Machine Learning for Improving Air Mobility under Emergency Situations
Emergency situations in aviation pose serious risks to life and result in huge negative impacts on air mobility, causing a significant economic and reputation loss to airlines and airports. However, the decisions to deal with emergencies are usually made by flight dispatchers according to their experience, and they merely consider local-view optimization. Therefore, there is an urgent need to design a decision-making assistant system to alleviate the negative impact of perturbations on aviation air mobility in the global-view perspective. In this project, the research team will develop a framework based on machine learning that captures the patterns of emergency situations and optimizes the operation schedules quickly and accurately for maximum air mobility efficiency at both micro-level and macro-level. The team will utilize multi-source data and leverage deep learning models to predict the consequence of emergency events considering the spatial-temporal characteristics of the events. Based on a prediction model, the team will optimize air mobility output by adopting a deep multi-agent reinforcement learning model. The goal is to provide pre-alert and decision-aid system for passengers and airport staff when emergency events occur, and to adjust the original schedule for quick recovery of disrupted air mobility.
Language
- English
Project
- Status: Completed
- Funding: $330000
-
Contract Numbers:
69A3551747125
-
Sponsor Organizations:
Center for Advanced Transportation Mobility
North Carolina Agricultural and Technical State University
Greensboro, NC United States 27411Office of the Assistant Secretary for Research and Technology
University Transportation Centers Program
Department of Transportation
Washington, DC United States 20590 -
Managing Organizations:
North Carolina A&T State University
1601 E. Market Street
Greensboro, NC United States 27411 -
Performing Organizations:
Embry-Riddle Aeronautical University
600 S. Clyde Morris Boulevard
Daytona Beach, Fl United States 32114 -
Principal Investigators:
Song, Houbing
Liu, Dahai
- Start Date: 20211001
- Expected Completion Date: 20230731
- Actual Completion Date: 20240101
- USDOT Program: University Transportation Centers Program
Subject/Index Terms
- TRT Terms: Air traffic; Aviation safety; Decision support systems; Emergencies; Machine learning; Service disruption
- Subject Areas: Aviation; Operations and Traffic Management; Planning and Forecasting; Safety and Human Factors; Security and Emergencies;
Filing Info
- Accession Number: 01841346
- Record Type: Research project
- Source Agency: Center for Advanced Transportation Mobility
- Contract Numbers: 69A3551747125
- Files: UTC, RIP
- Created Date: Apr 2 2022 11:16AM