AI/Machine Learning in Aerospace Autonomy

A special issue of Aerospace (ISSN 2226-4310). This special issue belongs to the section "Aeronautics".

Deadline for manuscript submissions: closed (15 March 2022) | Viewed by 19022

Special Issue Editor

School of Aerospace, Transport and Manufacturing, Cranfield University, Cranfield MK43 0AL, UK
Interests: autonomous systems; advanced flight controls; human–autonomy interaction; urban air mobility; explainable AI for trustworthy autonomous systems
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

As autonomous systems (ASs) become increasingly ubiquitous in complementing and supplementing humans and human-operated aerospace systems, our dependence on them is correspondingly growing. Applications and implementations of ASs within the aerospace domain will soon provide a spectrum of safety-critical, service-critical, and cost-critical functionalities. As such, their through-life evolution, adaptation, resilience, and security to unexpected inputs and events is essential to the trustworthiness of these systems. This dynamic nature of ASs presents us with new challenge frontiers for defining, analyzing, designing, and embedding the aforementioned features into their respective designs. To achieve this complex evolving behavior, the major paradigm shift that we currently face is the transition from design-time automated or sand-boxed autonomous systems to artificial intelligence (AI)-enabled self-aware and learning autonomous systems. AI-enabled autonomous systems within the aerospace domain operate in complex and unpredictable environments, while (a) accomplishing goals while providing through-life resilience and security against anomalies, failures and adversaries; and (b) learning and evolving through diverse experiences, often in contested environments. In that sense, a significant theoretical and methodological leap is required in developing learning-enabled systems within the aerospace domain with trustworthy and assured autonomy.

This Special Issue focuses on novel methods for applying artificial-intelligence-driven autonomy concepts to the design and execution of guidance, navigation, and control algorithms for aerospace vehicles. Topic areas of interest include the design, application, and implementation of AI technologies towards flight control system design, intelligent path/mission planning, sensor/data fusion and perception, situational awareness, classification and reconstruction, goal-based autonomy, multi-agent tactics development, target-task assignment, human–machine teaming, digital twins and data-driven modelling, model-free guidance and control, AI-driven testing and evaluation, AI hardware and software, dynamic verification and validation, and exploring pathways to the qualification and certification of learning-enabled designs.

Prof. Dr. Gokhan Inalhan
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Aerospace is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • autonomous systems
  • artificial intelligence
  • AI-driven guidance, navigation, and control
  • explainable AI
  • dynamic verification and validation for AI-enabled autonomy
  • digital twins
  • reinforcement learning
  • human–machine teaming
  • model-free learning
  • adversarial learning
  • qualification and certification for AI-enabled autonomy
  • deep learning
  • safety, robustness, adaptation, reconfiguration, resilience and security

Published Papers (5 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

14 pages, 1869 KiB  
Article
Active Fault-Tolerant Control for Near-Space Hypersonic Vehicles
by Kai Zhao, Jia Song, Shaojie Ai, Xiaowei Xu and Yang Liu
Aerospace 2022, 9(5), 237; https://doi.org/10.3390/aerospace9050237 - 25 Apr 2022
Cited by 10 | Viewed by 2048
Abstract
Due to the harsh working environment, Near-Space Hypersonic Vehicles (NSHVs) have the characteristics of frequent faults, which seriously affect flight safety. However, most researches focus on active fault-tolerant control for actuator faults. In order to fill the gap of active fault-tolerant control for [...] Read more.
Due to the harsh working environment, Near-Space Hypersonic Vehicles (NSHVs) have the characteristics of frequent faults, which seriously affect flight safety. However, most researches focus on active fault-tolerant control for actuator faults. In order to fill the gap of active fault-tolerant control for sensor faults, this paper presents an Active Fault-Tolerant Control (AFTC) strategy for NSHVs based on Active Disturbance Rejection Control (ADRC) combined with fault diagnosis and evaluation. With the proposed AFTC strategy, both sensor faults and actuator faults can be compensated within 0.5 s. Wavelet packet decomposition and Kernel Extreme Learning Machine (KELM) are associated to ensure the high accuracy and real-time ability of fault diagnosis. Simulation results show that the proposed fault diagnosis method can significantly reduce the divergence of diagnosis results by up to 98%. The fault information is used to generate tolerant compensation, which is combined with the ADRC to achieve AFTC. Statistical results indicate that AFTC has significantly lower static error than ADRC. The proposed AFTC method endows NSHVs with the ability to complete missions even when various types of faults appear. Its advantages are demonstrated in comparison with other fault diagnosis and tolerant control methods. Full article
(This article belongs to the Special Issue AI/Machine Learning in Aerospace Autonomy)
Show Figures

Figure 1

17 pages, 8282 KiB  
Article
Fast Path Planning for Long-Range Planetary Roving Based on a Hierarchical Framework and Deep Reinforcement Learning
by Ruijun Hu and Yulin Zhang
Aerospace 2022, 9(2), 101; https://doi.org/10.3390/aerospace9020101 - 14 Feb 2022
Cited by 12 | Viewed by 2448
Abstract
The global path planning of planetary surface rovers is crucial for optimizing exploration benefits and system safety. For the cases of long-range roving or obstacle constraints that are time-varied, there is an urgent need to improve the computational efficiency of path planning. This [...] Read more.
The global path planning of planetary surface rovers is crucial for optimizing exploration benefits and system safety. For the cases of long-range roving or obstacle constraints that are time-varied, there is an urgent need to improve the computational efficiency of path planning. This paper proposes a learning-based global path planning method that outperforms conventional searching and sampling-based methods in terms of planning speed. First, a distinguishable feature map is constructed through a traversability analysis of the extraterrestrial digital elevation model. Then, considering planning efficiency and adaptability, a hierarchical framework consisting of step iteration and block iteration is designed. For the planning of each step, an end-to-end step planner named SP-ResNet is proposed that is based on deep reinforcement learning. This step planner employs a double-branch residual network for action value estimation, and is trained over a simulated DEM map collection. Comparative analyses with baselines demonstrate the prominent advantage of our method in terms of planning speed. Finally, the method is verified to be effective on real lunar terrains using CE2TMap2015. Full article
(This article belongs to the Special Issue AI/Machine Learning in Aerospace Autonomy)
Show Figures

Figure 1

19 pages, 585 KiB  
Article
Safe Motion Planning and Learning for Unmanned Aerial Systems
by Baris Eren Perk and Gokhan Inalhan
Aerospace 2022, 9(2), 56; https://doi.org/10.3390/aerospace9020056 - 22 Jan 2022
Cited by 3 | Viewed by 3541
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 [...] Read more.
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. Full article
(This article belongs to the Special Issue AI/Machine Learning in Aerospace Autonomy)
Show Figures

Figure 1

17 pages, 2292 KiB  
Article
Unmanned Aerial Vehicle Pitch Control under Delay Using Deep Reinforcement Learning with Continuous Action in Wind Tunnel Test
by Daichi Wada, Sergio A. Araujo-Estrada and Shane Windsor
Aerospace 2021, 8(9), 258; https://doi.org/10.3390/aerospace8090258 - 11 Sep 2021
Cited by 10 | Viewed by 2391
Abstract
Nonlinear flight controllers for fixed-wing unmanned aerial vehicles (UAVs) can potentially be developed using deep reinforcement learning. However, there is often a reality gap between the simulation models used to train these controllers and the real world. This study experimentally investigated the application [...] Read more.
Nonlinear flight controllers for fixed-wing unmanned aerial vehicles (UAVs) can potentially be developed using deep reinforcement learning. However, there is often a reality gap between the simulation models used to train these controllers and the real world. This study experimentally investigated the application of deep reinforcement learning to the pitch control of a UAV in wind tunnel tests, with a particular focus of investigating the effect of time delays on flight controller performance. Multiple neural networks were trained in simulation with different assumed time delays and then wind tunnel tested. The neural networks trained with shorter delays tended to be susceptible to delay in the real tests and produce fluctuating behaviour. The neural networks trained with longer delays behaved more conservatively and did not produce oscillations but suffered steady state errors under some conditions due to unmodeled frictional effects. These results highlight the importance of performing physical experiments to validate controller performance and how the training approach used with reinforcement learning needs to be robust to reality gaps between simulation and the real world. Full article
(This article belongs to the Special Issue AI/Machine Learning in Aerospace Autonomy)
Show Figures

Figure 1

18 pages, 24794 KiB  
Article
The Effect of Real-World Interference on CNN Feature Extraction and Machine Learning Classification of Unmanned Aerial Systems
by Carolyn J. Swinney and John C. Woods
Aerospace 2021, 8(7), 179; https://doi.org/10.3390/aerospace8070179 - 01 Jul 2021
Cited by 11 | Viewed by 3489
Abstract
Small unmanned aerial systems (UASs) present many potential solutions and enhancements to industry today but equally pose a significant security challenge. We only need to look at the levels of disruption caused by UASs at airports in recent years. The accuracy of UAS [...] Read more.
Small unmanned aerial systems (UASs) present many potential solutions and enhancements to industry today but equally pose a significant security challenge. We only need to look at the levels of disruption caused by UASs at airports in recent years. The accuracy of UAS detection and classification systems based on radio frequency (RF) signals can be hindered by other interfering signals present in the same frequency band, such as Bluetooth and Wi-Fi devices. In this paper, we evaluate the effect of real-world interference from Bluetooth and Wi-Fi signals concurrently on convolutional neural network (CNN) feature extraction and machine learning classification of UASs. We assess multiple UASs that operate using different transmission systems: Wi-Fi, Lightbridge 2.0, OcuSync 1.0, OcuSync 2.0 and the recently released OcuSync 3.0. We consider 7 popular UASs, evaluating 2 class UAS detection, 8 class UAS type classification and 21 class UAS flight mode classification. Our results show that the process of CNN feature extraction using transfer learning and machine learning classification is fairly robust in the presence of real-world interference. We also show that UASs that are operating using the same transmission system can be distinguished. In the presence of interference from both Bluetooth and Wi-Fi signals, our results show 100% accuracy for UAV detection (2 classes), 98.1% (+/−0.4%) for UAV type classification (8 classes) and 95.4% (+/−0.3%) for UAV flight mode classification (21 classes). Full article
(This article belongs to the Special Issue AI/Machine Learning in Aerospace Autonomy)
Show Figures

Figure 1

Back to TopTop