Performance-driven Constrained Optimal Auto-Tuner for MPC
This work addresses the problem of reliable and efficient MPC tuning for control systems like autonomous racing, though it appears incremental as it builds on existing auto-tuning and Bayesian optimization methods.
The paper tackles the challenge of tuning Model Predictive Control (MPC) parameters to maintain performance above a threshold, proposing COAT-MPC, which theoretically ensures high-probability constraint satisfaction and finite-time convergence to optimal performance, and outperforms baselines in simulations and hardware tests, such as reducing constraint violations and cumulative regret in autonomous racing.
A key challenge in tuning Model Predictive Control (MPC) cost function parameters is to ensure that the system performance stays consistently above a certain threshold. To address this challenge, we propose a novel method, COAT-MPC, Constrained Optimal Auto-Tuner for MPC. With every tuning iteration, COAT-MPC gathers performance data and learns by updating its posterior belief. It explores the tuning parameters' domain towards optimistic parameters in a goal-directed fashion, which is key to its sample efficiency. We theoretically analyze COAT-MPC, showing that it satisfies performance constraints with arbitrarily high probability at all times and provably converges to the optimum performance within finite time. Through comprehensive simulations and comparative analyses with a hardware platform, we demonstrate the effectiveness of COAT-MPC in comparison to classical Bayesian Optimization (BO) and other state-of-the-art methods. When applied to autonomous racing, our approach outperforms baselines in terms of constraint violations and cumulative regret over time.