CoVO-MPC：サンプリングベースMPCの理論解析と最適共分散設計
CoVO-MPC: Theoretical Analysis of Sampling-based MPC and Optimal Covariance Design
サンプリングベースMPC（MPPI）の収束性を理論的に解析し、収束速度を最適化する共分散スケジューリングを導入したCoVO-MPCを提案。シミュレーションと実機ドローンの俊敏制御でMPPIを43〜54%上回った。
著者: Zeji Yi, Chaoyi Pan, Guanqi He, Guannan Qu, Guanya Shi
分類: cs.LG, cs.RO
原文アブストラクト
Sampling-based Model Predictive Control (MPC) has been a practical and effective approach in many domains, notably model-based reinforcement learning, thanks to its flexibility and parallelizability. Despite its appealing empirical performance, the theoretical understanding, particularly in terms of convergence analysis and hyperparameter tuning, remains absent. In this paper, we characterize the convergence property of a widely used sampling-based MPC method, Model Predictive Path Integral Control (MPPI). We show that MPPI enjoys at least linear convergence rates when the optimization is quadratic, which covers time-varying LQR systems. We then extend to more general nonlinear systems. Our theoretical analysis directly leads to a novel sampling-based MPC algorithm, CoVariance-Optimal MPC (CoVo-MPC) that optimally schedules the sampling covariance to optimize the convergence rate. Empirically, CoVo-MPC significantly outperforms standard MPPI by 43-54% in both simulations and real-world quadrotor agile control tasks. Videos and Appendices are available at \url{https://lecar-lab.github.io/CoVO-MPC/}.
