English

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

Systems and Control 2021-11-12 v1 Robotics Systems and Control

Abstract

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).

Keywords

Cite

@article{arxiv.2111.06084,
  title  = {On the Problem of Reformulating Systems with Uncertain Dynamics as a Stochastic Differential Equation},
  author = {Thomas Lew and Apoorva Sharma and James Harrison and Edward Schmerling and Marco Pavone},
  journal= {arXiv preprint arXiv:2111.06084},
  year   = {2021}
}