Improved localization in a corn crop row using a rotated laser rangefinder for three-dimensional data acquisition

Abstract

Small robotic vehicles have been navigating agricultural fields in the pursuit of new possibilities to increase agricultural production and to meet the increasing food and energetic demands. However, a perception system with reliable awareness of the surroundings remains a challenge to achieve autonomous navigation. Camera and single-layer laser scanners have been the primary sources of information, yet the first suffers from outdoor light sensibility and both from occlusion by leaves. This paper describes a three-dimensional system acquisition for corn crops. The sensing core is a single-layer UTM30-LX laser scanner rotating around its axis, while an inertial sensor provides angular measurements. With the rotation, multiple layers are used to compose a 3D point cloud, which is represented by a two-dimensional occupancy grid. Each cell is filled according to the number of readings, and their weights derive from two procedures: firstly, a mask enhances vertical entities (stalks); secondly, two Gaussian functions on the expected position of the immediate neighboring rows weaken readings in the middle of the lane and farther rows. The resulting occupancy grid allows the representation of the cornrows by virtual walls, which are used as references to a wall follower algorithm. According to experimental results, the virtual walls are segmented with reduced influence from straying leaves and sparse weeds when compared to the segmentation done with single-layer laser scanner data. Indeed, 64.02% of 3D outputs are within 0.05 m limit error from expected lane width, while only 11.63% of single-layer laser data are within same limit.

Unimodal and Multimodal Perception for Forest Management: Review and Dataset

“…Another application of perception systems in precision agriculture is characterising, monitoring, and phenotyping vegetative cultures using stereo vision [124,125], point clouds [126,127], satellite imagery [128], low-altitude aerial images [129], or multispectral imagery [130]. Along with these advances in terms of perception, several robotic platforms have appeared: for harvesting [101,102,[104][105][106], for precise spraying [131], for plant counting [132], and for general agricultural tasks [133][134][135][136]. A topic that is being increasingly studied in the agricultural sector is localisation and consequent autonomous navigation in crops.…”

2D LiDAR-based perception for under canopy autonomous scouting of small ground robots within narrow lanes of agricultural fields

“…For each experiment, hElvis IV traveled roughly 10 m with an average forward speed of 0.2 m/s. The findings were reported in Gasparino, Higuti, Velasquez and Becker (2020). An unsuccessful trial of autonomous hElvis using MLSS is provided in the supplementary material 6 .…”

“…Because MLSS and the robot shares same orientation angles, information from IMU 2 allows the correct spatial transformation of the scans from LiDAR's position (top of the mast) to the origin considered by the perception subsystem (geometric center of the LiDAR at the robot's front part). Additional information is provided on Gasparino, Higuti, Velasquez and Becker (2020). The other sensors such as IMU, motor rotary gauges and GNSS devices will be listed with the used platforms in the next section.…”

“…An unsuccessful trial of autonomous hElvis using MLSS is provided in the supplementary material 6 . Source: generated based on data from Gasparino, Higuti, Velasquez and Becker (2020).…”

“…LiDAR has been used to capture a horizontal scan of the surroundings. Angled LiDAR scans can be suitably treated to form a 3-D point cloud with similar procedures as MLSS (GASPARINO, 2020). Therefore, to understand the performance changes that will happen due to the change of LiDAR's orientation, the device was characterized in the standard orientation and an extreme case where the sensor was placed upside-down.…”