Research paper accepted by Transportation Research Part C
Collisions during airport surface operations can create risk of injury to passengers, crew or airport personnel and damage to aircraft and ground equipment. A machine learning model that is able to predict the trajectories of ground objects can help to diminish the occurrences of such collision events. In this paper, we pursue this objective by building a spatial-temporal graph convolutional neural network (STG-CNN) model to predict the movement of objects/vehicles on the airport surface. The methodology adopted in this paper consists of three steps: (1) Raw data processing: leverage Apache Spark to parse a large volume of raw data in Flight Information Exchange Model (FIXM) format streamed from the Surface Movement Event Service (SMES) for the purpose of deriving historical trajectory associated with each object on the ground; (2.1) Graph-based representations of ground object movements: build graph-based representations to characterize the movements of ground objects over time, where graph edges are used capture the spatial relationships of ground objects with each other explicitly; (2.2) Trajectory forecasts of all ground objects: combine STG-CNN with Time-Extrapolator Convolution Neural Network (TXP-CNN) to forecast the future trajectories of all the ground objects as a whole; and (3) Separation distance-based safety assessment: define a probabilistic separation distance-based metric to assess the safety of airport surface movements. The performance of the developed model for trajectory prediction of ground objects is validated at two airports with varying scales: Hartsfield-Jackson Atlanta International Airport and LaGuardia airport, under two different scenarios (peak hour and off-peak hour). Two quantitative performance metrics — Average Displacement Error (ADE) and Final Displacement Error (FDE) are used to compare the prediction performance of the proposed model with an alternative method. The computational results indicate that the developed method has an ADE within the range [7.55, 9.33], and it significantly outperforms an alternative approach that combines a STG-CNN with Convolutional Long Short-Term Memory (ConvLSTM) neural network with an ADE of [15.79, 16.89] in airport surface movement prediction, thus facilitating more accurate safety assessment during airport surface operations.
Research paper accepted by Advanced Engineering Informatics
Teams formulated by aviation professionals are essential in maintaining a safe and efficient aerodrome environment. Nonetheless, the shared situational awareness between the flight crews under adverse weather conditions might be impaired. This research aims to evaluate the impact of a proposed enhancement in communication protocol on cognitive workload and develop a human-centred classification model to identify hazardous meteorological conditions. Thirty groups of subjects completed four post-landing taxiing tasks under two visibility conditions (CAVOK/CAT IIIA) while two different communication protocols (presence/absence of turning direction information) were adopted by the air traffic control officer (ATCOs). Electroencephalography (EEG) and the NASA Task Load Index were respectively used to reflect the pilot’s mental state and to evaluate the pilot’s mental workload subjectively. Results indicated that impaired visibility increases the subjective workload significantly, while the inclusion of turning direction information in the ATCO’s instruction would not significantly intensify their cognitive workload. Mutual information was used to quantitatively assess the shared situational awareness between the pilot flying and the pilot monitoring. Finally, this research proposes a humancentred approach to identify potentially hazardous weather conditions from EEG power spectral densities with Bayesian neural networks (BNN). The classification model has outperformed other baseline algorithms with an accuracy of 66.5%, an F1 score of 61.4%, and an area under the ROC of 0.749. Using the concept of explainable AI with Shapley Additive Explanations (SHAP) values, the exploration of latent mental patterns formulates novel knowledge to gain insights into the vital physiological indicators of the pilots in response to different scenarios from the BNN model. In the long term, the model facilitates the decision regarding the necessity of providing automation and decision-making aids to pilots.
Research project funded by Early Career Scheme (ECS) of Research Grants Council
The past few years have witnessed the rapid development of artificial intelligence (AI) and machine learning (ML) in solving long-standing problems. AI/ML has played an indispensable role in profoundly transforming business, transportation, and finance. However, the adoption of AI/ML in risk-sensitive areas is still in its infancy because AI/ML systems exhibit fundamental limits and practical shortcomings: the field of AI/ML lacks a rigorous framework for reasoning about risk, uncertainty, and their potentially catastrophic outcomes, while safety and quality implications are top priorities in practice across a broad array of high-stakes applications that range from medical diagnosis to aerospace systems. Since the consequences of AI/ML system failures in life and safety-critical applications can be disastrous, it is becoming abundantly clear that, reasoning about uncertainty and risk will become a cornerstone when adopting AI/ML systems in large-scale risk-sensitive applications. As ML systems face varied risks arising from the input data (e.g., data bias, dataset shift etc.) as well as the ML model (e.g., model bias, model misspecification, etc.), the goal of this project is to develop a systematic risk-aware ML framework that consists of a series of control checkpoints to safeguard ML systems against potential risks to increase the credibility of adopting ML system in critical applications. Towards this goal, this project consists of three coherent tasks: (1) develop an integrated approach for data quality monitoring by combining feature-based anomaly detection technique with outcome-based uncertainty measure. The developed integrated approach will produce a composite probabilistic risk indicator to reveal input data quality; (2) develop a two-stage ML-based framework to estimate model reliability for individual prediction (MRIP). MRIP characterizes the probability of the observed difference between model prediction and actual value being within a tiny interval while model input varies within a small prescribed range, and it provides an individualized estimation on model prediction reliability for each input x. (3) develop a ML model to learn system-level risk. A ML model will be developed to map data-level and model-level risk indicators derived in the first two tasks to a risk measure at the system level. The proposed effort has profound practical implications, the risk-aware framework will act as an effective safety barrier in preventing ML models from making over-confident predictions on cases that are either too noisy, anomalous, outside the domain of the trained model, or with low model prediction reliability, thus facilitating safe and reliable adoption of ML systems in critical applications.
