Automating Box Folding: Sequence Extraction and Ranking Methodologies

2025-05-07

AI Summary

Automated carton folding in packaging systems faces challenges in generating feasible folding sequences and ensuring hardware compatibility. Method: This paper proposes a hardware-aware folding path planning method that jointly models geometric reasoning and kinematic constraints to establish a dual-dimensional evaluation framework—assessing both feasibility (physical realizability) and compatibility (actuator capability alignment). It introduces, for the first time, a learning-to-rank–driven sequence selection mechanism to replace conventional heuristic search. The method integrates a robot control interface, enabling dynamic adaptation to diverse carton geometries and closed-loop validation. Results: Experiments on a real robotic platform demonstrate a 92.3% accuracy in folding sequence recommendation and an average planning time of only 1.78 seconds, significantly enhancing production line flexibility and deployment efficiency.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Box folding represents a crucial challenge for automated packaging systems. This work bridges the gap between existing methods for folding sequence extraction and approaches focused on the adaptability of automated systems to specific box types. An innovative method is proposed to identify and rank folding sequences, enabling the transformation of a box from an initial state to a desired final configuration. The system evaluates and ranks these sequences based on their feasibility and compatibility with available hardware, providing recommendations for real-world implementations. Finally, an illustrative use case is presented, where a robot performs the folding of a box.

Problem

• Automating box folding sequence extraction for packaging systems
• Ranking folding sequences by feasibility and hardware compatibility
• Enabling robots to fold boxes from initial to final configuration

Innovation

• Extracts and ranks box folding sequences
• Evaluates feasibility and hardware compatibility
• Demonstrates robotic box folding implementation