Approaches for stochastic nonlinear model predictive control (SNMPC) typically make restrictive assumptions about the system dynamics and rely on approximations to characterize the evolution of the underlying uncertainty distributions. For this reason, they are often unable to capture more complex distributions (e.g., non-Gaussian or multi-modal) and cannot provide accurate guarantees of performance. In this paper, we present a sampling-based SNMPC approach that leverages recently derived sample complexity bounds to certify the performance of a feedback policy without making assumptions about the system dynamics or underlying uncertainty distributions. By parallelizing our approach, we are able to demonstrate real-time receding-horizon SNMPC with statistical safety guarantees in simulation and on hardware using a 1/10th scale rally car and a 24-inch wingspan fixed-wing UAV.

翻译：随机非线性模型预测控制（SNMPC）方法通常对系统动态施加严格的假设，并依赖近似方法来描述潜在不确定性分布的演变。因此，它们往往无法捕捉更复杂的分布（例如非高斯分布或多模态分布），也无法提供准确的性能保证。本文提出一种基于采样的SNMPC方法，利用近期推导的样本复杂度界限，在不假设系统动态或潜在不确定性分布的情况下，验证反馈策略的性能。通过并行化实现，我们能够在仿真和硬件上展示具有统计安全性保证的实时滚动时域SNMPC，所使用的硬件包括1/10比例拉力赛车和翼展24英寸的固定翼无人机。