arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.12367cs.RO
收藏

基于分层元学习的自适应控制器

Hierarchical Meta-learning-based Adaptive Controller

California Institute of Technology(加州理工学院);Carnegie Mellon University(卡内基梅隆大学)

Fengze Xie, Guanya Shi, Michael O'Connell, Yisong Yue, Soon-Jo Chung

AI总结:

本文提出基于分层元学习的自适应控制器(HMAC),通过分层迭代学习和平滑流式元学习技术,联合捕捉可管理与潜在多源干扰,实现了比其他控制器更精确快速的在线适应。

摘要:

我们研究如何设计基于学习的自适应控制器,以在不断变化的环境中实现快速且准确的在线适应。在这些场景中,学习通常在初始(离线)设计阶段完成,此时飞行器暴露于不同的环境条件和干扰(例如,无人机暴露于不同的风中)以收集训练数据。我们的研究动机源于观察到现实世界的干扰分为两类:1)在训练期间可以直接监控或控制的干扰,我们称之为“可管理的”;2)无法直接测量或控制的干扰(例如,标称模型不匹配、空气板效应和不可预测的风),我们称之为“潜在的”。对这些效应的不精确建模会导致控制性能下降,特别是当潜在干扰持续变化时。本文提出了基于分层元学习的自适应控制器(HMAC),以学习并适应这种多源干扰。在HMAC中,我们开发了两种技术:1)分层迭代学习,联合训练表征以捕捉各种干扰源;2)平滑流式元学习,学习捕捉潜在干扰随时间演变的结构(除了对可管理干扰的标准元学习之外)。实验结果表明,与其他自适应控制器相比,HMAC对多源干扰展现出更精确和快速的适应能力。

英文摘要:

We study how to design learning-based adaptive controllers that enable fast and accurate online adaptation in changing environments. In these settings, learning is typically done during an initial (offline) design phase, where the vehicle is exposed to different environmental conditions and disturbances (e.g., a drone exposed to different winds) to collect training data. Our work is motivated by the observation that real-world disturbances fall into two categories: 1) those that can be directly monitored or controlled during training, which we call "manageable", and 2) those that cannot be directly measured or controlled (e.g., nominal model mismatch, air plate effects, and unpredictable wind), which we call "latent". Imprecise modeling of these effects can result in degraded control performance, particularly when latent disturbances continuously vary. This paper presents the Hierarchical Meta-learning-based Adaptive Controller (HMAC) to learn and adapt to such multi-source disturbances. Within HMAC, we develop two techniques: 1) Hierarchical Iterative Learning, which jointly trains representations to caption the various sources of disturbances, and 2) Smoothed Streaming Meta-Learning, which learns to capture the evolving structure of latent disturbances over time (in addition to standard meta-learning on the manageable disturbances). Experimental results demonstrate that HMAC exhibits more precise and rapid adaptation to multi-source disturbances than other adaptive controllers.

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。

↑