Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Jun 26:14:1207742.
doi: 10.3389/fpls.2023.1207742. eCollection 2023.

Research on orchard navigation method based on fusion of 3D SLAM and point cloud positioning

Ye Xia  1   2   3 , Xiaohui Lei  1   2 , Jian Pan  1   2 , LuWei Chen  1   2 , Zhen Zhang  1   2 , Xiaolan Lyu  1   2
Affiliations

Research on orchard navigation method based on fusion of 3D SLAM and point cloud positioning

Ye Xia et al. Front Plant Sci. .

Abstract

Accurate navigation is crucial in the construction of intelligent orchards, and the need for vehicle navigation accuracy becomes even more important as production is refined. However, traditional navigation methods based on global navigation satellite system (GNSS) and 2D light detection and ranging (LiDAR) can be unreliable in complex scenarios with little sensory information due to tree canopy occlusion. To solve these issues, this paper proposes a 3D LiDAR-based navigation method for trellis orchards. With the use of 3D LiDAR with a 3D simultaneous localization and mapping (SLAM) algorithm, orchard point cloud information is collected and filtered using the Point Cloud Library (PCL) to extract trellis point clouds as matching targets. In terms of positioning, the real-time position is determined through a reliable method of fusing multiple sensors for positioning, which involves transforming the real-time kinematics (RTK) information into the initial position and doing a normal distribution transformation between the current frame point cloud and the scaffold reference point cloud to match the point cloud position. For path planning, the required vector map is manually planned in the orchard point cloud to specify the path of the roadway, and finally, navigation is achieved through pure path tracking. Field tests have shown that the accuracy of the normal distributions transform (NDT) SLAM method can reach 5 cm in each rank with a coefficient of variation that is less than 2%. Additionally, the navigation system has a high positioning heading accuracy with a deviation within 1° and a standard deviation of less than 0.6° when moving along the path point cloud at a speed of 1.0 m/s in a Y-trellis pear orchard. The lateral positioning deviation was also controlled within 5 cm with a standard deviation of less than 2 cm. This navigation system has a high level of accuracy and can be customized to specific tasks, making it widely applicable in trellis orchards with autonomous navigation pesticide sprayers.

Keywords: LiDAR; SLAM; autonomous navigation; orchard; robot; vector map.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Test fields. (A) Aerial view of the orchard. (B) Y-trellis for orchard.
Figure 2
Figure 2
Photograph of the mobile platform.
Figure 3
Figure 3
NDT mapping. NDT, normal distributions transform.
Figure 4
Figure 4
Pseudo code for conversion.
Figure 5
Figure 5
Flowchart of RTK fusion NDT location algorithm. RTK, real-time kinematics; NDT, normal distributions transform.
Figure 6
Figure 6
Vector map with manually labeled paths. The green part of the figure is the orchard point cloud, the pink route is the driving path, and the blue line is the driving boundary.
Figure 7
Figure 7
Pure pursuit model. Point A in the figure represents the current position, C represents the lookahead point position, and B represents the position of the vehicle during turning. The blue curve M represents the planned path, and the red curve AC represents the turning path. α is the heading angle at point A, β is the heading angle at point B, L is the distance from the center of the vehicle to the next position, Ld is the chord of the steering curvature arc, and ey is the error in the lateral direction between the rear wheel center position and the lookahead point.
Figure 8
Figure 8
Orchard point cloud map processing method. (A) Original point cloud map. (B) Voxel filtering point cloud. (C) Pass-through filtering point cloud. (D) The trellis point cloud.
Figure 9
Figure 9
Orchard point cloud mapping test. (A) Initial orchard point cloud and data collection trajectory in RVIZ. (B) Mapping effect test schematic. A1 to A8 and B1 to B8 are the relative horizontal distances between the trellis, and C1 to C8 are the vertical relative distances between the vertical vertices.
Figure 10
Figure 10
Fixed-point navigation tests. (A) Reference point distance measurement. (B) Schematic diagram of a fixed-point navigation test. M1 to M14 are measuring points on navigation path, and M is the distance between the tree column and the vehicle center.
Figure 11
Figure 11
Fixed-point navigation test results. (A) Lateral deviation results. (B) Heading deviation results. The top and bottom horizontal lines are the maximum and minimum values, respectively. Three-quarters of the experimental error data points are in the box.
Figure 12
Figure 12
Navigation tests at different speeds. (A–G) The control line planning under straight and curved roads.
See this image and copyright information in PMC

References

    1. Badrinarayanan V., Kendall A., Cipolla R. (2017). Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39, 2481–2495. doi: 10.1109/TPAMI.2016.2644615 - DOI - PubMed
    1. Bakker T., Van Asselt K., Bontsema J., Müller J., Van Straten G. (2011). Autonomous navigation using a robot platform in a sugar beet field. Biosyst. Eng. 109, 357–368. doi: 10.1016/j.biosystemseng.2011.05.001 - DOI
    1. Bayar G., Bergerman M., Koku A. B., Ilhan Konukseven E. (2015). Localization and control of an autonomous orchard vehicle. Comput. Electron. Agric. 115, 118–128. doi: 10.1016/j.compag.2015.05.015 - DOI
    1. Biber P., Straßer W. (2003). “The normal distributions transform: a new approach to laser scan matching,” in Proceedings2002, 003 IEEE/RSJ international conference on intelligent robots and systems (IROS2002, 003)(Cat. no. 03CH37453) (IEEE; ), 3, 2743–2748. doi: 10.1109/IROS.2003.1249285 - DOI
    1. Bin X., Junxiong Z., Feng Q., Zhiqi F., Dashuai W., Wei L. (2017). Navigation control system for orchard spraying machine based on beidou navigation satellite system. Nongye Jixie Xuebao/Transact. Chin. Soc. Agric. Machinery 48, 45–50. doi: 10.6041/j.issn.1000-1298.2017.02.006 - DOI

LinkOut - more resources