高相対次数系の学習ダイナミクスに対する確率的安全制約
Probabilistic Safety Constraints for Learned High Relative Degree System Dynamics
オンラインでベイズ学習した系のダイナミクス分布を用い、制御バリア関数へのチャンス制約で高確率の安全性を保証する手法を提案。
著者: Mohammad Javad Khojasteh, Vikas Dhiman, Massimo Franceschetti, Nikolay Atanasov
分類: cs.RO, cs.LG, cs.SY, eess.SY, math.OC
原文アブストラクト
This paper focuses on learning a model of system dynamics online while satisfying safety constraints.Our motivation is to avoid offline system identification or hand-specified dynamics models and allowa system to safely and autonomously estimate and adapt its own model during online operation.Given streaming observations of the system state, we use Bayesian learning to obtain a distributionover the system dynamics. In turn, the distribution is used to optimize the system behavior andensure safety with high probability, by specifying a chance constraint over a control barrier function.
