融合传感器数据与人工偏好，加速人机协同调优
Regularized GLISp for sensor-guided human-in-the-loop optimization
- 用传感器数据构建物理启发的假设函数，改进偏好学习
- 在悬架调优任务中收敛更快，最终性能优于基线方法
- 适合需要人机协作且有可观测物理量的工程优化场景
人机协同校准常通过基于偏好的优化实现，算法从成对比较中学习而非显式代价评估。尽管有效，如基于径向基函数的主动偏好学习（GLISp）等方法将系统视为黑箱，忽略有价值的传感器测量信息。本文提出一种传感器引导的正则化GLISp扩展，通过物理启发的假设函数和最小二乘正则项，将可测量特征融入偏好学习循环。该方法引入灰箱结构，结合主观反馈与定量传感器数据，同时保持偏好搜索的灵活性。在解析基准和人机协同车辆悬架调优任务上的数值实验表明，该方法收敛速度更快，最终解更优。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。