Learning-Enabled Collaborative Autonomy for Networked CPS

Team

• Vignesh Narayanan, UofSC
• Sarangapani Jagannathan, MST-Rolla

Overview

The primary objective of this research is to advance methodologies for modeling, learning, and controlling networked cyber-physical systems (CPS). In particular, the project emphasizes integrating human users or operators into the feedback loop of CPS by leveraging both data-driven and knowledge-based approaches. The research is organized around three key thrust areas:

• modeling the dynamics of human-robot collaboration;
• addressing scalability and data-related challenges in human-in-the-loop CPS using learning-based methods; and
• designing robust adaptation and control strategies to safely and effectively guide these collaborative systems toward desired outcomes.

Selected Products

• Kuan, Y.H., Narayanan, V. and Li, J.S., 2025. Iterative Reservoir Computing Networks for Reconstructing Irregular Time Series. IEEE Transactions on Neural Networks and Learning Systems.
• Ganie, I. and Jagannathan, S., 2025. Online learning-driven human intent estimation and control for human-robot interaction. Proceedings of the American Control Conference. IEEE.
• Muppasani, B.C., Nag, P., Narayanan, V., Srivastava, B. and Huhns, M., 2024. Towards effective planning strategies for dynamic opinion networks. Advances in Neural Information Processing Systems.