Metraipolis › archive › dc_51becbd5e93d
HarvestPoint-ACT: Explicit Target Selection and Harvest-Point Conditioning for Robotic Fruit Harvesting under Occlusion — arXiv:2608.18446
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.18446
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T14:06:59.155Z
- SHA-256 of the archived text
9b31e12cb5fbeed027eff5c11ba576333510ed74453224e8fed8d55409239dec- Stable URL of this page
https://metraipolis.com/documento/dc_51becbd5e93d
How to cite
HarvestPoint-ACT: Explicit Target Selection and Harvest-Point Conditioning for Robotic Fruit Harvesting under Occlusion — arXiv:2608.18446 — arXiv (en), https://arxiv.org/abs/2608.18446 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_51becbd5e93d (Metraipolis archive dc_51becbd5e93d, sha256 9b31e12cb5fbeed027eff5c11ba576333510ed74453224e8fed8d55409239dec)
BibTeX
@misc{dc51becbd5e93d,
title = {HarvestPoint-ACT: Explicit Target Selection and Harvest-Point Conditioning for Robotic Fruit Harvesting under Occlusion — arXiv:2608.18446},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.18446},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_51becbd5e93d; sha256 9b31e12cb5fbeed027eff5c11ba576333510ed74453224e8fed8d55409239dec},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18446. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
End-to-end imitation learning avoids hand-made robot motion for approaching and grasping, but the policy must still decide which fruit to pick and where to close the gripper. Occlusion can make the policy lose the selected fruit during harvesting, and the correct closing point is difficult to infer from pixels alone. This paper presents HarvestPoint-ACT, which makes both decisions explicit in perception and provides them to the policy. An instance segmentation front end with a keypoint branch predicts a mask and a harvest point for each visible fruit, where the harvest point specifies the location to close the gripper. A scheduler ranks detected candidates by occlusion and travel distance and selects one target. After each attempt, it redetects and reranks the candidates because the canopy may have changed. The selected fruit is encoded for an action chunking transformer as an eight-dimensional state, containing the absolute harvest point, the vector from the gripper to that point, a validity flag, and a confidence score. When the selected fruit is temporarily undetected, the system retains the last harvest point estimate in the robot base frame and marks it as stale, and aborts the attempt if the loss persists. On a canopy mock-up, HarvestPoint-ACT achieves a success rate of 88%, and of 75% under heavy occlusion. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-20 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2608.18446 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T14:02:33.839Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).