Guardado en:
Detalles Bibliográficos
Autores principales: Pan, Sicong, Lobefaro, Luca, Taherkhani, Moein, Huang, Xuying, Menon, Rohit, Stachniss, Cyrill, Bennewitz, Maren
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2510.07028
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915879587938304
author Pan, Sicong
Lobefaro, Luca
Taherkhani, Moein
Huang, Xuying
Menon, Rohit
Stachniss, Cyrill
Bennewitz, Maren
author_facet Pan, Sicong
Lobefaro, Luca
Taherkhani, Moein
Huang, Xuying
Menon, Rohit
Stachniss, Cyrill
Bennewitz, Maren
contents Repeated plant monitoring is essential for tracking crop growth, and 3D reconstruction enables consistent comparison across monitoring sessions. However, rebuilding a 3D model from scratch in every session is costly and overlooks informative geometry already observed previously. We propose efficient view planning guided by a previous-session reconstruction, which reuses a 3D model from the previous session to improve active perception in the current session. Based on this previous-session reconstruction, our method replaces iterative next-best-view planning with one-shot view planning that selects an informative set of views and computes the globally shortest execution path connecting them. Experiments on real multi-session datasets, including public single-plant scans and a newly collected greenhouse crop-row dataset, show that our method achieves comparable or higher surface coverage with fewer executed views and shorter robot paths than iterative and one-shot baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2510_07028
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient View Planning Guided by Previous-Session Reconstruction for Repeated Plant Monitoring
Pan, Sicong
Lobefaro, Luca
Taherkhani, Moein
Huang, Xuying
Menon, Rohit
Stachniss, Cyrill
Bennewitz, Maren
Robotics
Repeated plant monitoring is essential for tracking crop growth, and 3D reconstruction enables consistent comparison across monitoring sessions. However, rebuilding a 3D model from scratch in every session is costly and overlooks informative geometry already observed previously. We propose efficient view planning guided by a previous-session reconstruction, which reuses a 3D model from the previous session to improve active perception in the current session. Based on this previous-session reconstruction, our method replaces iterative next-best-view planning with one-shot view planning that selects an informative set of views and computes the globally shortest execution path connecting them. Experiments on real multi-session datasets, including public single-plant scans and a newly collected greenhouse crop-row dataset, show that our method achieves comparable or higher surface coverage with fewer executed views and shorter robot paths than iterative and one-shot baselines.
title Efficient View Planning Guided by Previous-Session Reconstruction for Repeated Plant Monitoring
topic Robotics
url https://arxiv.org/abs/2510.07028