We consider a moving target that we seek to learn from samples. Our results extend randomized techniques developed in control and optimization for a constant target to the case where the target is changing. We derive a novel bound on the number of samples that are required to construct a probably approximately correct (PAC) estimate of the target. Furthermore, when the moving target is a convex polytope, we provide a constructive method of generating the PAC estimate using a mixed integer linear program (MILP). The proposed method is demonstrated on an application to autonomous emergency braking.

翻译：本文研究如何从样本中学习一个移动目标。我们将控制与优化领域中针对恒定目标开发的随机化技术，推广到目标随时间变化的情形。我们推导出一个新颖的样本量界，用于构建目标的概率近似正确（PAC）估计。进一步地，当移动目标为凸多面体时，我们提出了一种利用混合整数线性规划（MILP）生成PAC估计的构造性方法。所提方法在自动驾驶紧急制动应用中进行了验证。