Large Scale Robotic Material Handling: Learning, Planning, and Control

2025-08-12

AI Summary

For high-safety, high-repeatability industrial tasks—such as precise bulk pile grasping and truck loading—in large-scale robotic material handling, this paper presents the first fully autonomous operational framework for 40-ton hydraulic material handlers. Methodologically: (1) an attack-point planning module based on deep reinforcement learning optimizes grasping efficiency; (2) a robust trajectory-tracking controller actively exploits the underactuated grab’s natural pendular dynamics to enable dynamic dumping, thereby enhancing placement accuracy and operational safety; and (3) integrated environment perception, closed-loop path planning, and motion control enable real-time adaptive operation under complex, unstructured conditions. Field evaluations demonstrate that the system surpasses human operators in positioning accuracy, task repeatability, and safety performance, achieving, for the first time, end-to-end automation of large-scale material handling workflows.

Technology Category

• Intelligent Robots: Manipulation
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Bulk material handling involves the efficient and precise moving of large quantities of materials, a core operation in many industries, including cargo ship unloading, waste sorting, construction, and demolition. These repetitive, labor-intensive, and safety-critical operations are typically performed using large hydraulic material handlers equipped with underactuated grippers. In this work, we present a comprehensive framework for the autonomous execution of large-scale material handling tasks. The system integrates specialized modules for environment perception, pile attack point selection, path planning, and motion control. The main contributions of this work are two reinforcement learning-based modules: an attack point planner that selects optimal grasping locations on the material pile to maximize removal efficiency and minimize the number of scoops, and a robust trajectory following controller that addresses the precision and safety challenges associated with underactuated grippers in movement, while utilizing their free-swinging nature to release material through dynamic throwing. We validate our framework through real-world experiments on a 40 t material handler in a representative worksite, focusing on two key tasks: high-throughput bulk pile management and high-precision truck loading. Comparative evaluations against human operators demonstrate the system's effectiveness in terms of precision, repeatability, and operational safety. To the best of our knowledge, this is the first complete automation of material handling tasks on a full scale.

Problem

• Autonomous large-scale material handling for industries
• Reinforcement learning for optimal grasping and scooping
• Precision and safety control for underactuated grippers

Innovation

• Reinforcement learning for optimal grasping locations
• Dynamic throwing with underactuated grippers
• Integrated perception, planning, and control system