Searched for: author%3A%22van+Kampen%2C+E.%22
(1 - 20 of 93)

Pages

document
Kumtepe, Y. (author), Pollack, T.S.C. (author), van Kampen, E. (author)
Incremental Nonlinear Dynamic Inversion (INDI) is a sensor-based control strategy, which has shown robustness against model uncertainties on various aerospace platforms. The sensor-based nature of the method brings attractive properties, which has made it popular in the last decade. INDI globally linearizes the system by making use of control...
conference paper 2022
document
Liu, C. (author), van Kampen, E. (author)
Reinforcement learning (RL) equipped with neural networks has recently led to a wide range of successes in learning policies for unmanned aerial vehicle (UAV) navigation and control problems. The success of RL relies on two human-designed heuristics: appropriate action space definition and reward function engineering. The commonly used fully...
conference paper 2022
document
Sun, B. (author), van Kampen, E. (author)
This paper develops an event-triggered optimal control method that can deal with asymmetric input constraints for nonlinear discrete-time systems. The implementation is based on an explainable global dual heuristic programming (XGDHP) technique. Different from traditional GDHP, the required derivatives of cost function in the proposed method...
journal article 2022
document
Sun, B. (author), Wang, Xuerui (author), van Kampen, E. (author)
In this paper, we establish an event-triggered intelligent control scheme with a single critic network, to cope with the optimal stabilization problem of nonlinear aeroelastic systems. The main contribution lies in the design of a novel triggering condition with input constraints, avoiding the Lipschitz assumption on the inverse hyperbolic...
journal article 2022
document
van Overeem, S. (author), Wang, Xuerui (author), van Kampen, E. (author)
Considerable growth in the number of passengers and cargo transported by air is predicted. Besides that, aircraft noise and climate impact become increasingly important factors in aircraft design. These existing challenges in aviation boost interest in the design of innovative aircraft configurations. One of these configurations is a V-shaped...
conference paper 2022
document
Smit, B. (author), Pollack, T.S.C. (author), van Kampen, E. (author)
Control augmentation systems based on Incremental Nonlinear Dynamic Inversion (INDI) are able to provide high-performance nonlinear control without a holistic model. Considering an angular rate control law for a fixed-wing aircraft, only a control effectiveness (CE) model and angular acceleration measurement feedback is required. Despite...
conference paper 2022
document
Paul, Acquatella B. (author), van Kampen, E. (author), Chu, Q. P. (author)
This paper presents a sampled-data form of the recently reformulated incremental nonlinear dynamic inversion (INDI) applied for robust spacecraft attitude control. INDI is a combined model- and sensor-based approach mostly applied for attitude control that only requires an accurate control effectiveness model and measurements of the state and...
conference paper 2022
document
De Buysscher, D.D.C. (author), Pollack, T.S.C. (author), van Kampen, E. (author)
Safe Curriculum Learning aims at improving safety and efficiency aspects of Reinforcement Learning (RL). Curricular RL approaches divide a task into stages of increasing complexity in order to increase efficiency. This paper proposes a black box safe curriculum learning architecture applicable to systems with parametric unknowns. The agent...
conference paper 2022
document
Pollack, T.S.C. (author), van Kampen, E. (author)
Incremental Nonlinear Dynamic Inversion (INDI) is a sensor-based control law design strategy that is based on the principles of feedback linearization. Contrary to its non-incremental counterpart (NDI), this design method does not rely on the availability of a high-fidelity on-board model of the airframe dynamics and is robust to aerodynamic...
conference paper 2022
document
Dally, Killian (author), van Kampen, E. (author)
Fault-tolerant flight control faces challenges, as developing a model-based controller for each unexpected failure is unrealistic, and online learning methods can handle limited system complexity due to their low sample efficiency. In this research, a model-free coupled-dynamics flight controller for a jet aircraft able to withstand multiple...
conference paper 2022
document
Zammit, C. (author), van Kampen, E. (author)
Unmanned Aerial Vehicles (UAVs) are taking active roles in personal, commercial, industrial and military applications due to their efficiency, availability and low-cost. UAVs must operate safely and in real-time in both static and dynamic environments. An extensive literature review, defines the dynamic environment term, the need for dynamic...
conference paper 2021
document
Das, H. (author), Pool, D.M. (author), van Kampen, E. (author)
Pneumatic cylinders provide an environmentfriendly actuation means by minimizing the leakage of any harmful industrial fluids, as occurs for hydraulic actuators. However, pneumatic actuation has not been utilized widely for industrial servo applications due to its highly nonlinear nature. Incremental nonlinear dynamic inversion (INDI) is a form...
conference paper 2021
document
de Alvear Cardenas, J.I. (author), Sun, B. (author), van Kampen, E. (author)
Linear Approximate Dynamic Programming (LADP) and Incremental Approximate Dynamic Programming (IADP) are Reinforcement Learning methods that seek to contribute to the field of Adaptive Flight Control. This paper assesses their performance and convergence, as well as the impact of sensor noise on policy convergence, online system...
conference paper 2021
document
Sun, B. (author), van Kampen, E. (author)
The scarcity of information regarding dynamics and full-state feedback increases the demand for a model-free control technique that can cope with partial observability. To deal with the absence of prior knowledge of system dynamics and perfect measurements, this paper develops a novel intelligent control scheme by combining global dual...
journal article 2021
document
Shayan, K. (author), van Kampen, E. (author)
Conventional discrete reinforcement learning methods fail in providing satisfactory performance for online Flight Control Systems (FCSs). The lack of efficiency of the discrete controller in exploration for finding the optimal policy, the so-called problem of ’curse of dimensionality’, results in an approach that is not suitable for online...
conference paper 2021
document
Lee, J.H. (author), van Kampen, E. (author)
Reinforcement learning is used as a type of adaptive flight control. Adaptive Critic Design (ACD) is a popular approach for online reinforcement learning control due to its explicit generalization of the policy evaluation and the policy improvement elements. A variant of ACD, Incremental Dual Heuristic Programming (IDHP) has previously been...
conference paper 2021
document
Konatala, R.B. (author), van Kampen, E. (author), Looye, Gertjan H.N. (author)
OnlineAdaptive Flight Control is interesting in the context of growing complexity of aircraft systems and their adaptability requirements to ensure safety. An Incremental Approximate Dynamic Programming (iADP) controller combines reinforcement learning methods, optimal control and online identified incremental model to achieve optimal adaptive...
conference paper 2021
document
Sun, B. (author), van Kampen, E. (author)
journal article 2021
document
Helder, B. (author), van Kampen, E. (author), Pavel, M.D. (author)
Reinforcement learning is an appealing approach for adaptive, fault-tolerant flight control, but is generally plagued by its need for accurate system models and lengthy offline training phases. The novel Incremental Dual Heuristic Programming (IDHP) method removes these dependencies by using an online-identified local system model. A recent...
conference paper 2021
document
Zammit, C. (author), van Kampen, E. (author)
Unmanned Aerial Vehicles (UAVs) are being integrated into all spheres of life varying in a wide range of applications from military to civil applications. In such applications, UAVs are expected to operate safely in the presence of uncertainties present in the dynamic environment and the UAV itself. Based on literature different uncertainty...
conference paper 2021
Searched for: author%3A%22van+Kampen%2C+E.%22
(1 - 20 of 93)

Pages