Back to Explorer
Research PaperResearchia:202603.10083[Robotics > Robotics]

SG-DOR: Learning Scene Graphs with Direction-Conditioned Occlusion Reasoning for Pepper Plants

Rohit Menon

Abstract

Robotic harvesting in dense crop canopies requires effective interventions that depend not only on geometry, but also on explicit, direction-conditioned relations identifying which organs obstruct a target fruit. We present SG-DOR (Scene Graphs with Direction-Conditioned Occlusion Reasoning), a relational framework that, given instance-segmented organ point clouds, infers a scene graph encoding physical attachments and direction-conditioned occlusion. We introduce an occlusion ranking task for retrieving and ranking candidate leaves for a target fruit and approach direction, and propose a direction-aware graph neural architecture with per-fruit leaf-set attention and union-level aggregation. Experiments on a multi-plant synthetic pepper dataset show improved occlusion prediction (F1=0.73, NDCG@3=0.85) and attachment inference (edge F1=0.83) over strong ablations, yielding a structured relational signal for downstream intervention planning.


Source: arXiv:2603.06512v1 - http://arxiv.org/abs/2603.06512v1 PDF: https://arxiv.org/pdf/2603.06512v1 Original Link: http://arxiv.org/abs/2603.06512v1

Submission:3/10/2026
Comments:0 comments
Subjects:Robotics; Robotics
Original Source:
View Original PDF
arXiv: This paper is hosted on arXiv, an open-access repository
Was this helpful?

Discussion (0)

Please sign in to join the discussion.

No comments yet. Be the first to share your thoughts!