Machine Learning-Based Traffic Management Model for UAS Instantaneous Density Prediction in an Urban Area

Zhao, Ziyi; Luo, Chen; Solomon, Adrian; Basti, Franco; Caicedo, Carlos; Gursoy, M. Cenk; Qiu, Qinru

doi:10.1109/dasc50938.2020.9256471

Cited by 5 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In predictions of airspace-complexity values 40 min in advance, the results showed a Mean Absolute Error (MAE) for the proposed model of 0.08. Image-based trajectory data (as inputs to a CNN and LSTM cascaded deep neural network), meanwhile, were deployed by Zhao et al [23], who consequently predicted UAV instantaneous density. This entailed a segmentation approach, with a concomitant reliance on historical data.…”

Section: Related Workmentioning

confidence: 99%

“…While this approach addresses static data, it fails to consider real-time variables [22], and research on the prediction of air traffic flow for UTM systems is limited. Most researchers have focused on predicting future traffic densities based on historical data [23]. Moreover, they assume a static environment, with fixed start and destination points for vehicles, as well as fixed airspace constraints regarding no-fly zones (NFZ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Architecture for UAV Traffic-Density Prediction

Alharbi

Petrunin

Panagiotakopoulos

2023

Drones

View full text Add to dashboard Cite

: The research community has paid great attention to the prediction of air traffic flows. Nonetheless, research examining the prediction of air traffic patterns for unmanned aircraft traffic management (UTM) is relatively sparse at present. Thus, this paper proposes a one-dimensional convolutional neural network and encoder-decoder LSTM framework to integrate air traffic flow prediction with the intrinsic complexity metric. This adapted complexity metric takes into account the important differences between ATM and UTM operations, such as dynamic flow structures and airspace density. Additionally, the proposed methodology has been evaluated and verified in a simulation scenario environment, in which a drone delivery system that is considered essential in the delivery of COVID-19 sample tests, package delivery services from multiple post offices, an inspection of the railway infrastructure and fire-surveillance tasks. Moreover, the prediction model also considers the impacts of other significant factors, including emergency UTM operations, static no-fly zones (NFZs), and variations in weather conditions. The results show that the proposed model achieves the smallest RMSE value in all scenarios compared to other approaches. Specifically, the prediction error of the proposed model is 8.34% lower than the shallow neural network (on average) and 19.87% lower than the regression model on average.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep Learning Architecture for UAV Traffic-Density Prediction

Alharbi

Petrunin

Panagiotakopoulos

2023

Drones

View full text Add to dashboard Cite

show abstract

“…It was observed that the majority of publications are related to road or highway traffic flow or ATFP for aircrafts. UAV navigation, obstacle avoidance, and/or control approaches are some of the issues investigated by the current works [6], [16].…”

Section: Machine Learning Algorithms For Atfpmentioning

confidence: 99%

“…The work presented in [6] used the image-based trajectory data as input to convolutional neural network (CNN) and LSTM cascaded deep neural network and predicted the UAV instantaneous density using the segmentation method that relies on historical data. Although this work used correlation as the metrics for the evaluation of the proposed network and established a continuous prediction time horizon of one hour with good correlation scores, it did not take into account the realistic or practical missions as considered in this current work, nor did it take into account the effect of dynamical airspace structural constraints such as recreational areas and airfields or the effects of UAV prioritization; there is always a need to set the priority list for different missions The effects of weather constraints such as adverse wind, rain and extreme weather conditions were also not considered in this work.…”

Section: Machine Learning Algorithms For Atfpmentioning

confidence: 99%

“…However, research about prediction of air traffic flow for Uncrewed Aircraft Traffic Management (UTM) systems is limited. Most researchers focused on predicting future traffic density based upon historical data [6]. They assumed a static environment with fixed start and destination points of vehicles, as well as fixed airspace constraints regarding no-fly zones (NFZ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Traffic Flow Prediction for UTM Application: A Deep Learning Approach

Alharbi

Petrunin

Panagiotakopoulos

2022

2022 IEEE/AIAA 41st Digital Avionics Systems Conference (DASC)

View full text Add to dashboard Cite

Over the past few years, the research community has focused greatly on predicting air traffic flows, yielding remarkable outcomes. We found that existing literature in the field mainly covers prediction of air traffic flows for conventional aircraft. However, there is limited research about prediction of air traffic flows for Uncrewed Aircraft Traffic Management (UTM). This research study proposes a deep learning-based approach to predict air traffic congestion in the context of UTM over a period of three minutes. The use of the model aims to address congestion considering air traffic uncertainties instead of addressing the conventional issues of trajectory prediction or conflict detection and resolution. Our model also considers the influence of recreational users who fly UAVs at random times, during the execution of the above essential missions. Further, the effects of airspace structure configurations like static No-Fly Zones (NFZ), airfields with variable availability for drone flights, recreational areas, emergency UTM operation and environmental factors such as weather conditions have also been studied. The proposed model shows better performance compared to other approaches such as the Shallow neural networks and regression models.

show abstract