Dynamic Hot Spot Prediction by Learning Spatial- Temporal Utilization of Taxiway Intersections

Ali, Hasnain; Delair, Raphael; Pham, Duc-Thinh; Alam, Sameer; Schultz, Michael

doi:10.1109/aida-at48540.2020.9049186

Cited by 10 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…scenario (corresponding to average traffic density of 40 aircraft/hour). This is equivalent to the average traffic density observed at mid to large sized airports like Singapore Changi [7], Charles de Gaulle (Paris; CDG) and Charlotte Douglas International (North Carolina; CLT). However, in reality, airside traffic density varies throughout the day.…”

Section: Methodsmentioning

confidence: 94%

“…1), ground trajectories of arrivals face fewer obstructions in their intended movement toward gates. This lowers chances of formation of congestion hotspots in the airside network, which in turn reduces Air Traffic Controller's (ATCO) workload [7]. Recent approaches have employed handcrafted multiinteger linear programming models [8], cell transmission models [9], queuing models [10], statistical models [7] etc.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Reinforcement Learning Based Airport Departure Metering

Ali

Thinh

Alam

2021

2021 IEEE International Intelligent Transportation Systems Conference (ITSC)

Self Cite

View full text Add to dashboard Cite

Airport taxi delays adversely affect airports and airlines around the world in terms of congestion, operational workload, and environmental emissions. Departure Metering (DM) is a promising approach to contain taxi delays by controlling departure pushback times. The key idea behind DM is to transfer aircraft waiting time from taxiways to gates. State-of-the-art DM methods use model-based control policies that rely on airside departure modeling to obtain simplified analytical equations. Consequently, these models fail to capture non-stationarity existing in the complex airside operations and the policies perform poorly under uncertainties. In this work, we propose model-free and learning-based DM using Deep Reinforcement Learning (DRL) approach to reduce taxi delays while meeting flight schedule constraints. We cast the DM problem in an MDP framework and develop a representative airport simulator to simulate airside operations and evaluate the learnt DM policy. For effective state representation, we introduce features to capture both local and airport-wide congestion levels. Finally, the performance of multiple agentssharing the same trained policy, is evaluated on different traffic densities. The proposed approach shows a reduction of up to 25% in taxi delays in medium traffic scenarios. Moreover, upon experiencing increased traffic density, taxi time savings achieved by proposed algorithm significantly increase while the average gate holding times do not increase as much. Results demonstrate that DRL can learn an effective DM policy to better manage airside traffic and contain congestion on the taxiways.

show abstract

Section: Methodsmentioning

confidence: 94%

Section: Introductionmentioning

confidence: 99%

Deep Reinforcement Learning Based Airport Departure Metering

Ali

Thinh

Alam

2021

2021 IEEE International Intelligent Transportation Systems Conference (ITSC)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Each trajectory represents aircraft movements in spatial and temporal domains. It is, however, observed that the raw data contains a lot of noise (irregularity in positional coordinates over time) and missing information which is pre-processed, map matched and cleaned [7], [39], [40]. Post cleaning, 60% of the data remains which is used for simulation purposes (refer TABLE I).…”

Section: B Extracting Aircraft Taxi Routes Using A-smgcs Datamentioning

confidence: 99%

“…1), arrivals face fewer obstructions in their intended movement toward gates. This brings down the likelihood of formation of congestion hotspots in the airside network, which in turn reduces Air Trafc Controller's (ATCO) workload [7].…”

Section: Introductionmentioning

confidence: 99%