On inherent limitations in robustness and performance for a class of prescribed-time algorithms
arXiv:2205.02528 · doi:10.1016/j.automatica.2023.111284
Abstract
Prescribed-time algorithms based on time-varying gains may have remarkable properties, such as regulation in a user-prescribed finite time that is the same for every nonzero initial condition and that holds even under matched disturbances. However, at the same time, such algorithms are known to lack robustness to measurement noise. This note shows that the lack of robustness of a class of prescribed-time algorithms is of an extreme form. Specifically, we show the existence of arbitrarily small measurement noises causing considerable deviations, divergence, and other detrimental consequences. We also discuss some drawbacks and trade-offs of existing workarounds as motivation for further analysis.
References in corpus (4)
- On the design of non-autonomous fixed-time controllers with a predefined upper bound of the settling time
- Designing predefined-time differentiators with bounded time-varying gains
- A predefined-time first-order exact differentiator based on time-varying gains
- Optimal Robust Exact Differentiation via Linear Adaptive Techniques