数字孪生校准的轨迹设计与预算查询
Trajectory Design and Budgeted Querying for Digital Twin Calibration
- National University of Kyiv-Mohyla Academy（基辅莫希拉国立大学）
- University of Turin（都灵大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对数字孪生校准中交互数据采集成本高的问题，提出耦合强化学习控制器、循环参数估计器与预算查询策略的框架，在倒立摆、水上世界任务中验证了其低误差性能，推动将轨迹设计与查询分配作为校准的显式变量。
AI中文摘要：
数字孪生校准需要收集成本高昂的交互数据。我们研究两类采集决策：生成哪些轨迹，以及何时将有限预算用于特权参数测量。我们的框架耦合了面向激励的强化学习控制器、带有预测不确定性的循环参数估计器，以及预算查询策略。在倒立摆（Pendulum）任务中，随机森林诊断模型从面向任务的轨迹中仅能微弱恢复重力参数，无法恢复质量或长度参数；而在面向激励的轨迹上训练的门控循环单元（GRU）无需任何查询，即可达到0.0066的平均绝对误差。随后，我们在一个 episode 的中途撤回连续的真值（oracle）访问权限，使得孪生体必须在剩余时间内依赖估计器的输出运行。在三次查询预算下，估计器加策略的流水线达到了0.0092的终端误差，而未校准的孪生体误差为0.2031。在部分可观测的水上世界（Waterworld）任务中，五个控制器在三个隐藏参数上产生不同的观测误差分布，在五种控制器混合数据上训练的估计器达到约4%-5%的在线归一化误差。这些探索性案例研究并非受控消融实验，但它们促使人们将轨迹设计与查询分配视为数据稀缺校准中的显式设计变量。
英文摘要：
Digital-twin calibration requires interaction data that is expensive to collect. We study two acquisition decisions: which trajectories to generate, and when to spend a limited budget on privileged parameter measurements. Our framework couples an excitation-oriented reinforcement learning controller, a recurrent parameter estimator with predictive uncertainty, and a budgeted query policy. In Pendulum, a Random Forest diagnostic recovers gravity only weakly from task-oriented trajectories and does not recover mass or length, while a GRU trained on excitation-oriented trajectories reaches a mean absolute error of 0.0066 with no queries. We then withdraw continuous oracle access partway through an episode, so that the twin must run on the estimator's output for the remainder. The estimator-plus-policy pipeline achieves a terminal error of 0.0092 under a three-query budget, against 0.2031 for an uncalibrated twin. In partially observable Waterworld, five controllers produce different observed error profiles across three hidden parameters, and an estimator trained on a five-controller mixture reaches online normalized errors of roughly 4-5%. These exploratory case studies are not controlled ablations, but they motivate treating trajectory design and query allocation as explicit design variables in data-scarce calibration.
