Resurgent interest in artificial intelligence (AI) techniques focused research attention on their application in aviation systems including air traffic management (ATM), air traffic flow management (ATFM), and unmanned aerial systems traffic management (UTM). By considering a novel cognitive human–machine interface (HMI), configured via machine learning, we examined the requirements for such techniques to be deployed operationally in an ATM system, exploring aspects of vendor verification, regulatory certification, and end-user acceptance. We conclude that research into related fields such as explainable AI (XAI) and computer-aided verification needs to keep pace with applied AI research in order to close the research gaps that could hinder operational deployment. Furthermore, we postulate that the increasing levels of automation and autonomy introduced by AI techniques will eventually subject ATM systems to certification requirements, and we propose a means by which ground-based ATM systems can be accommodated into the existing certification framework for aviation systems.
Advances in unmanned aircraft systems (UAS) have paved the way for progressively higher levels of intelligence and autonomy, supporting new modes of operation, such as the one-to-many (OTM) concept, where a single human operator is responsible for monitoring and coordinating the tasks of multiple unmanned aerial vehicles (UAVs). This paper presents the development and evaluation of cognitive human-machine interfaces and interactions (CHMI2) supporting adaptive automation in OTM applications. A CHMI2 system comprises a network of neurophysiological sensors and machine-learning based models for inferring user cognitive states, as well as the adaptation engine containing a set of transition logics for control/display functions and discrete autonomy levels. Models of the user’s cognitive states are trained on past performance and neurophysiological data during an offline calibration phase, and subsequently used in the online adaptation phase for real-time inference of these cognitive states. To investigate adaptive automation in OTM applications, a scenario involving bushfire detection was developed where a single human operator is responsible for tasking multiple UAV platforms to search for and localize bushfires over a wide area. We present the architecture and design of the UAS simulation environment that was developed, together with various human-machine interface (HMI) formats and functions, to evaluate the CHMI2 system’s feasibility through human-in-the-loop (HITL) experiments. The CHMI2 module was subsequently integrated into the simulation environment, providing the sensing, inference, and adaptation capabilities needed to realise adaptive automation. HITL experiments were performed to verify the CHMI2 module’s functionalities in the offline calibration and online adaptation phases. In particular, results from the online adaptation phase showed that the system was able to support real-time inference and human-machine interface and interaction (HMI2) adaptation. However, the accuracy of the inferred workload was variable across the different participants (with a root mean squared error (RMSE) ranging from 0.2 to 0.6), partly due to the reduced number of neurophysiological features available as real-time inputs and also due to limited training stages in the offline calibration phase. To improve the performance of the system, future work will investigate the use of alternative machine learning techniques, additional neurophysiological input features, and a more extensive training stage.
Recent evolutions of the Unmanned Aircraft Systems (UAS) Traffic Management (UTM) concept are driving the introduction of new airspace structures and classifications, which must be suitable for low-altitude airspace and provide the required level of safety and flexibility, particularly in dense urban and suburban areas. Therefore, airspace classifications and structures need to evolve based on appropriate performance metrics, while new models and tools are needed to address UTM operational requirements, with an increasing focus on the coexistence of manned and unmanned Urban Air Mobility (UAM) vehicles and associated Communication, Navigation and Surveillance (CNS) infrastructure. This paper presents a novel airspace model for UTM adopting Performance-Based Operation (PBO) criteria, and specifically addressing urban airspace requirements. In particular, a novel airspace discretisation methodology is introduced, which allows dynamic management of airspace resources based on navigation and surveillance performance. Additionally, an airspace sectorisation methodology is developed balancing the trade-off between communication overhead and computational complexity of trajectory planning and re-planning. Two simulation case studies are conducted: over the skyline and below the skyline in Melbourne central business district, utilising Global Navigation Satellite Systems (GNSS) and Automatic Dependent Surveillance-Broadcast (ADS-B). The results confirm that the proposed airspace sectorisation methodology promotes operational safety and efficiency and enhances the UTM operators’ situational awareness under dense traffic conditions introducing a new effective 3D airspace visualisation scheme, which is suitable both for mission planning and pre-tactical UTM operations. Additionally, the proposed performance-based methodology can accommodate the diversity of infrastructure and vehicle performance requirements currently envisaged in the UTM context. This facilitates the adoption of this methodology for low-level airspace integration of UAS (which may differ significantly in terms of their avionics CNS capabilities) and set foundations for future work on tactical online UTM operations.
27 June 2018 in IEEE Transactions on Aerospace and Electronic Systems
Avionics and Air Traffic Management (ATM) systems are evolving with the introduction of progressively higher levels of automation, towards attaining the ambitious operational, technical and safety enhancements required to sustain the present growth of global air traffic. This article presents novel 4-Dimensional Trajectory (4DT) functionalities that are being developed for integration in ATM and avionics systems to support Trajectory Based Operations (TBO). The 4DT planning process, which is the main focus of the article, is supported by a custom multi-objective variant of state-of-the-art optimal control algorithms, incorporating various operational, economic and environmental factors. Capitalizing on the higher theoretical accuracy offered by optimal control algorithms compared to other methods, a key feature of the proposed approach is the introduction of a post-processing stage to ensure that the mathematically optimal trajectories are translated into a set of standardized 4DT descriptors, which can be flown by state-of-the-art automatic flight control systems. Additionally, to support air-ground 4DT intent negotiation and validation in the TBO context, the 4DT post-processing ensures that optimal trajectories are synthetically described by a limited number of parameters, minimizing the bandwidth requirements imposed on airborne data links. Simulation-based verification activities addressing operational efficiency improvements and computational performance in the terminal area ATM context support the viability of the proposed 4DT planning functionality for online tactical TBO.
Intelligent automation and trusted autonomy are being introduced in aerospace cyber-physical systems to support diverse tasks including data processing, decision-making, information sharing and mission execution. Due to the increasing level of integration/collaboration between humans and automation in these tasks, the operational performance of closed-loop human-machine systems can be enhanced when the machine monitors the operator’s cognitive states and adapts to them in order to maximise the effectiveness of the Human-Machine Interfaces and Interactions (HMI2). Technological developments have led to neurophysiological observations becoming a reliable methodology to evaluate the human operator’s states using a variety of wearable and remote sensors. The adoption of sensor networks can be seen as an evolution of this approach, as there are notable advantages if these sensors collect and exchange data in real-time, while their operation is controlled remotely and synchronised. This paper discusses recent advances in sensor networks for aerospace cyber-physical systems, focusing on Cognitive HMI2 (CHMI2) implementations. The key neurophysiological measurements used in this context and their relationship with the operator’s cognitive states are discussed. Suitable data analysis techniques based on machine learning and statistical inference are also presented, as these techniques allow processing both neurophysiological and operational data to obtain accurate cognitive state estimations. Lastly, to support the development of sensor networks for CHMI2 applications, the paper addresses the performance characterisation of various state-of-the-art sensors and the propagation of measurement uncertainties through a machine learning-based inference engine. Results show that a proper sensor selection and integration can support the implementation of effective human-machine systems for various challenging aerospace applications, including Air Traffic Management (ATM), commercial airliner Single-Pilot Operations (SIPO), one-to-many Unmanned Aircraft Systems (UAS), and space operations management.
Collision risk modelling has a long history in the aviation industry, with mature models currently utilised for the strategic planning of airspace sectors and air routes. However, the progressive introduction of Unmanned Aircraft Systems (UAS) and other forms of air mobility poses new challenges, compounded by a growing need to address both offline and online operational requirements. To address the associated gaps in the existing airspace risk assessment models, this article proposes a comprehensive risk management framework, which relies on a novel methodology to model UAS collision risk in all classes of airspace. This methodology inherently accounts for the performance of Communication, Navigation and Surveillance (CNS) systems, and, as such, it can be applied to both strategic and tactical operational timeframes. Additionally, the proposed approach can be applied inversely to determine CNS performance requirements given a target value of collision probability. This new risk assessment methodology is based on a rigorous analysis of the CNS error characteristics and transformation of the associated models into the spatial domain to generate a protection volume around each predicted air traffic conflict. Additionally, a methodology to quickly and conservatively evaluate the multi-integral formulation of collision probability is introduced. The validity of the proposed framework is tested using representative CNS performance parameters in two simulation case studies targeting, respectively, a terminal manoeuvring area and an enroute scenario.