Revolutionizing clean energy labs: Robotic imitation learning for efficient fabrication AI-powered electrical units assembly platform

The energy industry, now in an era of digitization driven by computational design, is gradually moving towards automating the entire process from computational prediction to device assembly, aiming to minimize the reliance on time-consuming, manual trial-and-error validation. In this study, guided b...

Full description

Saved in:
Bibliographic Details
Main Authors: Xi Xu, Yijun Gu, Tianyi Zhang, Jiwen Yu, Stephen Skinner
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Energy and AI
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666546825000497
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849324097846116352
author Xi Xu
Yijun Gu
Tianyi Zhang
Jiwen Yu
Stephen Skinner
author_facet Xi Xu
Yijun Gu
Tianyi Zhang
Jiwen Yu
Stephen Skinner
author_sort Xi Xu
collection DOAJ
description The energy industry, now in an era of digitization driven by computational design, is gradually moving towards automating the entire process from computational prediction to device assembly, aiming to minimize the reliance on time-consuming, manual trial-and-error validation. In this study, guided by computational density functional theory (DFT) predictions, a humanoid robotic arm, based on artificial intelligence (AI), was creatively utilized to assemble clean energy devices, solid oxide fuel cells (SOFCs). The material (LBSF) was DFT-predicted to have high oxygen reduction reactions (ORRs) ability, suitable for the cathode in SOFCs compared to the conventional (LSF). The material was made into ink then passed to the assembly platform with AI-driven robotics. AI-driven robotics was employed with an imitation learning method to effectively learn skills directly from human demonstrations, thereby alleviating researchers from labor-intensive tasks. We demonstrate our approach for autonomous SOFCs fabrication. For easy platform usage in the future, Large Language Models (LLMs) were incorporated to understand human commands. Visual information was captured by an RGBD camera to identify and locate the cathode painting spot. An imitation learning framework was then applied to learn the painting path from human operations and can be generalized to different conditions. The auto-fabricated single cells with the DFT-predicted LBSF cathode were tested and achieved a power density of 966 mW/cm2 at 700 °C, more than double the performance of LSF. By integrating computational design with an AI-driven assembly platform, this study marks an initial step towards an AI-driven material lab, exponentially accelerating material design in the near future. The platform can also help disabled researchers achieve their ideas through the behavior cloning approach.
format Article
id doaj-art-ea68b7f1fa154d91884fbb7f2e2fd38a
institution Kabale University
issn 2666-5468
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Energy and AI
spelling doaj-art-ea68b7f1fa154d91884fbb7f2e2fd38a2025-08-20T03:48:47ZengElsevierEnergy and AI2666-54682025-09-012110051710.1016/j.egyai.2025.100517Revolutionizing clean energy labs: Robotic imitation learning for efficient fabrication AI-powered electrical units assembly platformXi Xu0Yijun Gu1Tianyi Zhang2Jiwen Yu3Stephen Skinner4Department of Materials, Imperial College London, Exhibition Road, London, SW7 2AZ, UKDepartment of Electrical and Electronic Engineering, Imperial College London, Exhibition Road, London, SW7 2AZ, UKDepartment of Materials, Imperial College London, Exhibition Road, London, SW7 2AZ, UKDepartment of Materials, Imperial College London, Exhibition Road, London, SW7 2AZ, UKDepartment of Materials, Imperial College London, Exhibition Road, London, SW7 2AZ, UK; Corresponding author.The energy industry, now in an era of digitization driven by computational design, is gradually moving towards automating the entire process from computational prediction to device assembly, aiming to minimize the reliance on time-consuming, manual trial-and-error validation. In this study, guided by computational density functional theory (DFT) predictions, a humanoid robotic arm, based on artificial intelligence (AI), was creatively utilized to assemble clean energy devices, solid oxide fuel cells (SOFCs). The material (LBSF) was DFT-predicted to have high oxygen reduction reactions (ORRs) ability, suitable for the cathode in SOFCs compared to the conventional (LSF). The material was made into ink then passed to the assembly platform with AI-driven robotics. AI-driven robotics was employed with an imitation learning method to effectively learn skills directly from human demonstrations, thereby alleviating researchers from labor-intensive tasks. We demonstrate our approach for autonomous SOFCs fabrication. For easy platform usage in the future, Large Language Models (LLMs) were incorporated to understand human commands. Visual information was captured by an RGBD camera to identify and locate the cathode painting spot. An imitation learning framework was then applied to learn the painting path from human operations and can be generalized to different conditions. The auto-fabricated single cells with the DFT-predicted LBSF cathode were tested and achieved a power density of 966 mW/cm2 at 700 °C, more than double the performance of LSF. By integrating computational design with an AI-driven assembly platform, this study marks an initial step towards an AI-driven material lab, exponentially accelerating material design in the near future. The platform can also help disabled researchers achieve their ideas through the behavior cloning approach.http://www.sciencedirect.com/science/article/pii/S2666546825000497Solid oxide fuel cells (SOFCs)AI-driven assembly platformDensity functional theory (DFT)Behavior cloning approachLarge language models (LLMs)
spellingShingle Xi Xu
Yijun Gu
Tianyi Zhang
Jiwen Yu
Stephen Skinner
Revolutionizing clean energy labs: Robotic imitation learning for efficient fabrication AI-powered electrical units assembly platform
Energy and AI
Solid oxide fuel cells (SOFCs)
AI-driven assembly platform
Density functional theory (DFT)
Behavior cloning approach
Large language models (LLMs)
title Revolutionizing clean energy labs: Robotic imitation learning for efficient fabrication AI-powered electrical units assembly platform
title_full Revolutionizing clean energy labs: Robotic imitation learning for efficient fabrication AI-powered electrical units assembly platform
title_fullStr Revolutionizing clean energy labs: Robotic imitation learning for efficient fabrication AI-powered electrical units assembly platform
title_full_unstemmed Revolutionizing clean energy labs: Robotic imitation learning for efficient fabrication AI-powered electrical units assembly platform
title_short Revolutionizing clean energy labs: Robotic imitation learning for efficient fabrication AI-powered electrical units assembly platform
title_sort revolutionizing clean energy labs robotic imitation learning for efficient fabrication ai powered electrical units assembly platform
topic Solid oxide fuel cells (SOFCs)
AI-driven assembly platform
Density functional theory (DFT)
Behavior cloning approach
Large language models (LLMs)
url http://www.sciencedirect.com/science/article/pii/S2666546825000497
work_keys_str_mv AT xixu revolutionizingcleanenergylabsroboticimitationlearningforefficientfabricationaipoweredelectricalunitsassemblyplatform
AT yijungu revolutionizingcleanenergylabsroboticimitationlearningforefficientfabricationaipoweredelectricalunitsassemblyplatform
AT tianyizhang revolutionizingcleanenergylabsroboticimitationlearningforefficientfabricationaipoweredelectricalunitsassemblyplatform
AT jiwenyu revolutionizingcleanenergylabsroboticimitationlearningforefficientfabricationaipoweredelectricalunitsassemblyplatform
AT stephenskinner revolutionizingcleanenergylabsroboticimitationlearningforefficientfabricationaipoweredelectricalunitsassemblyplatform