arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.08013eess.SYcs.LGcs.SYmath.OC
收藏

从稀疏输出测量中学习动态以实现不确定性感知的最优控制

Learning Dynamics from Infrequent Output Measurements for Uncertainty-Aware Optimal Control

Chair of Information-oriented Control, School of Computation, Information and Technology(信息导向控制研究所,计算、信息与技术学院)

Robert Lefringhausen, Theodor Springer, Sandra Hirche

AI总结:

该研究提出了一种基于贝叶斯先验的连续时间动态和潜在状态轨迹建模方法,利用目标Metropolis-Hastings采样器和数值ODE求解器进行更新,通过场景优化方法解决不确定性下的最优控制问题,验证了在1型糖尿病血糖调节中的有效性。

摘要:

当非线性系统动态未知且仅有稀疏、噪声的输出测量时,可靠的最优控制极具挑战性。本文针对这种有限传感设置,通过构建连续时间动态和潜在状态轨迹的状态空间形式的贝叶斯先验,并利用配备数值ODE求解器的目标Metropolis-Hastings采样器进行更新。所得后验样本用于构建考虑动态和潜在状态不确定性的场景优化最优控制问题,并通过标准非线性规划方法求解。该方法在使用1型糖尿病模型的数值案例研究中得到了验证。

英文摘要:

Reliable optimal control is challenging when the dynamics of a nonlinear system are unknown and only infrequent, noisy output measurements are available. This work addresses this setting of limited sensing by formulating a Bayesian prior over the continuous-time dynamics and latent state trajectory in state-space form and updating it through a targeted Metropolis-Hastings sampler equipped with a numerical ODE integrator. The resulting posterior samples are used to formulate a scenario-based optimal control problem that accounts for the uncertainty in the dynamics and latent state and is solved using standard nonlinear programming methods. The approach is validated in a numerical case study on glucose regulation using a Type 1 diabetes model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑