3D Pallet Cell Planning for Stable Mixed-Item Palletizing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current palletization and depalletization processes are often manual, time-consuming, and inefficient, particularly for mixed item loads with varying shapes and sizes, lacking stability considerations and flexibility for non-rectangular items.
Innovation Solution
A system and method using machine learning models, specifically reinforcement learning, to determine optimal three-dimensional placement and removal locations for items on a pallet by generating three-dimensional pallet and item cells, considering item characteristics and stability factors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual palletization is used, then item stability and damage prevention are improved, but time consumption and labor efficiency worsen
Solution Approach 1:
The patent replaces manual mechanical placement operations with an automated robotic system controlled by a placement location determination system. The system uses machine learning models to automatically calculate optimal placement locations and generate control signals for robotic manipulators, eliminating manual labor while maintaining stability through computational planning and simulation.
Solution Approach 2:
The system performs self-optimization by automatically determining placement locations based on item characteristics, pallet configuration, and stability constraints. The machine learning model continuously learns from placement outcomes to improve future placement decisions, enabling the system to autonomously optimize its own performance without human intervention.
2Productivity
If automated palletization systems are implemented, then productivity is improved, but device complexity and control difficulty worsen
Solution Approach 1:
The patent divides the complex palletization task into discrete three-dimensional placement cells that segment the pallet surface. Each cell is independently evaluated for suitability, and the system processes items one at a time through standardized placement decisions. This segmentation transforms a complex continuous optimization problem into a manageable discrete decision-making process.
Solution Approach 2:
The patent introduces a machine learning-based placement location determination system as an intermediary between the robotic manipulator and the palletization task. This intermediary layer processes item characteristics, evaluates placement options, and generates control signals, simplifying the overall system architecture by centralizing the decision-making logic in a dedicated computational module.
3Adaptability or versatility
If manual placement is used, then adaptability to item characteristics is improved, but time consumption worsens
Solution Approach 1:
The patent performs preliminary computation by pre-calculating optimal placement locations and generating detailed placement sequences before physical placement occurs. The system simulates placement scenarios and determines the most efficient sequence and location for each item based on its characteristics, allowing the robotic system to execute placements rapidly without real-time manual adjustment.
Data Source
AI summary
Method, apparatuses, and computer program products for automatically determining a placement location or removal location for one or more items is disclosed. An example method comprising generating a plurality of three-dimensional pallet cells for a pallet; generating one or more three-dimensional item cells for each item of a plurality of items; determining a placement location comprising one or more three-dimensional pallet cells for one or more items of the plurality of items; and causing one or more indications describing the placement location for the one or more items of the plurality of items.