3D Surface Printhead Path Planning With Reinforcement Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Printing images on complex 3D surfaces, particularly curved surfaces, is challenging due to the complexity of planning a control path for robotic printheads, which is exacerbated by the numerous degrees of freedom involved in robotic movement.
Innovation Solution
A reinforcement learning method is employed to generate simulated control paths for printhead movement, using a training system that includes a processor to analyze 3D models, sensor data, and reward values to optimize printhead positioning, coverage, and speed, with a recursive Monte Carlo analysis to refine the path generation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If robotic printing systems are used to print on complex 3D surfaces, then productivity is improved, but device complexity increases due to numerous degrees of freedom in robotic movement
Solution Approach 1:
The system performs preliminary action by pre-calculating and storing optimal control paths for various surface geometries in a database. During actual printing operations, the appropriate pre-computed path is retrieved and executed, eliminating the need for complex real-time control path planning while maintaining high productivity
Solution Approach 2:
An intermediary computational layer is introduced between the robotic system and the surface geometry. This intermediary pre-processes surface data, generates optimal paths offline, and stores them for rapid retrieval, thereby decoupling the complexity of control path planning from the actual printing operation
2Manufacturing precision
If control path planning is optimized for precision, then manufacturing precision is improved, but loss of time increases due to complex calculations
Solution Approach 1:
Optimal control paths are pre-calculated and stored in advance for different surface types. When printing, the system simply retrieves the pre-computed path rather than calculating it in real-time, thereby maintaining high positioning accuracy without incurring time penalties during actual production
Solution Approach 2:
Instead of repeatedly performing complex calculations, the system creates copies of optimal control paths for various surface geometries and stores them in a database. These copied paths can be quickly retrieved and applied during printing operations, eliminating time-consuming real-time computations while preserving precision
Data Source
AI summary
Disclosed herein is a livery printing system and a method of generating a control path. The system includes a training system having a processor and a memory with code configured to cause the processor to receive a 3D digital model associated with an object; generate simulated control paths, based on the 3D digital model, for actuators of a printing device with printheads, determine a reward value for each one of the simulated control paths based on a simulated physical value, a simulated surface coverage value, or a simulated printing speed value. A value of one simulated control path variable of any of the simulated control paths is different than the value of the simulated control path variable of another simulated control path. One of the simulated control paths is selected based on a comparison between the reward values determined for the simulated control paths.