Young Scientist Award

Mercedes Premalatha Ramesh — Senior Research Engineer, Air Traffic Management Research Institute (ATMRI), and Part-time PhD Researcher in Mechanical and Aerospace Engineering, Nanyang Technological University (NTU), Singapore.

Mercedes Premalatha Ramesh is a Senior Research Engineer at NTU’s Air Traffic Management Research Institute and a part-time PhD researcher in Mechanical and Aerospace Engineering. Her academic and professional experience spans aviation, robotics, intelligent manufacturing and semiconductor systems, with research focused on human-AI collaboration, multi-agent reinforcement learning and autonomous systems for safety-critical applications.[1]

Abstract

Mercedes Premalatha Ramesh’s research is situated at the intersection of artificial intelligence, autonomous systems, human factors and safety-critical aviation. Her work addresses multi-agent reinforcement learning, dynamic airspace sectorization, adaptive air traffic control automation, workload-aware decision support and collision-constrained robot swarms. Her research portfolio also includes low-resource language AI, illustrating an interdisciplinary approach to intelligent systems that combines computational methods with operational and human-centred requirements.[1]

Keywords

Computer Science; Artificial Intelligence; Multi-Agent Systems; Reinforcement Learning; Robot Perception; Swarm Robotics; Air Traffic Optimisation; Human-AI Collaboration; Autonomous Systems; Large Language Models.

Introduction

Mercedes Premalatha Ramesh’s academic profile combines engineering education with applied research in aviation and intelligent autonomous systems. She holds a Bachelor of Engineering in Electronics and Communication Engineering and a Master of Technology in Intelligent Systems from the National University of Singapore. Her professional R&D experience includes work associated with A*STAR ARTC, ST Engineering, Micron, Hindustan Aeronautics Limited and ROS-Industrial, providing an interdisciplinary foundation for research involving robotics, industrial systems and artificial intelligence.

At NTU ATMRI, her current research addresses the interaction between human operators and increasingly autonomous decision-support systems. This focus is particularly relevant to air traffic management, where AI-based optimisation must operate within safety, workload, interpretability and human-oversight constraints. Her research therefore considers both algorithmic performance and the conditions under which intelligent systems can be responsibly integrated into operational environments.

Research Profile

The research profile comprises six principal streams: AIR-LION and multi-sector planning for air traffic management simulation; multi-agent reinforcement learning for dynamic airspace sectorisation; adaptive automation and AI-assisted air traffic control coordination; workload-aware human-AI decision support; collision-constrained and shared-control robot swarms; and low-resource Tamil-Malay machine translation. These streams connect reinforcement learning, autonomous control, human factors and language technologies across different safety- and resource-constrained settings.

Her consultancy and industry-oriented R&D experience further connects academic research with practical engineering requirements. Work across aviation, robotics, intelligent manufacturing and semiconductor environments has contributed to a research orientation centred on deployability, system constraints and interdisciplinary collaboration.[1]

Research Contributions

Mercedes Premalatha Ramesh develops research approaches for trustworthy human-AI systems in safety-critical environments. Her contributions combine multi-agent reinforcement learning, human-factors evidence and autonomous-system control to address coordination and decision-support challenges while retaining human oversight. Areas of contribution include dynamic airspace sectorisation, adaptive air traffic control automation, workload-aware decision support and collision-constrained swarm control.[1]

Her interdisciplinary work additionally extends to low-resource language AI, including computational analysis and translation-support systems for Tamil and related language contexts. The resulting research portfolio links simulation and algorithm development with operational constraints and human-centred evaluation, providing a foundation for further investigation of explainable and responsible autonomy.

Publications

Available publication records indicate more than nine peer-reviewed indexed outputs during 2024–2026, covering multi-agent reinforcement learning, air traffic control automation, human-AI decision support, swarm robotics, robot navigation and low-resource language AI. The publication record includes work presented through IEEE venues and Springer-associated research, together with a 2026 article in Education Sciences. Bibliographic records and author profiles provide the principal basis for assessing the documented publication portfolio. [1] [3] [4] [5]

Representative research includes a 2024 IEEE ISIE contribution on quantitative analysis of robot navigation under rain conditions, a 2026 Education Sciences study examining stream-aware vocabulary demands in Singapore secondary Tamil textbooks, and a 2026 Human-Computer Interaction conference contribution addressing linguistic ambiguity in low-resource translation-support systems. [3] [4] [5]

Research Impact

The documented research profile demonstrates an interdisciplinary trajectory spanning artificial intelligence, aviation, robotics and language technologies. Its potential research impact lies particularly in connecting algorithmic approaches such as reinforcement learning with human-centred and safety-oriented requirements. Applications in dynamic airspace management, autonomous coordination and decision support are relevant to the development of intelligent systems that must operate under uncertainty while maintaining human supervision.

The publication record also demonstrates cross-domain collaboration, with research extending from autonomous robot navigation to educational language technologies. The available scholarly metrics report 19 documents, 5 citations and an h-index of 1 in the supplied profile data, while individual publications provide additional evidence of research activity and interdisciplinary engagement. [1] [2]

Award Suitability

For consideration under the Young Scientist Award category, Mercedes Premalatha Ramesh’s profile presents a combination of early-career research activity, multidisciplinary engineering experience and work in emerging AI applications. Particularly relevant elements include research on multi-agent reinforcement learning, human-AI collaboration, autonomous systems and safety-critical air traffic management, together with peer-reviewed scholarly outputs and industry-linked R&D experience.

The suitability assessment should be based on independently verifiable evidence, including indexed publications, documented research projects, institutional affiliation, scholarly profiles and supporting certificates. Professional memberships should be listed only where current membership can be documented. NTU identification and relevant academic or professional certificates may be supplied as supporting evidence during the award-submission process.[1] [2]

Conclusion

Mercedes Premalatha Ramesh’s research profile reflects an interdisciplinary focus on artificial intelligence, multi-agent learning, human-AI collaboration and autonomous systems. Her work connects aviation and robotics research with human-centred considerations and extends into low-resource language AI. The combination of applied R&D experience, peer-reviewed publications and research activity in safety-critical intelligent systems provides a documented basis for consideration within an early-career scientific recognition framework.[1]

External Links

• Google Scholar Profile
• Scopus Author Profile
• ORCID Profile
• Top Teachers Awards

References

1. Google Scholar. (n.d.). Mercedes Premalatha Ramesh — Google Scholar author profile. https://scholar.google.com/citations?user=_TNjmuMAAAAJ&hl=en
2. Elsevier. (n.d.). Scopus author details: Mercedes Premalatha Ramesh, Author ID 59234522100. Scopus. https://www.scopus.com/pages/authors/59234522100
3. Ramu, U., Ramesh, M. P., Paranthaman, K., Khan, S. G. S., & Fern, T. C. (2024). Generalized framework for quantitative analysis of robot navigation under rain conditions. 2024 IEEE 33rd International Symposium on Industrial Electronics (ISIE), 1–7. https://doi.org/10.1109/ISIE54533.2024.10595805
4. Pal Thamburaj, K., & Ramesh, M. P. (2026). Stream-aware vocabulary demands in Singapore secondary Tamil textbooks: A morphology-and multiword-unit-sensitive corpus analysis, with a textbook-faithful GenAI item benchmark. Education Sciences, 16(8), 1270. https://doi.org/10.3390/educsci16081270
5. Pal Thamburaj, K., & Ramesh, M. P. (2026). Deciphering divergence: Visualizing linguistic ambiguity in low-resource translation support systems. International Conference on Human-Computer Interaction, 581–591. https://link.springer.com/chapter/10.1007/978-3-032-30826-9_60