arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.04751cs.LG
收藏

用于传感器引导的人在回路优化的正则化GLISp

Regularized GLISp for sensor-guided human-in-the-loop optimization

IDSIA Dalle Molle Institute for Artificial Intelligence Research - SUPSI(IDSIA达摩斯人工智能研究所-瑞士SUPSI)

Matteo Cercola, Michele Lomuscio, Dario Piga, Simone Formentin

AI总结:

提出传感器引导的正则化GLISp方法,通过物理信息假设函数和最小二乘正则化将传感器测量集成到偏好学习回路中,在基准和车辆悬架调校任务上实现更快收敛和更优解。

摘要:

人在回路校准通常通过基于偏好的优化来解决,其中算法从成对比较中学习,而不是从显式代价评估中学习。虽然诸如Preferential Bayesian Optimization或基于径向基函数主动偏好学习的全局优化(GLISp)等方法很有效,但它们将系统视为黑箱,忽略了信息丰富的传感器测量。在这项工作中,我们引入了GLISp的一种传感器引导的正则化扩展,通过物理信息假设函数和最小二乘正则化项将可测量的描述符集成到偏好学习回路中。这注入了灰箱结构,将主观反馈与定量传感器信息相结合,同时保持了基于偏好搜索的灵活性。在解析基准和人在回路车辆悬架调校任务上的数值评估表明,与基线GLISp相比,该方法收敛更快,最终解更优。

英文摘要:

Human-in-the-loop calibration is often addressed via preference-based optimization, where algorithms learn from pairwise comparisons rather than explicit cost evaluations. While effective, methods such as Preferential Bayesian Optimization or Global optimization based on active preference learning with radial basis functions (GLISp) treat the system as a black box and ignore informative sensor measurements. In this work, we introduce a sensor-guided regularized extension of GLISp that integrates measurable descriptors into the preference-learning loop through a physics-informed hypothesis function and a least-squares regularization term. This injects grey-box structure, combining subjective feedback with quantitative sensor information while preserving the flexibility of preference-based search. Numerical evaluations on an analytical benchmark and on a human-in-the-loop vehicle suspension tuning task show faster convergence and superior final solutions compared to baseline GLISp.

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。

↑