Hostname: page-component-7b7567c8c-2n9c9 Total loading time: 0 Render date: 2026-11-16T21:49:34.017Z Has data issue: false hasContentIssue false

Development of a sensor fusion method for crop row tracking operations

Published online by Cambridge University Press:  01 June 2017

B. Benet*
Affiliation:
IRSTEA, UR TSCF, 9 avenue Blaise Pascal, 63178 Aubière, France
R. Lenain
Affiliation:
IRSTEA, UR TSCF, 9 avenue Blaise Pascal, 63178 Aubière, France
V. Rousseau
Affiliation:
IRSTEA, UR TSCF, 9 avenue Blaise Pascal, 63178 Aubière, France

Abstract

A sensor fusion method was developed in order to track crop rows, considering various vegetation levels, for various crops. This application consisted to use a laser sensor, an inertial measurement unit and a color camera, in a fusion mode, to get a set of points corresponding to crop rows and eliminate noise like grass or leaves in environment, in real time. After applying a method such as Hough or Least Square (LS) technique for obtaining the geometric data of the crop line, automatic control operations were applied to realize the crop row tracking operation, with the desired lateral deviation parameter, taking into account the robot angular deviation and the temporal aspect, to realize the task with accuracy and without oscillations. The results showed the robustness of fusion method, to get a stable autonomous navigation for crop row tracking, particularly in the vineyards, with many perturbations such as bumps, hole and mud, and speeds between 1 and 2 m s-1. The mean lateral error between desired and obtained trajectory varied between 0.10 and 0.40 m, depending of speed and perturbations.

Figure 0

Figure 1Mobile robot with color Camera, LiDAR and IMU

Figure 1

Figure 2Crop row tracking operation

Figure 2

Figure 3Robot model – Fusion LiDAR/IMU

Figure 3

Figure 4Calibration Camera/LiDAR

Figure 4

Figure 5Fusion Camera/LiDAR

Figure 5

Figure 6Crop row detection

Figure 6

Figure 7Robot control for crop row tracking

Figure 7

Figure 8Test fields for crop row tracking operations

Figure 8

Figure 9Fusion results

Figure 9

Figure 10Experimental data for comparison between LS technique and Hough method

Figure 10

Table 1Statistical data for comparison between LS technique and Hough method

Figure 11

Figure 11Crop row tracking on soil without and with perturbations

Figure 12

Figure 12Speed influence on crop row tracking accuracy