3D Distance Filter for the Autonomous Navigation of UAVs in Agricultural Scenarios

Abstract

In precision agriculture, remote sensing is an essential phase in assessing crop status and variability when considering both the spatial and the temporal dimensions. To this aim, the use of unmanned aerial vehicles (UAVs) is growing in popularity, allowing for the autonomous performance of a variety of in-field tasks which are not limited to scouting or monitoring. To enable autonomous navigation, however, a crucial capability lies in accurately locating the vehicle within the surrounding environment. This task becomes challenging in agricultural scenarios where the crops and/or the adopted trellis systems can negatively affect GPS signal reception and localisation reliability. A viable solution to this problem can be the exploitation of high-accuracy 3D maps, which provide important data regarding crop morphology, as an additional input of the UAVs’ localisation system. However, the management of such big data may be difficult in real-time applications. In this paper, an innovative 3D sensor fusion approach is proposed, which combines the data provided by onboard proprioceptive (i.e., GPS and IMU) and exteroceptive (i.e., ultrasound) sensors with the information provided by a georeferenced 3D low-complexity map. In particular, the parallel-cuts ellipsoid method is used to merge the data from the distance sensors and the 3D map. Then, the improved estimation of the UAV location is fused with the data provided by the GPS and IMU sensors, using a Kalman-based filtering scheme. The simulation results prove the efficacy of the proposed navigation approach when applied to a quadrotor that autonomously navigates between vine rows.

Complementary Use of Ground-Based Proximal Sensing and Airborne/Spaceborne Remote Sensing Techniques in Precision Agriculture: A Systematic Review

“…Some issues arise during this stage. As sensors become better and spatial resolution increases, the volume of acquired data increases, and UAV use in PA is faced with extreme data bloat ( [81,110,111]). Moreover, as mentioned earlier, data acquisition is not standardized, adding to the already considerable computing complexity of UAV images ( [57,86]).…”

“…Moreover, as mentioned earlier, data acquisition is not standardized, adding to the already considerable computing complexity of UAV images ( [57,86]). On top of that, the UAV itself can do little to share the burden of data processing as its computing capabilities are very limited ( [81,111]). When these ultra-high resolution data are used for machine learning (ML) training, it can take quite a while to complete ( [72,106]), even though the final results are more trustworthy and useful than training the ML algorithms with satellite acquired images.…”

Technical Challenges for Multi-Temporal and Multi-Sensor Image Processing Surveyed by UAV for Mapping and Monitoring in Precision Agriculture

“…To perform more sophisticated diagnoses, some systems also incorporate multiple sensors [19]. In addition, several methods are studied to apply Artificial Intelligence (AI) techniques on board UAVs [14], to make UAVs navigation autonomous even in complex scenarios [20], to use them in combination with ground-based instruments [21], or to overcome limitations due to the low resolution of images acquired from satellite platforms [22]. This technical note focuses on surveys using multiple sensors in a multi-temporal study, including RGB and thermal sensors.…”

Base de datos abierta TRAM-FPV RACING. Secuencias completas de vuelo indoor para el estudio de drones de carreras.

“…La información contenida en estas bases de datos suele contener datos de los sistemas de posicionamiento global (GNSS), cuando los vuelos se han realizado en espacios abiertos. Así como registros de los sensores del sistema de navegación inercial e, incluso, secuencias de vídeo para el guiado autónomo de la aeronave [17,29,49]. De igual forma, existen bases de datos que incorporan información de otro tipo de sensores, por ejemplo, sensores láser o ultrasónicos para detectar objetos o marcadores en el entorno de navegación [46].…”