Safe Motion Planning and Learning for Unmanned Aerial Systems

Baris Eren Perk*, Gokhan Inalhan

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

To control unmanned aerial systems, we rarely have a perfect system model. Safe and aggressive planning is also challenging for nonlinear and under-actuated systems. Expert pilots, however, demonstrate maneuvers that are deemed at the edge of plane envelope. Inspired by biological systems, in this paper, we introduce a framework that leverages methods in the field of control theory and reinforcement learning to generate feasible, possibly aggressive, trajectories. For the control policies, Dynamic Movement Primitives (DMPs) imitate pilot-induced primitives, and DMPs are combined in parallel to generate trajectories to reach original or different goal points. The stability properties of DMPs and their overall systems are analyzed using contraction theory. For reinforcement learning, Policy Improvement with Path Integrals (PI2) was used for the maneuvers. The results in this paper show that PI2 updated policies are a feasible and parallel combination of different updated primitives transfer the learning in the contraction regions. Our proposed methodology can be used to imitate, reshape, and improve feasible, possibly aggressive, maneuvers. In addition, we can exploit trajectories generated by optimization methods, such as Model Predictive Control (MPC), and a library of maneuvers can be instantly generated. For application, 3-DOF (degrees of freedom) Helicopter and 2D-UAV (unmanned aerial vehicle) models are utilized to demonstrate the main results.

Original languageEnglish
Article number56
JournalAerospace
Volume9
Issue number2
DOIs
Publication statusPublished - Feb 2022

Bibliographical note

Publisher Copyright:
© 2022 by the authors. Licensee MDPI, Basel, Switzerland.

Keywords

  • Artificial intelligence
  • Contraction theory
  • Imitation learning
  • Maneuvers
  • Nonlinear control
  • Primitives
  • Reinforcement learning
  • UAV

Fingerprint

Dive into the research topics of 'Safe Motion Planning and Learning for Unmanned Aerial Systems'. Together they form a unique fingerprint.

Cite this