Summary
Mahdis Rabbani is a PhD candidate and mentor in Robotics and Control at UC Davis with eight years of experience developing interaction-aware decision-making and path-planning methods for autonomous and multi-agent systems. Her work weaves game theory, model predictive control, and data-driven modeling to enable agents that predict and respond to others in real time, and she has demonstrated this end-to-end—from fast Nash-seeking algorithms and Koopman-based identification to CARLA-integrated simulation and Julia-based nonlinear MPC prototypes. She leads the CORE Lab’s Vehicle Trajectory Prediction team, guiding students on deployable deep-learning pipelines and translating research into functional autonomous-driving components. Hands-on roots in sensor design, embedded control, and prototype instrumentation inform her practical approach to control and autonomy research. Notably, she pairs rigorous analytical skills with production-minded implementation, building both the math and the simulation/validation stacks that make interaction-aware autonomy work in realistic settings.
8 years of coding experience
Doctor of Philosophy - PhD Mechanical Engineering, Doctor of Philosophy - PhD Mechanical Engineering at University of California, Davis
Bachelor's degree Mechanical Engineering, Bachelor's degree Mechanical Engineering at University of Tehran