Researchers at the Indian Institute of Technology Delhi have successfully transitioned artificial intelligence from computer screens into actual laboratories. In a groundbreaking study published in Nature Communications, the team demonstrated that an AI system can independently conduct complex scientific experiments, analyze results, and make decisions in real time.
This innovative research, conducted in collaboration with institutions from Denmark and Germany, introduces AILA—short for Artificially Intelligent Lab Assistant. Unlike previous AI tools primarily focused on data analysis or writing assistance, AILA operates directly with laboratory instruments, executing experiments much like a seasoned scientist would.
The focus of the research is the Atomic Force Microscope (AFM), a sophisticated instrument used to study materials at the nanoscale. Due to its sensitivity and complexity, mastering the AFM typically requires years of training. However, the IIT Delhi team showcased AILA’s capability to control the microscope, make real-time adjustments, respond to feedback, and interpret data autonomously.
Indrajeet Mandal, the first author of the study and a PhD scholar at IIT Delhi, remarked that the impact of AILA is already apparent in day-to-day research operations. Tasks that once took a full day can now be accomplished in mere minutes. The process of optimizing microscope settings, which previously demanded constant human oversight, can now be completed by the AI system within 7 to 10 minutes.
Professor N M Anoop Krishnan, a supervisor on the project, explained the significance of this shift in straightforward terms. “Until now, AI could assist scientists in explaining science. With AILA, AI is now doing science.” The AI system is capable of designing experiments, running them on real machines, and analyzing the results without any human intervention.
Professor Nitya Nand Gosvami noted that this development represents a significant evolution in experimental research. Mastery of AFM operation requires extensive knowledge of physics, surface interactions, and control systems. AILA’s autonomous functioning in these areas indicates the onset of a new era in laboratory automation.
However, the study also sheds light on potential limitations and risks associated with AI in laboratory settings. Researchers found that AI models proficient in answering scientific questions do not always perform effectively in real-world experiments, which often require quick judgment and adaptability. Safety concerns were also raised; in some instances, the AI deviated from its instructions, underscoring the necessity for robust safeguards to prevent potential damage to equipment.
This project brought together researchers from IIT Delhi, Aalborg University, Leibniz Institute of Photonic Technology, and the University of Jena. The research aligns with India’s commitment to fostering AI-led initiatives, as the government has initiated funding through the Anusandhan National Research Foundation to support the integration of AI in scientific endeavors.
Researchers anticipate that systems like AILA could democratize access to advanced research capabilities. Institutions with limited infrastructure may soon be able to conduct high-end experiments more efficiently. As India aims to bolster its efforts in materials science, energy, and manufacturing, the advent of autonomous lab assistants like AILA could accelerate discoveries and position Indian science at the forefront of global research initiatives.
See also
AI Study Maps 100 Years of Aging Research, Reveals Key Trends and Gaps
Cornell Study Reveals AI Boosts Paper Output by 50% but Undermines Quality
HCLTech Joins Microsoft Discovery to Boost Agentic AI in Scientific Research
AI Race Shifts: Companies Prioritize Adoption Over Model Quality as Spending Scrutinized
