Autonomous platform for solution processing of electronic polymers

Area of Science:

• Materials Science
• Artificial Intelligence
• Polymer Chemistry

Background:

• Processing electronic polymers into thin films with desired properties is critical for electronics and energy research.
• Current methods face challenges in efficiently achieving specific solid-state properties.

Purpose of the Study:

• To develop an AI-driven automated laboratory (Polybot) for autonomous exploration of processing pathways.
• To achieve high-conductivity, low-defect electronic polymer films through automated optimization.

Main Methods:

• Utilized importance-guided Bayesian optimization to navigate a 7-dimensional processing space.
• Implemented an automated workflow with algorithms to explore search space, mitigate bias, and ensure data repeatability.
• Employed concurrent optimization for multiple objectives with statistical precision.

Main Results:

• Generated scale-up fabrication recipes for transparent conductive thin films.
• Achieved an average conductivity exceeding 4500 S/cm.
• Identified key design factors through feature importance analysis and morphological characterizations.

Conclusions:

• Polybot demonstrates effective AI-driven automation for electronic polymer film manufacturing.
• This approach significantly advances material science by optimizing processing for enhanced material properties.
• Highlights the potential of AI in transforming the production of advanced electronic materials.