Aircraft Fault Tolerant Control

Sep 27, 2018

The Cessna Citation 550 aircraft (PH-LAB) owned by NLR and the TU Delft.

With the development of aerospace engineering, aerospace systems are becoming more complex in structure, function, and working environment. Unknown conditions and even sudden faults can be encountered. This project aims at improving safety by developing advanced nonlinear control methods based on reinforcement learning and optimal control theory. The proposed control approaches have the capability of online learning and adapting to new circumstances, which enable the aircraft to tolerate actuator faults, structural damage and atmospheric disturbances.

Reinforcement Learning Aerospace Engineering Adaptive Control

Bo Sun

PhD Candidate

My research interests include reinforcement learning, intelligent control and aerospace systems.

Publications

Intelligent Aircraft Stabilization Control with Event-Triggered Scheme

This paper develops an intelligent optimal stabilization control approach that can be applied to general flight control systems. The …

Bo Sun, Cheng Liu, Killian Dally, Erik-Jan van Kampen

Event-Triggered Constrained Control Using Explainable Global Dual Heuristic Programming for Nonlinear Discrete-Time Systems

This paper develops an event-triggered optimal control method that can deal with asymmetric input constraints for nonlinear …

Bo Sun, Erik-Jan van Kampen

Reinforcement-Learning-Based Adaptive Optimal Flight Control with Output Feedback and Input Constraints

This Note aims at improving the present incremental-model-based global dual heuristic programming algorithm proposed in our recent work …

Bo Sun, Erik-Jan van Kampen

Intelligent adaptive optimal control using incremental model-based global dual heuristic programming subject to partial observability

The scarcity of information regarding dynamics and full-state feedback increases the demand for a model-free control technique that can …

Bo Sun, Erik-Jan van Kampen

Intelligent Adaptive Control Using LADP and IADP Applied to F-16 Aircraft with Imperfect Measurements

Linear Approximate Dynamic Programming (LADP) and Incremental Approximate Dynamic Programming (IADP) are Reinforcement Learning methods …

Jose Ignacio de Alvear Cardenas, Bo Sun, Erik-Jan van Kampen

Incremental Model-Based Heuristic Dynamic Programming with Output Feedback Applied to Aerospace System Identification and Control

Sufficient information about system dynamics and inner states is often unavailable to aerospace system controllers, which requires …

Bo Sun, Erik-Jan van Kampen

Launch Vehicle Discrete-Time Optimal Tracking Control using Global Dual Heuristic Programming

Optimal tracking is a widely researched control problem, but the unavailability of sufficient information referring to system dynamics …

Bo Sun, Erik-Jan van Kampen

Incremental model-based global dual heuristic programming with explicit analytical calculations applied to flight control

A novel adaptive dynamic programming method, called incremental model-based global dual heuristic programming, is proposed to generate …

Bo Sun, Erik-Jan van Kampen

Incremental Model-Based Global Dual Heuristic Programming for Flight Control

This paper proposes a novel adaptive dynamic programming method, called Incremental model-based Global Dual Heuristic Programming, to …

Bo Sun, Erik-Jan van Kampen