日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

週刊ニュースレター購読
arXiv:2111.06084

On the Problem of Reformulating Systems with Uncertain Dynamics as a Stochastic Differential Equation

On the Problem of Reformulating Systems with Uncertain Dynamics as a Stochastic Differential Equation

シェア:XThreadsFacebookLINEはてブBluesky

著者: Thomas Lew, Apoorva Sharma, James Harrison, Edward Schmerling, Marco Pavone

分類: eess.SY, cs.RO, cs.SY

原文アブストラクト

We identify an issue in recent approaches to learning-based control that reformulate systems with uncertain dynamics using a stochastic differential equation. Specifically, we discuss the approximation that replaces a model with fixed but uncertain parameters (a source of epistemic uncertainty) with a model subject to external disturbances modeled as a Brownian motion (corresponding to aleatoric uncertainty).