Unmanned Forklift Cup-Feet Pallet Alignment Using LiDAR and BEV
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current pallet stacking technologies are not effectively adapted for cup-feet pallets, which are commonly used in smart factories, limiting the autonomy and efficiency of unmanned forklifts in transferring and stacking these types of pallets.
Innovation Solution
A pallet stacking apparatus equipped with a lidar for 3D point cloud data conversion to 2D bird's-eye view images, utilizing convolutional neural networks for cup position recognition, and a closed-loop control system to adjust the forklift's operation for precise alignment and stacking of cup-feet pallets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If standard pallet recognition technology is used, then standard pallets can be transferred, but cup-feet pallets cannot be recognized or stacked
Solution Approach 1:
The patent replaces traditional mechanical or simple optical recognition systems with a lidar-based 3D point cloud sensing system. The lidar captures precise spatial coordinates of cup-feet pallet structures, enabling the system to recognize and adapt to non-standard pallet geometries that conventional systems cannot detect accurately.
Solution Approach 2:
The system transforms 3D point cloud data from multiple angles into 2D bird's-eye view images through coordinate transformation and projection operations. This parameter transformation allows the application of 2D image processing algorithms to 3D spatial data, enabling cup position recognition through familiar image processing techniques.
2Extent of automation
If manual pallet stacking is used, then cup-feet pallets can be stacked, but automation is reduced
Solution Approach 1:
The system employs closed-loop feedback control where the lidar continuously monitors the positions of cups on both the moving and stationary pallets. The control unit compares actual positions with target positions and dynamically adjusts the forklift's positioning and the moving pallet's orientation to achieve precise alignment, ensuring accurate stacking even under automated operation.
Solution Approach 2:
The system creates a digital replica of the physical cup-feet pallet structure by generating 3D point cloud models from lidar scans. This digital model includes precise coordinates of all cup positions, which serves as a virtual template for planning and executing the stacking operation, enabling the automated system to understand and replicate the desired final configuration.
3Speed
If simple 2D image recognition is used, then processing is faster, but 3D spatial information is lost
Solution Approach 1:
The system projects 3D point cloud data onto a 2D plane by creating bird's-eye view images through coordinate transformation. This dimensionality reduction preserves essential spatial relationships (horizontal and vertical positions of cups) while enabling the use of computationally efficient 2D image processing algorithms, achieving a balance between processing speed and information retention.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables precise recognition and automated transfer and multi-stage stacking of cup-feet pallets, reducing labor costs and enhancing the autonomy of unmanned forklifts in smart factory environments.
Implementation Method 1
a lidar installed in an unmanned forklift and configured to radiate laser light and convert range data reflected from a cup-feet pallet to 3D point cloud data
Data Source
AI summary
An embodiment pallet stacking apparatus includes a lidar installed in an unmanned forklift and configured to radiate laser light and convert range data reflected from a first cup-feet pallet to 3D point cloud data, a bird's eye view (BEV) conversion unit configured to convert the 3D point cloud data to a 2D BEV image, a cup recognition unit configured to perform channel normalization with input data of the 2D BEV image and recognize a cup position through calculation using convolutional neural network, a forklift controller configured to control operation of the unmanned forklift according to a control signal, and a control unit configured to identify a difference between a cup position of the first cup-feet pallet and a cup position of a stationary second cup-feet pallet and apply a control signal for adjustment to a matching position to the forklift controller.