Learning-Aided Warmstart of Model Predictive Control in Uncertain Fast-Changing Traffic
This addresses safety and convergence issues for autonomous vehicles in dynamic environments, representing an incremental improvement over existing warmstart methods.
The paper tackled the problem of Model Predictive Control (MPC) getting stuck in local minima and failing in fast-changing, uncertain traffic by proposing a learning-aided warmstart framework that uses a neural network predictor and sampling to generate multiple trajectory proposals, resulting in improved initial guesses validated through Monte Carlo simulations.
Model Predictive Control lacks the ability to escape local minima in nonconvex problems. Furthermore, in fast-changing, uncertain environments, the conventional warmstart, using the optimal trajectory from the last timestep, often falls short of providing an adequately close initial guess for the current optimal trajectory. This can potentially result in convergence failures and safety issues. Therefore, this paper proposes a framework for learning-aided warmstarts of Model Predictive Control algorithms. Our method leverages a neural network based multimodal predictor to generate multiple trajectory proposals for the autonomous vehicle, which are further refined by a sampling-based technique. This combined approach enables us to identify multiple distinct local minima and provide an improved initial guess. We validate our approach with Monte Carlo simulations of traffic scenarios.