Shivanshu Tripathi

“Hybrid-time PINNs: Discontinuity-Aware Physics-Informed Neural Networks for Learning Hybrid Dynamical Systems” was submitted to IEEE Control Systems Letters (L-CSS) — see the project page.

“Exact Distributed Attitude Alignment on SO(3) for Robot Teams with Conflicting Local Objectives” was submitted to the American Control Conference (ACC).

“VeraGrid-Agent: Tool-Augmented LLMs for Distribution Optimal Power Flow at the Grid Edge” was accepted to IEEE PES Grid Edge — read the preprint.

“Online Optimization with Unknown Time-Varying Parameters using Noisy Gradient Measurements” was accepted to IEEE Control Systems Letters (L-CSS) — read the preprint.

Attended ICHQP in Dresden, Germany, to present our physics-informed synchro-waveform paper.

Our critical review of AI and machine learning methods for data-center load forecasting is out in Energies — read the paper.

Posted two grid-edge papers on arXiv: VeraGrid-Agent, a tool-augmented LLM for distribution optimal power flow, and a spectrogram-based detector for events in continuously recorded IBR waveforms.

Started a graduate research internship at NLR (National Laboratory of the Rockies) in Golden, CO, building foundation models and AI agents for power systems with Dr. Fei Ding.

“Test-Driven Agentic Framework for Reliable Robot Controller” was accepted to ICCAS (International Conference on Control, Automation and Systems) — read the preprint or see the project page.

“Data-Efficient Physics-Informed Learning for Synchro-Waveform Analytics of Grid-Integrated Inverter-Based Resources” was accepted to ICHQP (IEEE International Conference on Harmonics and Quality of Power) — read the preprint.

Presented our NSF-supported work on physics-informed learning at Rutgers University.

Advanced to PhD candidacy after passing the qualifying examination.

Joined PNNL (Pacific Northwest National Laboratory) as a graduate research intern, developing AI agents for power systems with Dr. Kaveri Mahapatra.

“Online Optimization with Unknown Time-Varying Parameters” was published in IEEE Control Systems Letters — read the paper.