A Novel Perception and Semantic Mapping Method for Robot Autonomy in Orchards

TL;DR

This paper introduces a new semantic mapping and navigation framework for orchard robots, combining 3D object detection and terrain-aware visibility mapping to enhance autonomous operation in complex agricultural environments.

Contribution

The study presents a novel 3D detection network and a semantic visibility mapping framework tailored for orchard environments, advancing robotic autonomy in agriculture.

Findings

High accuracy in environment understanding demonstrated

Effective robot autonomy in orchard scenarios achieved

Framework applicable to phenotyping and harvesting tasks

Abstract

Agricultural robots must navigate challenging dynamic and semi-structured environments. Recently, environmental modeling using LiDAR-based SLAM has shown promise in providing highly accurate geometry. However, how this chaotic environmental information can be used to achieve effective robot automation in the agricultural sector remains unexplored. In this study, we propose a novel semantic mapping and navigation framework for achieving robotic autonomy in orchards. It consists of two main components: a semantic processing module and a navigation module. First, we present a novel 3D detection network architecture, 3D-ODN, which can accurately process object instance information from point clouds. Second, we develop a framework to construct the visibility map by incorporating semantic information and terrain analysis. By combining these two critical components, our framework is evaluated in a number of key horticultural production scenarios, including a robotic system for in-situ phenotyping and daily monitoring, and a selective harvesting system in apple orchards. The experimental results show that our method can ensure high accuracy in understanding the environment and enable reliable robot autonomy in agricultural environments.