Hybrid AI-Based Demand-Capacity Balancing for UAS Traffic Management and Urban Air Mobility

Xie, Yibing; Gardi, Alessandro; Sabatini, Roberto

doi:10.2514/6.2021-2325

Cited by 3 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This integrated approach produces an optimal solution that minimizes operational costs while maintaining airspace thresholds for traffic density. To accomplish the DCB mission in dense urban airspace, a novel framework [129] is presented, namely a hybrid AI algorithm architecture based on Deep Q Learning (DQN) + GA. To ensure optimal performance of strategic decision-making components, the hybrid AI architecture utilizes current state data for various factors, including UAV operating states, airspace states, flow management states, and low-altitude airspace environmental changes. Although the above studies showed promising results by providing effective DCB solutions to the UTM system, these proposed approaches did not provide more details on how it enhances the efficiency of UTM airspace by balancing capacity and safety.…”

Section: Comparison Of the Proposed Model With Other Approachesmentioning

confidence: 99%

“…We also included a maximum capacity efficiency figure of merit based on individual scheme data. Table 9 below shows the remarks and weights assigned to various factors for the three methodologies presented in [111,129], and this XAI DCM. It can be observed from the comparison table that the proposed XAI DCM surpasses the [111,129] methodologies based on more realistic airspace considerations and thus present an overall weight factor of 81% as compared to the above methodologies with 55% and 40%, respectively.…”

Section: Comparison Of the Proposed Model With Other Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Assuring Safe and Efficient Operation of UAV Using Explainable Machine Learning

Alharbi

Petrunin

Panagiotakopoulos

2023

Drones

View full text Add to dashboard Cite

The accurate estimation of airspace capacity in unmanned traffic management (UTM) operations is critical for a safe, efficient, and equitable allocation of airspace system resources. While conventional approaches for assessing airspace complexity certainly exist, these methods fail to capture true airspace capacity, since they fail to address several important variables (such as weather). Meanwhile, existing AI-based decision-support systems evince opacity and inexplicability, and this restricts their practical application. With these challenges in mind, the authors propose a tailored solution to the needs of demand and capacity management (DCM) services. This solution, by deploying a synthesized fuzzy rule-based model and deep learning will address the trade-off between explicability and performance. In doing so, it will generate an intelligent system that will be explicable and reasonably comprehensible. The results show that this advisory system will be able to indicate the most appropriate regions for unmanned aerial vehicle (UAVs) operation, and it will also increase UTM airspace availability by more than 23%. Moreover, the proposed system demonstrates a maximum capacity gain of 65% and a minimum safety gain of 35%, while possessing an explainability attribute of 70%. This will assist UTM authorities through more effective airspace capacity estimation and the formulation of new operational regulations and performance requirements.

show abstract

Section: Comparison Of the Proposed Model With Other Approachesmentioning

confidence: 99%