Lavender Autonomous Navigation with Semantic Segmentation at the Edge

TL;DR

This paper presents a segmentation-based visual navigation method for lavender fields that operates effectively in real-world and simulation scenarios, especially when GPS signals are unreliable or unavailable.

Contribution

It introduces a novel edge-based navigation algorithm tailored for lavender fields, demonstrating its robustness and adaptability across diverse conditions.

Findings

High accuracy in real-world lavender navigation

Effective generalization across different scenarios

Reliable performance without GPS reliance

Abstract

Achieving success in agricultural activities heavily relies on precise navigation in row crop fields. Recently, segmentation-based navigation has emerged as a reliable technique when GPS-based localization is unavailable or higher accuracy is needed due to vegetation or unfavorable weather conditions. It also comes in handy when plants are growing rapidly and require an online adaptation of the navigation algorithm. This work applies a segmentation-based visual agnostic navigation algorithm to lavender fields, considering both simulation and real-world scenarios. The effectiveness of this approach is validated through a wide set of experimental tests, which show the capability of the proposed solution to generalize over different scenarios and provide highly-reliable results.