Deep Semantic Segmentation at the Edge for Autonomous Navigation in Vineyard Rows

TL;DR

This paper presents an affordable, low-power edge AI solution for vineyard navigation using semantic segmentation, enabling autonomous robots to operate reliably with minimal sensors and computational resources.

Contribution

The authors introduce a novel low-cost, low-power semantic segmentation approach for vineyard navigation that combines custom-trained networks with RGB-D cameras, enhancing practicality and robustness.

Findings

Achieved smooth, stable navigation trajectories in vineyards

Demonstrated robustness in real-world and simulated environments

Segmentation maps can be used for crop health assessment

Abstract

Precision agriculture is a fast-growing field that aims at introducing affordable and effective automation into agricultural processes. Nowadays, algorithmic solutions for navigation in vineyards require expensive sensors and high computational workloads that preclude large-scale applicability of autonomous robotic platforms in real business case scenarios. From this perspective, our novel proposed control leverages the latest advancement in machine perception and edge AI techniques to achieve highly affordable and reliable navigation inside vineyard rows with low computational and power consumption. Indeed, using a custom-trained segmentation network and a low-range RGB-D camera, we are able to take advantage of the semantic information of the environment to produce smooth trajectories and stable control in different vineyards scenarios. Moreover, the segmentation maps generated by the control algorithm itself could be directly exploited as filters for a vegetative assessment of the crop status. Extensive experimentations and evaluations against real-world data and simulated environments demonstrated the effectiveness and intrinsic robustness of our methodology.