16 October 2023 in IEEE Access
As research advances diverse forms and missions of aircraft, the National Airspace System (NAS) will become increasingly crowded, limiting the current aviation spectrum to accommodate future air operations. To tackle this challenge, the concept of intelligent spectrum management is proposed for autonomous and dynamic resource allocations, where accurate aircraft position estimation is one of the crucial tasks. However, current research on flight trajectory prediction has been limited in its scope of efforts, frequently utilizing a unique flight route, architecture, set of weather data, and date range. In this paper, we propose a generalized hybrid-recurrent predictive model for flight trajectory prediction. Our generalizable deep learning approach not only improves trajectory prediction accuracy, but also can be contextualized by exploring a large amount of data. Experimental results illustrate a tradeoff between horizontal and vertical errors as flight data are generalized across dates and routes.
13 March 2023 in IEEE Transactions on Vehicular Technology
The emerging concepts of Urban Air Mobility (UAM) and Advanced Air Mobility (AAM) open a new paradigm for urban air transportation. One big challenge is that new aerial vehicles (AV) will quickly saturate the already crowded aviation spectrum, which is an essential resource to ensure reliable communications for safe air operations. In this paper, we consider an air transportation system where multiple AVs are operated to transport passengers or cargo from different sources to destinations along their pre-defined paths. During the flight, the minimum communication Quality of Service (QoS) must be achieved at all times to ensure flight safety. Our objective is to minimize the total mission completion time by jointly optimizing the velocities and spectrum allocation for all AVs. We formulate the optimization problem as a multi-stage Markov game where the optimization variables are coupled together. A multi-agent deep reinforcement learning VD3QN algorithm is proposed to enable cooperative learning among AVs. Additionally, we propose a heuristic greedy algorithm (HGA) and an orthogonal multiple access (OMA) solution as baseline solutions. Extensive simulation results show that our learning-based solution outperforms the baseline solutions under different network configurations.
10 January 2023 in IEEE Aerospace and Electronic Systems Magazine
The emergence of new aerial vehicles into the airspace and the continued growth of aviation operations will result in an increased demand for voice and data communications throughout the National Airspace System (NAS). However, recent studies have shown that the continued use of existing aviation spectrum allocations will not meet the anticipated needs of future aerospace applications; as a result, a new approach to aviation spectrum management is needed to support the forecasted needs of new airspace users. The National Aeronautics and Space Administration (NASA) is investigating the use of modern advancements in wireless communications, artificial intelligence (AI), machine learning (ML), and other advanced concepts in order to implement a novel spectrum management approach that allows for the intelligent utilization of aviation spectrum throughout the airspace. This technical investigation considers various airspace communications configurations, including air-ground and air-air communications, and can be applied to the existing air traffic control (ATC) system, as well as to future applications, such as the emerging Advanced Air Mobility (AAM) initiative. To support the evaluation of the proposed concepts and technologies, a modeling and simulation capability is currently under development, which will continue to evolve in support of new and advanced airspace applications. It is anticipated that this proposed spectrum management concept will allow for increased spectrum utilization efficiency and enhanced airspace capacity, which will better serve the needs of future NAS applications.
5 November 2024 in IEEE Access
In an era dominated by a surge in air travel and heightened reliance on efficient communication systems, there’s a critical need to smartly allocate frequency resources for aviation communications to efficiently manage airspace operations. This is essential to ensure safe, smooth, and technologically advanced flight services. Over time, techniques for managing frequency resources and new radio technologies have evolved to cope with the increased demands on the system due to growing airspace activities. With the development of Urban Air Mobility (UAM) operations, a fresh challenge has emerged, further burdening the already limited aviation spectrum. There is a pressing need for a new approach to efficiently manage and utilize frequencies. This paper explores the application of Multi-agent Reinforcement Learning (MARL) technique to minimize aircraft mission completion time and enhance safety, all while dealing with the limitations of airspace and frequency resources. The proposed MARL approach utilizes the value decomposition network (VDN) technique to optimize frequency use, flight time, and departure wait times by managing spectrum allocation, vehicle departure, and flight speed. To achieve the goal of minimizing mission completion time, the Markov Decision Process (MDP) is utilized. It takes into account factors like frequency channel availability, signal-to-interference-plus-noise power ratio, aircraft location, and flight status. In our investigation, we develop a case study scenario and assess the performance of the MARL technique through simulation in a hypothetical UAM scenario. The solution is evaluated against Q-Mixing (QMIX), Orthogonal Multiple Access and a Heuristic Greedy Algorithm.
17 July 2024 in IEEE Access
As the airspace is experiencing an increasing number of low-altitude aircraft, the concept of spectrum sharing between aerial and terrestrial users emerges as a compelling solution to improve the spectrum utilization efficiency. In this paper, we consider a new Aerial and Terrestrial Hybrid Network (ATHN) comprising aerial vehicles (AVs), ground base stations (BSs), and terrestrial users (TUs). In this ATHN, AVs and BSs collaboratively form a multi-hop ad-hoc network with the objective of minimizing the average end-to-end (E2E) packet transmission delay. Meanwhile, the BSs and TUs constitute a terrestrial network aimed at maximizing the uplink and downlink sum capacity. Given the concept of spectrum sharing between aerial and terrestrial users in ATHN, we formulate a joint routing and capacity optimization problem, which is a multi-stage combinatorial problem subject to the curse of dimensionality. To navigate this complexity, we propose a Deep Reinforcement Learning (DRL) based algorithm. Specifically, the Dueling Double Deep Q-Network (D3QN) structure is constructed to learn an optimal policy through trial and error. Extensive simulation results demonstrate the efficacy of our proposed solution.
1 January 2026 in IEEE Access