I am working on the following problems
1. Robotics applications of artificial intelligence
2. Theoretical developments in scientific machine learning through polynomial chaos theory
3. Theretical developments in safe learning through model predictive control
4. Reinforcement learning from human feedback in large language models
5. Reinforcement learning for control-communication co-design in cyber physical systems

All Publications

Minimum variance constrained estimator by Mishra P. K., Chowdhary G. , Mehta P. G. Automatica - (2022)
Deep Model Predictive Control by Mishra P. K., Gasparino M. V., Velasquez A. E., Chowdhary G. Conference on Robot Learning (CoRL), workshop on Learning to Adapt and Improve in the Real World - (2022)
Reference tracking stochastic model predictive control over unreliable channels and bounded control actions by Mishra P. K., Diwale S. S., Chatterjee D. , Jones C. N. Automatica - (2021)
Stochastic predictive control under intermittent observations and unreliable actions by Mishra P. K., Chatterjee D. , Quevedo D. E. Automatica - (2020)
Sparse and constrained stochastic predictive control for networked systems by Mishra P. K., Chatterjee D. , Quevedo D. E. Automatica - (2018)
Stabilizing stochastic predictive control under Bernoulli dropouts by Mishra P. K., Chatterjee D. , Quevedo D. E. IEEE Transactions on Automatic Control - (2018)
Unmatched Uncertainty Mitigation Through Neural Network Supported Model Predictive Control by Gasparino M. V., Mishra P. K., Chowdhary G. Conference on Decision and Control (CDC) - (2023)
Deep Model Predictive Control With Stability Guarantees by Mishra P.K., Gasparino M.V., Chowdhary G. IEEE Transactions on Automatic Control 70 5460-5467 (2025)
Algorithmic design and implementation considerations of deep MPC by Mishra P. K., Gasparino M. V., Chowdhary G. Indian Control Conference 461-466 (2025)
Learning to Swim Upstream: Koopman-Physics AI for Smart Microswimmer Navigation by Chakraborty P., Mishra P. K., Chakraborty S. International Symposium on AI and Fluid Mechanics - (2026)

Completed Projects

Principal Investigator

IQuaP: Intelligent Quadrupeds for Police Anusandhan National Research Foundation (ANRF)
Safe and robust learning for dynamical systems under uncertainties Sponsored Research and Industrial Consultancy (SRIC)

Co-Principal Investigator

Development of an advanced reliability-based remaining useful life (RUL) estimation framework for multi-component autonomous underwater vehicle (AUV) systems Directorate of Futuristic Technology Management (DFTM), Defence Research and Development Organisation, Ministry of Defence

Alumni members

Ph. D. Students

P. B. Salim

Area of Research: AI + Economics

Ranjan Sarkar

Area of Research: Reinforcement Learning

MS Students

Ahon Bandyopadhyay

Area of Research: Learning based Model Predictive Control