Robotic Palletizing of Mixed Items Using Sensor-Guided Final Placement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for palletizing and depalletizing heterogeneous items are inefficient and prone to instability due to the variety of item sizes, weights, and types, often requiring human intervention and relying on manual judgment, which can lead to unstable stacks and item damage.
Innovation Solution
A robotic system equipped with 3D cameras, force sensors, and a library of item types and grasp strategies uses programmable algorithms to identify and stack items, adjusting plans dynamically based on sensor data and human feedback to ensure stability and efficient packing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual stacking by human workers is used, then item selection and placement can be done with human judgment, but the process is slow and inconsistent in ensuring stability
Solution Approach 1:
The patent replaces manual human stacking with an automated robotic system that uses computer vision and control algorithms to select and place items. The system captures images of items on the conveyor, processes them to determine optimal stacking sequences, and automatically executes the stacking process, eliminating the need for human judgment while maintaining or improving stability through algorithmic optimization.
Solution Approach 2:
The system enables the palletizing process to be self-regulating by automatically analyzing item characteristics through image processing, determining optimal stacking strategies, and executing placements without human intervention. The control system continuously monitors and adjusts the stacking process based on real-time data from the conveyor and item properties.
2Productivity
If items are stacked in arrival order, then the process is simple and fast, but the palletized set becomes unstable
Solution Approach 1:
The system performs preliminary analysis of all incoming items through image capture and processing before actual stacking begins. It determines the optimal stacking sequence in advance by evaluating item dimensions, weights, and stability characteristics, then prepares the stacking plan before execution, ensuring both speed and stability.
Solution Approach 2:
The stacking strategy dynamically adapts based on real-time item characteristics detected by the image processing system. The control algorithm adjusts the stacking sequence and placement positions dynamically according to the specific properties of each item batch, rather than following a fixed predetermined pattern.
3Productivity
If heavy items are placed on top during manual stacking, then the process is faster, but the pallet becomes unstable and items may be damaged
Solution Approach 1:
The system incorporates feedback loops where image processing continuously monitors item characteristics, the control system analyzes stability implications of proposed placements, and adjustments are made in real-time. The system evaluates the stability impact of each potential placement decision and selects sequences that prevent instability and damage while maintaining efficient stacking speed.
4Productivity
If robotic automation is implemented, then productivity increases, but the system becomes more complex to program and adapt to various item types
Solution Approach 1:
The system manages complexity by parameterizing the stacking logic around key item characteristics such as dimension thresholds, weight categories, and stability coefficients. The image processing system extracts these parameters automatically, and the control algorithm uses them to determine stacking sequences, allowing the system to adapt to different item types through parameter variations rather than requiring complex reprogramming.
Data Source
AI summary
Techniques are disclosed to use a robotic arm to palletize or depalletize diverse items. In various embodiments, data associated with a plurality of items to be stacked on or in a destination location is received. A plan to stack the items on or in the destination location is generated based at least in part on the received data. The plan is implemented at least in part by controlling a robotic arm of the robot to pick up the items and stack them on or in the receptacle according to the plan, including by for each item: using one or more first order sensors to move the item to a first approximation of a destination position for that item at the destination location; and using one or more second order sensors to snug the item into a final position.