Towards Autonomous Wood-Log Grasping with a Forestry Crane: Simulator and Benchmarking

2025-02-03

AI Summary

To address the low success rate of autonomous grasping of heavy, multi-sized logs by forestry cranes in unstructured forest environments, this paper introduces the first open-source, high-fidelity MuJoCo simulation benchmark—built upon a CAD-driven, 8-DOF crane model—and proposes a curriculum-based deep reinforcement learning grasping policy tailored to its underactuated dynamics, extending the DDPG framework with a sparse reward function and phased training. Key contributions include: (1) the first open-source simulation and evaluation standard specifically designed for forestry equipment, supporting logs of varying diameters and randomized initial poses; (2) achieving a 96% average grasping success rate across diverse log configurations; and (3) releasing the full simulation environment and baseline algorithms to enable reproducible research on autonomous manipulation of heavy objects in野外 settings.

Technology Category

• Intelligent Robots: Manipulation
• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Forestry machines operated in forest production environments face challenges when performing manipulation tasks, especially regarding the complicated dynamics of underactuated crane systems and the heavy weight of logs to be grasped. This study investigates the feasibility of using reinforcement learning for forestry crane manipulators in grasping and lifting heavy wood logs autonomously. We first build a simulator using Mujoco physics engine to create realistic scenarios, including modeling a forestry crane with 8 degrees of freedom from CAD data and wood logs of different sizes. We further implement a velocity controller for autonomous log grasping with deep reinforcement learning using a curriculum strategy. Utilizing our new simulator, the proposed control strategy exhibits a success rate of 96% when grasping logs of different diameters and under random initial configurations of the forestry crane. In addition, reward functions and reinforcement learning baselines are implemented to provide an open-source benchmark for the community in large-scale manipulation tasks. A video with several demonstrations can be seen at https://www.acin.tuwien.ac.at/en/d18a/

Problem

• Forestry crane
• Automated wood retrieval
• Efficiency improvement

Innovation

• Reinforcement Learning
• Deep Learning
• Automated Timber Grasping