Safe Leaf Manipulation for Accurate Shape and Pose Estimation of Occluded Fruits

TL;DR

This paper presents an active manipulation approach where robots physically move occluding leaves to improve the accuracy of fruit shape and pose estimation, especially under heavy occlusion conditions.

Contribution

It introduces a novel framework combining scene-consistent shape completion and perception-driven leaf deformation modeling for improved fruit estimation.

Findings

Enhanced accuracy in fruit shape and pose estimation under occlusion

Effective leaf manipulation that minimizes damage and maximizes visibility

Outperforms baseline methods in experiments on real and artificial plants

Abstract

Fruit monitoring plays an important role in crop management, and rising global fruit consumption combined with labor shortages necessitates automated monitoring with robots. However, occlusions from plant foliage often hinder accurate shape and pose estimation. Therefore, we propose an active fruit shape and pose estimation method that physically manipulates occluding leaves to reveal hidden fruits. This paper introduces a framework that plans robot actions to maximize visibility and minimize leaf damage. We developed a novel scene-consistent shape completion technique to improve fruit estimation under heavy occlusion and utilize a perception-driven deformation graph model to predict leaf deformation during planning. Experiments on artificial and real sweet pepper plants demonstrate that our method enables robots to safely move leaves aside, exposing fruits for accurate shape and pose estimation, outperforming baseline methods. Project page: https://shaoxiongyao.github.io/lmap-ssc/.