.png){kind=icon}
Return
Control-Oriented Learning on the Fly
.png){kind=icon}
OA
AI
DOI：10.1109/TAC.2019.2963293.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This article focuses on developing a strategy for control of systems, whose dynamics are almost entirely unknown. This situation arises naturally in a scenario, where a system undergoes a critical failure. In that case, it is imperative to retain the ability to satisfy basic control objectives in order to avert an imminent catastrophe. To deal with limitations on the knowledge of system dynamics, we develop a theory of myopic control. At any given time, myopic control optimizes the current direction of the system trajectory, given solely the knowledge about system dynamics obtained from data until that time. We propose an algorithm that uses small perturbations in the control effort to learn system dynamics around the current system state, while ensuring that the system moves in a nearly optimal direction, and provide bounds for its suboptimality.
Keywords:
System dynamics
Trajectory
Optimal control
Aircraft
Approximation algorithms
Heuristic algorithms
Estimation
learning
optimal control
uncertain systems
Journal
IF:
7
Papers:
1.3W
Citations:
6.7W
Organization
Cited Papers
Development of summary indices of antenatal care service quality in Haiti, Malawi and Tanzania.png)
BMJ OpenOAAI
BMJ OpenIF0
OAAIShareSaveDiscovering governing equations from data by sparse identification of nonlinear dynamical systemsOAAI
OAAIShareSaveIsolation, chemical and functional characterization of several new K+-channel blocking peptides from the venom of the scorpion Centruroides tecomanusToxiconOAAI
ToxiconIF0
OAAIShareSave
ShareSaveShareSaveShareSave
View more