An Online Learning Approach to Model Predictive Control
This work provides a new theoretical foundation for MPC that could improve algorithm design for control tasks in robotics and autonomous systems, though it appears incremental as it builds on existing online learning methods.
The paper tackles the problem of designing model predictive control (MPC) algorithms by connecting MPC to online learning, proposing a new algorithm called DMD-MPC based on dynamic mirror descent, and demonstrates its flexibility in simulated and real-world tasks like cartpole and aggressive driving.
Model predictive control (MPC) is a powerful technique for solving dynamic control tasks. In this paper, we show that there exists a close connection between MPC and online learning, an abstract theoretical framework for analyzing online decision making in the optimization literature. This new perspective provides a foundation for leveraging powerful online learning algorithms to design MPC algorithms. Specifically, we propose a new algorithm based on dynamic mirror descent (DMD), an online learning algorithm that is designed for non-stationary setups. Our algorithm, Dynamic Mirror Descent Model Predictive Control (DMD-MPC), represents a general family of MPC algorithms that includes many existing techniques as special instances. DMD-MPC also provides a fresh perspective on previous heuristics used in MPC and suggests a principled way to design new MPC algorithms. In the experimental section of this paper, we demonstrate the flexibility of DMD-MPC, presenting a set of new MPC algorithms on a simple simulated cartpole and a simulated and real-world aggressive driving task. Videos of the real-world experiments can be found at https://youtu.be/vZST3v0_S9w and https://youtu.be/MhuqiHo2t98.