Abstract
This article reviews the state-of-the-art modeling and control techniques for aerial robots such as quadrotor systems and presents several future research directions in this area. The review starts by introducing the benefits and drawbacks of classic physic-based dynamic modeling and control techniques. Subsequently, the manuscript presents the key challenges to augment or replace classic techniques with data-driven approaches that can offer several key benefits in terms of flight precision, safety, adaptation, and agility.
Original language | English (US) |
---|---|
Pages (from-to) | 45-60 |
Number of pages | 16 |
Journal | Annual Reviews in Control |
Volume | 55 |
DOIs | |
State | Published - Jan 2023 |
Keywords
- Aerial vehicles
- Model learning
- Modeling dynamics
- Neural networks
- Robot learning
- System identification
ASJC Scopus subject areas
- Software
- Control and Systems Engineering