发表机构
McGill University; FPInnovations（麦吉尔大学; FPInnovations）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对液压起重机清理原木堆任务，提出一种从点云学习抓取目标的方法，通过行为克隆和强化学习训练策略，在仿真和现场试验中均优于几何启发式，实现高效清理。
AI 中文摘要
在木材堆场中，原木装载机通过一系列成捆抓取来清理密集的原木堆：数百根原木相互接触，每次移除都会改变下一次抓取可用的原木堆。一种学习策略从未分割的点云中选择抓斗的放置位置和方向，并运行在拖车安装的液压林业起重机上。该策略对在哪个观察点进行抓取进行分类，并预测该处的深度和抓斗方向。同一网络支持行为克隆（BC）、强化学习（RL）和部署。BC从成功的堆顶演示中学习；RL通过微调克隆策略（BC→RL）或从头训练来探索改进。在仿真中，BC清除了200根原木的100堆中的98堆，而BC→RL提高了负载稳定性。十二次现场试验比较了几何启发式、从头RL、BC和BC→RL在完整的抓取-运输-放置循环中的表现。BC和BC→RL分别清除了总库存的93.8%和88.9%，而启发式为80.4%。BC→RL在其83.6%的循环中放置了原木，而启发式为79.6%，BC为65.7%，而其模拟中的稳定性提升并未转移到起重机测试台上。完全在仿真中训练并原样在起重机上运行，学习策略比手工过滤的启发式清理得更多，同时观察未过滤的点云，其中仍包含存储架的轨道和杆。
英文摘要
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.
Comments9 pages, 15 figures. Supplementary video: https://youtu.be/woyDNW_oN7A
