Learning Grasp Targeting from Point Clouds for Log Pile Clearing on a Hydraulic Crane

2026-10-05

AI Summary

This study addresses the challenge of precise autonomous grasping by hydraulic cranes operating within dense log piles using unsegmented point clouds. To this end, we propose an end-to-end neural network architecture that directly processes raw 3D point clouds to predict grasp poses and depths. By integrating behavioral cloning with reinforcement learning for simulation-only training, our method enables zero-shot sim-to-real transfer to physical cranes without requiring manual background filtering. Field experiments demonstrate that the proposed policy achieves a stockpile clearance rate of 93.8%, substantially outperforming the 80.4% attained by conventional geometry-based heuristic methods. These results validate the effectiveness of the Sim2Real paradigm in unstructured industrial environments.

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.

Problem

• log pile clearing
• grasp targeting
• point clouds
• hydraulic crane
• unsegmented

Innovation

• Point Clouds
• Behavior Cloning
• Reinforcement Learning
• Sim-to-Real Transfer
• Grasp Targeting