Mixed-Case Robotic Palletizing for Stable Multi-Pallet Stacking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for stacking dissimilar items on pallets are inefficient and unstable, often requiring manual intervention and struggling with the variety and mix of items, leading to potential collapse or damage.
Innovation Solution
A robotic system equipped with 3D cameras, force sensors, and sensor arrays programmatically determines item attributes and uses grasp strategies from a dynamic library to stack and unstack heterogeneous items, incorporating human intervention when needed and ensuring stability through machine learning and safety protocols.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual stacking is used by human workers, then items can be selected and stacked based on judgment and intuition to achieve stability, but labor intensity is high and efficiency is low
Solution Approach 1:
The patent replaces manual human stacking with an automated robotic system that uses computer vision, sensors, and control algorithms to detect item attributes, determine optimal stacking positions, and execute placement. This substitution maintains stacking reliability through intelligent algorithms while dramatically improving productivity by eliminating manual labor constraints.
Solution Approach 2:
The system enables items to be automatically selected and stacked based on their inherent attributes (weight, size, shape) detected by sensors. The robotic system autonomously evaluates item characteristics and makes stacking decisions without human intervention, achieving both high reliability through objective measurement and high productivity through automation.
2Productivity
If items are stacked in arrival order without selection, then stacking process is simple and fast, but pallet stability is compromised leading to potential collapse
Solution Approach 1:
The system performs preliminary detection and evaluation of item attributes (weight, dimensions, shape) using computer vision and sensors before stacking. Based on this advance information, the control system pre-determines the optimal stacking sequence and positions that ensure stability, then executes the stacking in that optimized order rather than arrival order.
Solution Approach 2:
The system continuously monitors item attributes through sensors and computer vision, feeds this information to the control algorithm, and adjusts the stacking plan in real-time. The feedback loop ensures that each item is placed in the optimal position to maintain pallet stability while preserving high stacking speed through automated decision-making.
3Productivity
If robotic system is used to automate stacking, then productivity increases and human labor is reduced, but system complexity increases due to variety of items and coordination requirements
Solution Approach 1:
The patent employs a universal robotic system with multi-functional capabilities: computer vision for detection, multiple sensors for attribute measurement, adaptive grippers for different item types, and intelligent control algorithms. This universal system can handle diverse items (packages, boxes, containers of various sizes and weights) with a single integrated platform, managing complexity through standardization while maintaining high productivity.
Solution Approach 2:
The system segments the complex stacking task into distinct functional modules: item detection by computer vision, attribute measurement by sensors, decision-making by control algorithms, and physical manipulation by robotic manipulators. This modular segmentation manages overall system complexity by making each component specialized and interchangeable while maintaining high integrated productivity.
4Ease of manufacture
If heavy and large items are placed on top of lighter items, then stacking is simpler, but pallet stability is compromised and items may be damaged
Solution Approach 1:
The system dynamically changes the stacking parameters (sequence, position, orientation) based on real-time detection of item attributes such as weight, size, and fragility. The control algorithm uses these parameter changes to determine the optimal stacking configuration that ensures item safety while maintaining simplicity through automated decision-making rather than complex manual assessment.
Data Source
AI summary
A robotic system is disclosed. The system includes a communication interface, and one or more processors coupled to the communication interface and configured to: generate based at least in part on the received data a plan to stack the items on or in the destination location. For each item, the generating the plan includes determining the destination location based at least in part on a characteristic associated with the item, and at least one of (i) a characteristic of a platform or receptacle on which one or more items are to be stacked, and (ii) an existing stack of one or more items on the platform or receptacle. The destination location is determined from among a plurality of zones in which platforms or receptacles are disposed, and each of the plurality of zones are within a range of a robotic arm. A robotic arm is controlled to implement the plan.