Robot-supervised Learning of Crop Row Segmentation

Abstract

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.

Improved Real-Time Semantic Segmentation Network Model for Crop Vision Navigation Line Detection

“…The tractor was controlled for precise autonomous navigation in rice fields. Bakken et al (2021) proposed a CNN-based semantic segmentation network for crop row detection. The algorithm automatically uses noisy labels to train the network, enabling the robot to adapt well to seasonal and crop changes.…”