Skip to content
View FarzanehTatari's full-sized avatar

Block or report FarzanehTatari

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
FarzanehTatari/README.md

Hi, I'm Farzaneh πŸ‘‹

AI-driven Control Engineer & Researcher (Ph.D.) working at the intersection of machine learning, reinforcement learning, and control theory β€” applied to automotive systems, robotics, and electrified powertrains.

πŸŽ“ Google Scholar Β· πŸ’Ό LinkedIn Β· βœ‰οΈ fa_tatari@yahoo.com


Research interests

  • Reinforcement learning and online learning for control under uncertainty
  • System identification of nonlinear dynamics β€” fixed-time, finite-time, concurrent learning
  • Data-driven modeling of electrified powertrains and electric motors
  • Distributed and adaptive control of multi-agent / networked systems

Selected publications & code

  • A Hybrid End-to-End and Modular Control Architecture Toward Safe Vehicle Lateral Control β€” arXiv preprint, 2026. πŸ“„ arXiv Β· πŸ’» Code Blends a Soft Actor-Critic policy with constrained MPC for CAV lateral control through a single monotone coefficient.

  • Deep Learning-Based Rotor Temperature Estimation for Rare-Earth-Free Motors β€” NDIA GVSETS, 2026. πŸ“„ Paper Β· πŸ’» Related Code GRU and LSTM virtual sensors for rotor temperature estimation in a 190 kW EESM. Open-source implementation on public PMSM data.

  • Online Learning of Noisy Functions via a Data-Regularized Gradient-Descent Approach β€” IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2025. πŸ“„ Paper Online learning under measurement noise, with robotics and vehicle dynamics case studies.

  • Discrete-Time Nonlinear System Identification via Fixed-Time Concurrent Learning β€” IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2024. Identification of nonlinear discrete-time systems with provable fixed-time convergence.

  • Data-driven Thermal Modeling for Electrically Excited Synchronous Motors β€” A Supervised Machine Learning Approach β€” IEEE Transportation Electrification Conference & Expo (ITEC), 2024. πŸ“„ Paper Β· πŸ’» Related Code Supervised ML for sensorless thermal estimation in EV traction motors.

  • Fixed-Time System Identification Using Concurrent Learning β€” IEEE Transactions on Neural Networks and Learning Systems, 2021. Concurrent-learning-based system identification with fixed-time convergence guarantees.

For the full publication list (30+ papers), see my Google Scholar profile.


Currently

Senior Control & AI Engineer at Drive System Design, working on ML-driven control and diagnostics for electrified powertrains. Outside of work, I'm building open-source Python implementations of my published methods β€” repos coming soon.


Reach out

Always open to research collaboration in AI for control, ML for automotive, and reinforcement learning for real-world systems.

Pinned Loading

  1. motor-thermal-deeplearning motor-thermal-deeplearning Public

    LSTM, GRU, and MLP virtual sensors for motor temperature estimation on the public Paderborn PMSM dataset. Python, PyTorch.

    Python

  2. hybrid-sac-mpc-lateral-control hybrid-sac-mpc-lateral-control Public

    Safe vehicle lateral control combining Soft Actor-Critic with constrained MPC. Python, PyTorch, stable-baselines3, OSQP. arXiv:2608.17258

    Python