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