Aircraft taxi time prediction: Feature importance and their implications

Wang, Xinwei; Brownlee, Alexander E. I.; Woodward, John R.; Weiszer, Michal; Mahfouf, Mahdi; Chen, Jun

doi:10.1016/j.trc.2020.102892

Cited by 41 publications

(30 citation statements)

References 37 publications

(82 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The average absolute error of the taxiing time was 51 s, with that of the taxiing time for arrival and departure being 34 and 68 s, respectively. This shows high and acceptable accuracy [52] and a convincing basis for further calibrating the congestion cost functions of the runways and aprons.…”

Section: Verification Of Baseline Simulation Environmentmentioning

confidence: 71%

A Holistic Approach for Optimal Pre-Planning of Multi-Path Standardized Taxiing Routes

et al. 2021

View full text Add to dashboard Cite

Standardized Taxiing Routes (STRs) are defined as published taxiing-in and taxiing-out routes for aircraft between gates and runways, aiming at improving ground movement safety at busy or complex airports. Most of the STRs specify only one path between each O–D (Origin–Destination) pair, which compromises the flexibility of route choice in time-varying traffic scenarios. In this paper, we present a holistic approach of planning and validating Multi-Path Standardized Taxiing Routes (MPSTRs) based on System-Optimal Traffic Assignment (SOTA), by firstly defining the flow-based congestion cost of runway, taxiway, and sectorized apron operation at a macroscopic level. A human-in-the-loop experiment comprised of six operation scenarios follows to investigate the impact of the pre-planned MPSTRs on human controllers’ performance. Results confirm the positive effect of the MPSTRs on taxiing performance without increasing the controllers’ workload, which also implies that the MPSTRs would be a promising approach for balancing safety and efficiency for the STRs-based taxiing operation and dynamic routing optimization without substantial investment.

show abstract

Section: Verification Of Baseline Simulation Environmentmentioning

confidence: 71%

A Holistic Approach for Optimal Pre-Planning of Multi-Path Standardized Taxiing Routes

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The Principal Component Analysis (PCA) was utilized in this study to extract the maximum amount of information from the features, to reduce the number of features, and to avoid any multicollinearity among these features, which is evident in the correlation matrix in Table 2. The PCA is a commonly used statistical technique that adopts an orthogonal transformation to obtain uncorrelated features from correlated features (Jolliffe 2002). The uncorrelated features, which are the output of the PCA, are called Principal Components (PCs).…”

Section: Data Reductionmentioning

confidence: 99%

“…The first PC includes the highest variability in the data followed by the second PC, and so on. For more details about the PCA, readers are referred to (Jolliffe 2002). The PCs used in this study were selected based on an eigenvalue of equal or greater than 1.…”

Section: Data Reductionmentioning

confidence: 99%

Human-like speed modeling for autonomous vehicles during car-following at intersections

Tawfeek

2022

Can. J. Civ. Eng.

View full text Add to dashboard Cite

This study aims at modelling drivers’ speed in car-following during braking situations at intersections to estimate a safe comfortable human-like speed at the minimum car-following distance for Autonomous Vehicles (AV). Several car-following behavioral measures at different times before reaching the minimum following distance and the intersection control type (signalized or unsignalized) were extracted to train the model using three machine learning techniques. The results showed that the XGBoost model is superior when compared to other techniques with R-squared values of 0.99 and 0.97 for training and testing datasets. The results also indicated that the control type impact driver speed at the minimum following distance. The modelled speed will provide more comfortable speed to the AV riders and will not violate the expectations of the surrounding traditional vehicle drivers. Also, the proposed model can be adopted to enhance current car-following models by considering the effect of intersections and its control type.

show abstract

“…Concerning learning assurance, xAI techniques are a key element to address the explainability challenge and they have been the subject of many research papers in recent years. Of the papers that we reviewed, [43] [12] and [44] used model-agnostic techniques for feature importance, and others such as [45] used tree-ensemble post-hoc explanation for simplification and feature relevance. [40] have done a really extensive and comprehensive review of xAI methods and many ATM research papers reviewed are starting to incorporate such techniques in order to explain the performance of their chosen algorithms.…”

Section: B Technical Robustness and Learning Assurancementioning

confidence: 99%

An Explainable Artificial Intelligence (xAI) Framework for Improving Trust in Automated ATM Tools

Hernandez

Ayo

Panagiotakopoulos

2021

2021 IEEE/AIAA 40th Digital Avionics Systems Conference (DASC)

View full text Add to dashboard Cite

With the increased use of intelligent Decision Support Tools in Air Traffic Management (ATM) and inclusion of non-traditional entities, regulators and end users need assurance that new technologies such as Artificial Intelligence (AI) and Machine Learning (ML) are trustworthy and safe. Although there is a wide amount of research on the technologies themselves, there seem to be a gap between research projects and practical implementation due to different regulatory and practical challenges including the need for transparency and explainability of solutions. In order to help address these challenges, a novel framework to enable trust on AI-based automated solutions is presented based on current guidelines and end user feedback. Finally, recommendations are provided to bridge the gap between research and implementation of AI and ML-based solutions using our framework as a mechanism to aid advances of AI technology within ATM.

show abstract

Aircraft taxi time prediction: Feature importance and their implications

Cited by 41 publications

References 37 publications

A Holistic Approach for Optimal Pre-Planning of Multi-Path Standardized Taxiing Routes

A Holistic Approach for Optimal Pre-Planning of Multi-Path Standardized Taxiing Routes

Human-like speed modeling for autonomous vehicles during car-following at intersections

An Explainable Artificial Intelligence (xAI) Framework for Improving Trust in Automated ATM Tools

Contact Info

Product

Resources

About