Mingyuan Tao

About

Mingyuan Tao is a researcher at the forefront of autonomous vehicle control, specializing in the integration of reinforcement learning (RL) with model predictive control (MPC). His work bridges the gap between data-driven decision-making and classical control theory, with a focus on enhancing the safety and performance of self-driving systems. In his most cited work, "RL-MPC: Reinforcement Learning Aided Model Predictive Controller for Autonomous Vehicle Lateral Control" (2024), Tao introduces a novel nonlinear MPC framework that leverages a pre-trained RL model to improve lateral control tasks. This hybrid approach demonstrates how RL can augment traditional controllers to handle complex, real-world driving scenarios more effectively. Though early in his career, Tao’s contributions are already gaining traction, with his work cited by peers exploring advanced vehicle dynamics and intelligent control. His research holds promise for making autonomous driving more robust and adaptive, particularly in challenging environments. As the field evolves, Tao’s innovative fusion of RL and MPC positions him as a rising voice in next-generation vehicle autonomy.

Research Focus

Key Achievements

Top Papers

1. 1
   RL-MPC: Reinforcement Learning Aided Model Predictive Controller for Autonomous Vehicle Lateral Control

   2 citations · 2024

Key Collaborators

Contact & Links