its control system. The goal of the developed controller is to bring the vehicle at a desired distance from the crop rows and keep it aligned to them, so that the operator only has to set the tractor advancement speed and can focus on the ongoing agricultural procedures. This is achieved through a Linear Quadratic Integral (LQI) controller that relies on a control-oriented model of the system describing the dynamics of the vehicle position with respect to the vines. The system proves to be effective and easily tunable in order to obtain the desired behavior. An extensive experimental campaign validates the closed-loop system performance. In particular, the controller attains a steady state error of 5 cm, using a steering angle with Root Mean Square (RMS) of 1.05 deg.