Vehicle Control Systems

Vehicle control systems 

Holistic vehicle control

The group's main goal is to make vehicle controllers as effective and universal as possible. Doing so would reduce development and tuning times for new vehicles. This would have a major impact in the automotive industry as currently companies spend a huge amount of time and money to develop controllers for new vehicles.

Learning MPC

The integration of machine learning with MPC in the form of learning a prediction model, controller design, or even the control law directly, provides the controller the ability of learning from previous valuable vehicle data/experience resulting in improved vehicle control systems.

Agent-based MPC

In this project, we intend to further extend the modularity and scalability of vehicular control systems by introducing agent-based model predictive controllers (AMPC). Different agent clustering schemes are analyzed for modular and production vehicle platforms, and a general decoupling technique for vehicle dynamics model is then introduced, which decomposes the original problem into multi-agent formulations.