A Novel Hybrid Approach for Fault-Tolerant Control of UAVs based on Robust Reinforcement Learning

Sohège, Yves; Quiñones-Grueiro, Marcos; Provan, Gregory

doi:10.1109/icra48506.2021.9562097

Cited by 6 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Studies on this topics in mobile robotics focusing on fault detection [9][10][11], fault diagnosis [12,13] or fault/error recovery [14][15][16]. Fault tolerance approaches in robotics involve also fault tolerant control approaches [17][18][19]. Dependability management concerns also the task level [20,21].…”

Section: Introductionmentioning

confidence: 99%

Performance Guarantee for Autonomous Robotic Missions using Resource Management: The PANORAMA Approach

Lambert,

Godary-Dejean,

Lapierre

et al. 2024

J Intell Robot Syst

View full text Add to dashboard Cite

This paper proposes the PANORAMA approach, which is designed to dynamically and autonomously manage the allocation of a robot’s hardware and software resources during fully autonomous mission. This behavioral autonomy approach guarantees the satisfaction of the mission performance constraints. This article clarifies the concept of performance for autonomous robotic missions and details the different phases of the PANORAMA approach. Finally, it focuses on an experimental implementation on a patrolling mission example.

show abstract

Section: Introductionmentioning

confidence: 99%

Performance Guarantee for Autonomous Robotic Missions using Resource Management: The PANORAMA Approach

Lambert,

Godary-Dejean,

Lapierre

et al. 2024

J Intell Robot Syst

View full text Add to dashboard Cite

show abstract

“…Moreover, an RL agent can interact with the environment and analyze the measured data in-depth to capture key system information instead of relying on accurate analytical models. Note that the RL-based FTC methods have shown advantages in various fields [15], such as unmanned aerial vehicles [16], highly flexible aircraft [17], and mobile robots [18]. To be brief, it is still an open area to design RL-based optimal FTC for wind turbines.…”

Section: Introductionmentioning

confidence: 99%

Wind Turbine Fault-Tolerant Control via Incremental Model-Based Reinforcement Learning

Xie,

Dong,

Zhao

et al. 2024

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

A reinforcement learning (RL) based fault-tolerant control strategy is developed in this paper for wind turbine torque & pitch control under actuator & sensor faults subject to unknown system models. An incremental model-based heuristic dynamic programming (IHDP) approach, along with a criticactor structure, is designed to enable fault-tolerance capability and achieve optimal control. Particularly, an incremental model is embedded in the critic-actor structure to quickly learn the potential system changes, such as faults, in real-time. Different from the current IHDP methods that need the intensive evaluation of the state and input matrices, only the input matrix of the incremental model is dynamically evaluated and updated by an online recursive least square estimation procedure in our proposed method. Such a design significantly enhances the online model evaluation efficiency and control performance, especially under faulty conditions. In addition, a value function and a target critic network are incorporated into the main criticactor structure to improve our method's learning effectiveness. Case studies for wind turbines under various working conditions are conducted based on the fatigue, aerodynamics, structures, and turbulence (FAST) simulator to demonstrate the proposed method's solid fault-tolerance capability and adaptability.Note to Practitioners-This work achieves high-performance wind turbine control under unknown actuator & sensor faults. Such a task is still an open problem due to the complexity of turbine dynamics and potential uncertainties in practical situations. A novel data-driven and model-free control strategy based on reinforcement learning is proposed to handle these issues. The designed method can quickly capture the potential changes in the system and adjust its control policy in realtime, rendering strong adaptability and fault-tolerant abilities. It provides data-driven innovations for complex operational tasks of wind turbines and demonstrates the feasibility of applying reinforcement learning to handle fault-tolerant control problems. The proposed method has a generic structure and has the potential to be implemented in other renewable energy systems.

show abstract

Fault-tolerant control for UAV based on deep reinforcement learning under single rotor failure

Cheng,

Li,

Hou

2024

2024 36th Chinese Control and Decision Conference (CCDC)

View full text Add to dashboard Cite

A Novel Hybrid Approach for Fault-Tolerant Control of UAVs based on Robust Reinforcement Learning

Cited by 6 publications

References 23 publications

Performance Guarantee for Autonomous Robotic Missions using Resource Management: The PANORAMA Approach

Performance Guarantee for Autonomous Robotic Missions using Resource Management: The PANORAMA Approach

Wind Turbine Fault-Tolerant Control via Incremental Model-Based Reinforcement Learning

Fault-tolerant control for UAV based on deep reinforcement learning under single rotor failure

Contact Info

Product

Resources

About