Redirigiendo al acceso original de articulo en 23 segundos...
Inicio  /  Aerospace  /  Vol: 9 Par: 2 (2022)  /  Artículo
ARTÍCULO
TITULO

Safe Motion Planning and Learning for Unmanned Aerial Systems

Baris Eren Perk and Gokhan Inalhan    

Resumen

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 (????2 P I 2 ) was used for the maneuvers. The results in this paper show that ????2 P I 2 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.

 Artículos similares

       
 
Shunan Hu, Shenpeng Tian, Jiansen Zhao and Ruiqi Shen    
In order to ensure the safe navigation of USVs (unmanned surface vessels) and real-time collision avoidance, this study conducts global and local path planning for USVs in a variable dynamic environment, while local path planning is proposed under the co... ver más

 
Shuo Liu, Zijing Yu, Tao Wang, Yifan Chen, Yu Zhang and Yong Cai    
In the traditional motion control method of an unmanned sailboat, the sail and rudder are divided into two independent controllers. The sail is used to obtain the thrust and the rudder is used to adjust the yaw angle. The traditional control method does ... ver más

 
Zeng Wang, Xiancheng Wang and Ruidong Li    
In previous research on treadmills, the main focus has been on comparing the physiological differences induced by running on treadmill decks and other exercise surfaces, with relatively little research on the mechanical properties of treadmill decks. Red... ver más
Revista: Applied Sciences

 
Ayesha Hameed, Andrzej Ordys, Jakub Mozaryn and Anna Sibilska-Mroziewicz    
Collaborative robots cooperate with humans to assist them in undertaking simple-to-complex tasks in several fields, including industry, education, agriculture, healthcare services, security, and space exploration. These robots play a vital role in the re... ver más
Revista: Applied Sciences

 
Noor Arifah Azwani Abdul Yamin, Khairul Salleh Basaruddin, Muhammad Farzik Ijaz, Mohd Hanafi Mat Som, Muhammad Nazrin Shah Shahrol Aman and Hiroshi Takemura    
Postural stability may be affected during slope walking, as there are different body kinetics and kinematic responses compared with level walking. Understanding body adaptations toward different inclinations is essential to prevent the risk of injury fro... ver más
Revista: Applied Sciences