arXiv：cs.LG· George Sideris, Lucas Bessai, Heshan Fernando, Elie Ayoub, Nicolas Lemieux, Inna Sharf·· 4 小时前AI 评分38
基于点云的学习式抓取目标定位：液压林业起重机原木堆清理
Learning Grasp Targeting from Point Clouds for Log Pile Clearing on a Hydraulic Crane
AI 导读
研究提出一种从无分割点云中学习抓取策略的方法，部署于拖车式液压林业起重机，由同一网络同时输出抓取点分类及抓取深度与朝向预测。仿真中行为克隆（BC）成功清理100堆200根原木中的98堆，BC→RL 进一步提升负载稳定性。12次现场试验显示，BC 与 BC→RL 分别堆放93.8%和88.9%的原木，优于几何启发式的80.4%；策略完全在仿真中训练并在起重机原样运行。
正文
Abstract:In mill yards, log loaders clear dense piles by a sequence of bundle grasps: hundreds of logs rest in contact, and each removal changes the pile available to the next grasp. A learned policy chooses where to place and orient the grapple from unsegmented point clouds and runs on a trailer-mounted hydraulic forestry crane. The policy classifies at which observed point to grasp and predicts depth and grapple orientation there. The same network outputs support behavior cloning (BC), reinforcement learning (RL), and deployment. BC learns from successful top-of-pile demonstrations; RL explores for improvements by fine-tuning the cloned policy (BC$\to$RL) or by training from scratch. In simulation, BC clears 98 of 100 piles of 200 logs, while BC$\to$RL improves load stability. Twelve field trials compare a geometric heuristic, RL from scratch, BC, and BC$\to$RL through complete grasp-transport-deposit cycles. BC and BC$\to$RL deposit 93.8% and 88.9% of pooled inventory, against 80.4% for the heuristic. BC$\to$RL deposits logs on 83.6% of its cycles, against 79.6% for the heuristic and 65.7% for BC, while its simulated stability gain does not carry over to the crane testbed. Trained entirely in simulation and run unchanged on the crane, the learned policies clear more than the hand-filtered heuristic while observing unfiltered clouds that still contain the storage rack's rails and poles.
| Comments: | 9 pages, 15 figures. Supplementary video: this https URL |
| Subjects: | Robotics (cs.RO); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.07613 [cs.RO] |
| (or arXiv:2610.07613v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07613 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: George Sideris [view email]
[v1]
Tue, 6 Oct 2026 02:01:30 UTC (4,716 KB)
来源：arXiv：cs.LG · arxiv.org