Gokhan Inalhan

• Ph.D.
• BAE Systems Professor of Autonomous Systems and Artificial Intelligence at Cranfield University

The integration of unmanned aerial vehicles (UAVs) with vertical takeoff and landing (VTOL) capability into commercial and military applications marks a significant advancement in aerial technology, necessitating robust systems for safe operation. Performing autonomous safe landing in emergencies remains a critical concern among other challenges. E...

Aerial vehicles are increasingly relying on connectivity to cellular networks, with 5G new radio (NR) and 6G technologies deemed critical for the next generation of indoor and outdoor positioning systems. Conventional time of arrival approaches require time synchronisation between base stations and vehicles, and a clock bias greater than 30 ns can...

Recent advances in radar seeker technologies have considerably improved missile precision and efficacy during target interception. This is especially concerning in the arenas of protection and safety, where appropriate countermeasures against enemy missiles are required to ensure the protection of naval facilities. In this study, we present a reinf...

The conceptual design of unmanned aerial vehicles (UAVs) presents significant multidisciplinary challenges requiring the optimization of aerodynamic and structural performance, stealth, and propulsion efficiency. This work addresses these challenges by integrating deep neural networks with a multiobjective genetic algorithm to optimize UAV configur...

This research introduces a Multi-Agent Reinforcement Learning (MARL) system designed for supporting Tactical Conflict Resolution service in shared corridor-based routes for Urban Air Mobility (UAM) operations. The solver incorporates an innovative approach that integrates flight plan adherence into the decision-making process, aligning with the vis...

In this paper, we explore the development of an explainability system for air combat agents trained with reinforcement learning, thus addressing a crucial need in the dynamic and complex realm of air combat. The safety-critical nature of air combat demands not only improved performance but also a deep understanding of artificial intelligence (AI) d...

A device includes a processor configured to obtain flight data of one or more aircraft of an aircraft type. The processor is configured to identify a first portion of the flight data as first phase flight data associated with a first phase of one or more flights of the one or more aircraft, and to apply a first aircraft performance model to the fir...

A device includes a processor configured to obtain flight data of one or more aircraft of an aircraft type. The processor is configured to identify a first portion of the flight data as first phase flight data associated with a first phase of one or more flights of the one or more aircraft, and to apply a first aircraft performance model to the fir...

The multi-agent reinforcement learning (MARL) problem is a well-known field of study that has been gaining special interest in the last decade. From cooperative to competitive learning, MARL systems are mainly validated in game-theoretical environments and real-time game engines due to the inherent system complexity. Given the robustness of Q-based...

In this study, we consider the problem of motion planning for urban air mobility applications to generate a minimal snap trajectory and trajectory that cost minimal time to reach a goal location in the presence of dynamic geo-fences and uncertainties in the urban airspace. We have developed two separate approaches for this problem because designing...

This paper presents a multidisciplinary conceptual design framework for unmanned aerial vehicles based on artificial intelligence-driven analysis models. This approach leverages AI-driven analysis models that include aerodynamics, structural mass, and radar cross-section predictions to bring quantitative data to the initial design stage, enabling t...

This paper discusses the development of an adaptive Deep Reinforcement Learning solver, designed for centralised onground Tactical Conflict Resolution and applied within diverse in-cruise configurations of urban airspace. Our approach utilises a Multi-agent Reinforcement Learning algorithm with a shared policy framework, employing a Proximal Policy...

This book presented in detail how some key aspects in the design of guidance, navigation, and control systems for unmanned aerial vehicles (UAVs) have been addressed in recent years by experts in the field. This final chapter draws some conclusions on the state-of-the-art and discusses future research directions that embrace not only UAV technology...

The interest in agile maneuvering unmanned aerial vehicles (UAVs) specifically the quadrotor has increased considerably. The control of UAVs at high speed becomes a challenging task due to unmodeled aerodynamic forces and moments. In this study, position and attitude tracking controllers are presented in a structured cascaded fashion using incremen...

This paper provides a new method to nonlinear control theory, which is developed from the eigenvalue assignment method. The main purpose of this method is to locate the pointwise eigenvalues of the linear-like structure built by freezing the nonlinear systems at a given time instant in a desired disk region. Since the control requirements for the t...

Integrating autonomous unmanned aerial vehicles (UAVs) with fifth-generation (5G) networks presents a significant challenge due to network interference. UAVs’ high altitude and propagation conditions increase vulnerability to interference from neighbouring 5G base stations (gNBs) in the downlink direction. This paper proposes a novel deep reinforce...

Although existing visual-based navigation solutions for aerial applications provide outstanding results under nominal conditions, their performance is highly constrained by the lighting conditions, making them infeasible for real operations. With the main focus of addressing this limitation, and expanding the current operational range to include ex...

In this chapter, a fast chance-constrained trajectory generation strategy is presented that uses convex optimization and convex approximation of chance constraints to settle the problem of unmanned vehicle path planning. A path-length-optimal trajectory optimization model is developed for unmanned vehicles, taking into account pitch angle constrain...

This chapter investigates the optimal flight of aero-assisted reentry vehicles during the atmospheric entry flight phase while taking into account both deterministic and control chance constraints. We construct a chance-constrained optimal control model in order to depict the mission profile. However, standard numerical trajectory planning methods...

Conventional optimization methods have certain problems in finding the optimal solution. The feasible solution space of a trajectory optimization model may be constrained to a relatively limited corridor due to numerous mission-related constraints, easily leading to local minimum or infeasible solution identification. This section focuses on an att...

In this chapter, the problem of time-optimal reconnaissance trajectory design for the aeroassisted vehicle is taken into account. Unlike the vast majority of previously reported works, the feasibility of using the dynamic model of high-order aeroassisted vehicle to plan the optimal flight trajectory is discussed, so as to narrow the gap between the...

When encountering atmospheric or exo-atmospheric spacecraft flight, a well-designed trajectory is essential for making the flight stable and enhancing the guidance and control of the vehicle. Much research has focused on how to design suitable spacecraft trajectories available for various mission profiles. To optimize the flight trajectory, researc...

In this chapter, we study the optimal time-varying attitude control problem for rigid spacecraft with unknown system constraints and additive perturbations. A dual-loop cascaded tracking control framework is established by designing a new nonlinear tube-based robust model predictive control (TRMPC) algorithm. The proposed TRMPC algorithm explicitly...

This chapter focuses on the design of predictive control-based optimization method for addressing missile interception problems. Due to the nonlinearity or inherent limitations of the missile-target dynamics, it is often hard to design control algorithms with high accuracy and efficiency. To tackle this issue, a pseudo-spectral nonlinear receding h...

Over the past few decades, how to design a sophisticated guidance and control the (G &C) system for space and aerospace vehicles has been widely researched, which has increasingly drawn attention from all over the world and will continue to do so. As is known to all, there are various model uncertainties and environmental disturbances in G &C syste...

Advanced Air Mobility (AAM) is a concept that is expected to transform the current air transportation system and provide more flexibility, agility, and accessibility by extending the operations to urban environments. This study focuses on flight test, integration, and analysis considerations for the feasibility of the future AAM concept and showcas...

The emerging field of Advanced Air Mobility (AAM) holds great promise for revolutionizing transportation by enabling the efficient, safe, and sustainable movement of people and goods in urban and regional environments. AAM encompasses a wide range of electric vertical take-off and landing (eVTOL) aircraft and infrastructure that support their opera...

In this paper, we propose an AI-based methodology for estimating angle-of-attack and angle-of-sideslip without the need for traditional vanes and pitot-static systems. Our approach involves developing a custom neural-network model to represent the input-output relationship between air data and measurements from various sensors such as inertial meas...

This paper presents an intelligent conceptual design framework for the configuration selection of aerial vehicles. In this approach, the quantitative data is brought to the earliest stage of design utilizing AI-driven analysis models and it allows to choose the most suitable one among the possible configurations. Thanks to the design optimization c...

Reinforcement learning tree-based planning methods have been gaining popularity in the last few years due to their success in single-agent domains, where a perfect simulator model is available: for example, Go and chess strategic board games. This paper pretends to extend tree search algorithms to the multiagent setting in a decentralized structure...

Specifying the intended behaviour of autonomous systems is becoming increasingly important but is fraught with many challenges. This technical report provides an overview of existing work on specifications of autonomous systems and places a particular emphasis on formal specification, i.e. mathematically rigorous approaches to specification that re...

Reports on the activities of the CS Technical Committee on Aerospace Control.

In this study, an intelligent wargaming approach is proposed to evaluate the effectiveness of a military operation plan in terms of operational success and survivability of the assets. The proposed application is developed based on classical military decision making and planning (MDMP) workflow for ease of implementation into the real-world applica...

The next generation low-cost modular unmanned combat aerial vehicles (UCAVs) provide the opportunity to implement innovative solutions to complex tasks, while also bringing new challenges in design, production, and certification subjects. Solving these problems with tools that provide fast modeling in line with the digital twin concept is possible....

Technological breakthroughs in the Internet of Things (IoT) easily promote smart lives for humans by connecting everything through the Internet. The de facto standardised IoT routing strategy is the routing protocol for low-power and lossy networks (RPL), which is applied in various heterogeneous IoT applications. Hence, the increase in reliance on...

The present paper formalises the development of a co-simulation environment aimed at demonstrating a number of advanced U-space services for the Air Mobility Urban-Large Experimental Demonstrations (AMU-LED) project. The environment has a visionary build that addresses Urban Air Mobility (UAM) challenges to support the High/Standard Performance Veh...

This article presents an integrated approach for on-demand dynamic capacity management (DCM) service to be offered in U-space. The approach involves three main threads, including flight planning (demand), airspace configuration (capacity), and demand-capacity balancing (DCB). The flight planning thread produces unmanned aerial systems (UAS) traject...

Deep reinforcement learning (DRL) has been widely studied in single agent learning but require further development and understanding in the multi-agent field. As one of the most complex swarming settings, competitive learning evaluates the performance of multiple teams of agents cooperating to achieve certain goals while surpassing the rest of grou...

Disaster management has always been a struggle due to unpredictable changing conditions and chaotic occurrences that require real-time adaption. Highly optimized missions and robust systems mitigate uncertainty effects and improve notoriously success rates. This paper brings a niching hybrid human–machine system that combines UAVs fast responsivene...

Advanced Air Mobility (AAM) is expected to revolutionize the future of general transportation expanding the conventional notion of air traffic to include several services carried out by autonomous aerial platforms. However, the significant challenges associated with such complex scenarios require the introduction of sophisticated technologies able...

The Sequential Monte Carlo Probability Hypothesis Density (SMC-PHD) filter is a permissive multi-target tracker, performing state estimation through particle filtering with implicit data association. This filter is thus effective even in presence of clutter and nonlinear dynamics, while remaining tractable for real-time applications due to its comp...

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 meth...

The Internet of Things (IoT) connects billions of sensors to share and collect data at any time and place. The Advanced Metering Infrastructure (AMI) is one of the most important IoT applications. IoT supports AMI to collect data from smart sensors, analyse and measure abnormalities in the energy consumption pattern of sensors. However, two-way com...

View Video Presentation: https://doi.org/10.2514/6.2022-0879.vid Tilt-rotor vertical takeoff and landing aerial vehicles have been gaining popularity in urban air mobility applications because of their ability in performing both hover and forward flight regimes. This hybrid concept leads energy efficiency which is quite important to obtain a profit...

View Video Presentation: https://doi.org/10.2514/6.2022-2102.vid In this paper we consider the application of Safe Deep Reinforcement Learning in the context of a trustworthy autonomous Airborne Collision Avoidance System. A simple 2D airspace model is defined, in which a hypothetical air vehicle attempts to fly to a given waypoint while autonomous...

View Video Presentation: https://doi.org/10.2514/6.2022-2104.vid n this paper, a reinforcement learning-based decoy deployment strategy is proposed to protect naval platforms against radar seeker-equipped anti-ship missiles. The decoy system consists of a rotary-wing unmanned aerial vehicle (UAV) and an integrated onboard jammer. This decoy concept...

View Video Presentation: https://doi.org/10.2514/6.2022-1839.vid Uncertainty and partial or unknown information about environment dynamics have led reward-based methods to play a key role in the Single-Agent and Multi-Agent Learning problem. Tree-based planning approaches such as Monte Carlo Tree Search algorithm have been a striking success in sin...

In this work, a computationally efficient and high-precision nonlinear aerodynamic configuration analysis method is presented for both design optimization and mathematical modeling of small unmanned aerial vehicles. First, we have developed a novel nonlinear lifting line method which (a) provides very good match for the pre- and post-stall aerodyna...

In this study, reinforcement learning (RL)-based centralized path planning is performed for an unmanned combat aerial vehicle (UCAV) fleet in a human-made hostile environment. The proposed method provides a novel approach in which closing speed and approximate time-to-go terms are used in the reward function to obtain cooperative motion while ensur...

The growth of the Internet of Things (IoT) offers numerous opportunities for developing industrial applications such as smart grids, smart cities, smart manufacturers, etc. By utilising these opportunities, businesses engage in creating the Industrial Internet of Things (IIoT). IoT is vulnerable to hacks and, therefore, requires various techniques...

This paper presents a physics-guided deep neural network framework to estimate fuel consumption of an aircraft. The framework aims to improve data-driven models’ consistency in flight regimes that are not covered by data. In particular, we guide the neural network with the equations that represent fuel flow dynamics. In addition to the empirical er...

Presents the editorial for this issue of the publication.

In this study, we develop a machine learning based fleet autonomy for Unmanned Combat Aerial Vehicles (UCAVs) utilizing a synthetic simulation-based wargame environment. Aircraft survivability is modeled as Markov processes. Mission success metrics are developed to introduce collision avoidance and survival probability of the fleet. Flight path pla...

In this paper, we present a brief review of the state of the art physics informed deep learning methodology and examine its applicability, limits, advantages, and disadvantages via several applications. The main advantage of this method is that it can predict the solution of the partial differential equations by using only boundary and initial cond...

High-Altitude Pseudo-Satellites (HAPS) have been identified as a potential option to either supplement or replace various military communications services. A network of HAPS aircraft operating at an altitude of 20km offers localized, high performance services to military operations. The intention of this work is to investigate whether a network of...

In this study, we present a reinforcement learning (RL)‐based flight control system design method to improve the transient response performance of a closed‐loop reference model (CRM) adaptive control system. The methodology, known as RL‐CRM, relies on the generation of a dynamic adaption strategy by implementing RL on the variable factor in the fee...

In this paper, we provide a system identification, model stitching and model-based flight control system design methodology for an agile maneuvering quadrotor micro aerial vehicle (MAV) technology demonstrator platform. The proposed MAV is designed to perform agile maneuvers in hover/low-speed and fast forward flight conditions in which significant...

In this paper, we present a deep learning based surrogate model to determine non-linear aerodynamic characteristics of UAVs. The main advantage of this model is that it can predict the aerodynamic properties of the configurations very quickly by using only geometric configuration parameters without the need for any special input data or pre-process...

This paper applies machine learning techniques to improve flight efficiency. Specifically, we focus on two distinct problems: uncertainties in aircraft performance models and uncertainties in wind. In this sense, this paper proposed methodologies to improve baseline models for fuel flow and wind estimations are via operational data. We utilize Base...

In this work, we develop a new non-linear lifting line method for wings and similar lifting surfaces using the Prandtl’s classical lifting line theory. Specifically, the developed method is able to determine 3D maximum lift coefficient and pre- and post-stall aerodynamic behavior of a wing by using its section’s non-linear 2D lift curve obtained ex...

In this paper, a model-based flight control system design approach is proposed for a micro aerial vehicle (MAV) using integrated flight testing and hardware-in-the-loop (HIL) simulation. This approach relies on adaptation of system identification and control system design methodologies from the manned aircraft domain. The MAV is specifically design...