Automated robotic platforms are an important part of precision agriculture solutions for sustainable food production. Agri-robots require robust and accurate guidance systems in order to navigate between crops and to and from their base station. Onboard sensors such as machine vision cameras offer a flexible guidance alternative to more expensive solutions for structured environments such as scanning lidar or RTK-GNSS. The main challenges for visual crop row guidance are the dramatic differences in appearance of crops between farms and throughout the season and the variations in crop spacing and contours of the crop rows. Here we present a visual guidance pipeline for an agri-robot operating in strawberry fields in Norway that is based on semantic segmentation with a convolution neural network (CNN) to segment input RGB images into crop and not-crop (i.e., drivable terrain) regions. To handle the uneven contours of crop rows in Norway’s hilly agricultural regions, we develop a new adaptive multi-ROI method for fitting trajectories to the drivable regions. We test our approach in open-loop trials with a real agri-robot operating in the field and show that our approach compares favourably to other traditional guidance approaches.
In this paper, we present an automatic motion planner for agricultural robots that allows us to set up a robot to follow rows without having to explicitly enter waypoints. In most cases, when robots are used to cover large agricultural areas, they will need waypoints as inputs, either as premeasured coordinates in an outdoor environment, or as positions in a map in an indoor environment. This can be a tedious process as several hundreds or even thousands of waypoints will be needed for large farms. In particular, we find that in unstructured environments such as the ones found on farms, the need for waypoints increases. In this paper, we present an approach that enables robots to safely traverse not only between straight rows but also through curved rows without the need for any predetermined waypoints. Most types of infrastructure found in agriculture, such as polytunnels, are built on uneven terrain, thus containing a mix of straight and curved plant rows, for which traditional methods of row following will fail. Different from traditional approaches of row following that only consider straight‐line‐of‐sight rows, our approach identifies the rows on each side with the goal of staying in the middle of the rows, even if the rows are not straight. Waypoints are only needed on the very extreme of the rows, and these will be automatically generated by the system. With our approach, the robot can just be placed in the corner of the field and will then determine the trajectory without further input from the user. We thus obtain an approach that can reduce the installation time from potentially hours to just a matter of minutes. The final autonomous system is low cost and efficient for various tasks that requires moving between plant rows inside a polytunnel. Several experiments were performed and the robot demonstrates 1.4% position drift over 21 m of navigation path.
We propose an approach for robot-supervised learning that automates label generation for semantic segmentation with Convolutional Neural Networks (CNNs) for crop row detection in a field. Using a training robot equipped with RTK GNSS and RGB camera, we train a neural network that can later be used for pure vision-based navigation. We test our approach on an agri-robot in a strawberry field and successfully train crop row segmentation without any hand-drawn image labels. Our main finding is that the resulting segmentation output of the CNN shows better performance than the noisy labels it was trained on. Finally, we conduct open-loop field trials with our agri-robot and show that row-following based on the segmentation result is likely accurate enough for closedloop guidance. We conclude that automatically generating noisy segmentation labels is a promising approach for vision-based row following that can be quickly and easily adapted to new scenes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.