Designing an Urban Air Mobility Corridor Network: A Multi-Objective Optimization Approach Using U-NSGA-III

Zhiyuan Zhang, Yuan Zheng, Chenglong Li, Bo Jiang, Yichao LiAerospace 2025 · DOI

TL;DR

This paper tackles the complex challenge of designing Urban Air Mobility (UAM) corridor networks by employing a multi-objective optimization approach. Using a novel encoding scheme and the U-NSGA-III algorithm, they simultaneously optimize for travel time efficiency, ground risk, and implementation costs, demonstrating significant improvements over traditional methods in a Chengdu case study.

What Problem Does This Paper Address?

The rapid development of Urban Air Mobility (UAM) necessitates safe and efficient operational environments. A crucial component of this is the design of a robust corridor network, which dictates the flight paths for UAM vehicles. However, existing approaches often fall short by:

  • Neglecting ground risk: Many designs overlook the potential hazards UAM operations could pose to people on the ground.
  • Focusing on single objectives: Current methods typically optimize for just one factor, like cost or travel time, failing to account for the inherent trade-offs between competing goals.
  • Limited flexibility: Existing encoding schemes can be rigid, restricting the diversity and adaptability of potential network designs.

This paper aims to bridge these gaps by developing a comprehensive framework that balances travel time efficiency, ground safety (quantified by population density in potential impact areas), and implementation costs (represented by corridor length).

Methods

The core of this research lies in its multi-objective optimization framework and the algorithms used to solve it.

  • Multi-Objective Optimization Formulation: The problem is framed as maximizing travel time-saving rate while minimizing ground risk and implementation costs. These objectives are mathematically defined using specific metrics.
  • Novel Encoding Scheme: A key contribution is a flexible encoding scheme that represents corridor networks. It combines node coordinates and connectivity information into a fixed-length vector, allowing for variable numbers of corridors and thus a richer exploration of network designs.
  • U-NSGA-III Algorithm: The Unified Non-Dominated Sorting Genetic Algorithm III (U-NSGA-III) is employed to solve the multi-objective problem. This algorithm is chosen for its ability to handle complex, high-dimensional problems and its effectiveness in finding a diverse set of Pareto-optimal solutions.
  • Parameter Tuning: The paper details an experimental process to select optimal crossover and mutation probabilities for the U-NSGA-III algorithm, using the hypervolume metric to evaluate different combinations.

Datasets

The study utilizes real-world data from Chengdu, China, for its case analysis:

  • Travel Demand Data: A dataset of long-distance ride-hailing trips from Didi Chuxing in Chengdu (November 2016) was used. This data was filtered for trips exceeding 30 km and within the main urban area.
  • Population Distribution Data: Mobile signaling data from Chengdu (2023) was used to estimate population density, filtered to the main urban area.
  • No-Fly Zone Data: This includes data on obstacle limitation surfaces for aerodromes (based on CAAC regulations), tall buildings (over 200m), and densely populated areas, all within Chengdu's main urban area.

Key Insights and Ideas

  • The Power of Multi-Objective Optimization: The research strongly advocates for a multi-objective approach in UAM corridor design, demonstrating that balancing competing goals (efficiency, safety, cost) leads to more robust and practical solutions than single-objective optimization.
  • Ground Risk is Crucial: Explicitly incorporating ground risk, linked to population density, is shown to be a vital factor in designing UAM networks, leading to significant risk reductions.
  • Flexible Encoding Enables Diversity: The proposed encoding scheme's ability to represent networks with a variable number of corridors is critical for exploring a wider range of potential designs and finding more optimal solutions.
  • Trade-offs are Inevitable: The Pareto fronts clearly illustrate the inherent trade-offs between objectives. Improving one metric often comes at the expense of another, requiring careful consideration of decision-maker preferences.

Key Results

The case study in Chengdu yielded impressive results:

  • Ground Risk Reduction: The optimized corridor network achieved a 37.8% reduction in ground risk compared to traditional methods.
  • Implementation Cost Savings: A significant 69.9% decrease in implementation costs was observed.
  • Time Efficiency: The network provided a 4.7% improvement in travel time savings compared to traditional ride-hailing services.
  • Network Characteristics: The final optimized network comprised 8 nodes and 9 corridors, predominantly located in the northern part of Chengdu, aligning with areas of high demand and fewer no-fly zones.
  • Comparison with K-Means: The U-NSGA-III method outperformed the K-means clustering benchmark in travel time-saving rate, average population density, and travel time-saving rate of covered demands, though K-means showed slightly better demand coverage.

Limitations and Future Work

The authors acknowledge and suggest several avenues for future research:

  • Non-linear Corridor Design: The current model assumes linear connections between nodes. Future work could explore non-linear pathways to better navigate complex urban environments and no-fly zones.
  • Dynamic Factors: Incorporating dynamic elements like weather conditions, time-varying demands, and real-time traffic data would enhance the robustness and adaptability of the network design.
  • Additional Objectives: Expanding the optimization framework to include objectives such as noise pollution, environmental impact, and social equity would provide a more holistic assessment.
  • Implementation Feasibility: Further research is needed to evaluate the practical aspects of deploying the optimized network, including regulatory compliance, public acceptance, and economic viability.

Summary updated

Abstract

The corridor network serves as an effective solution for the airspace structure safety design of UAM. However, current studies rarely account for the ground risk posed by the corridor operation and typically consider a single design objective with limited variables. In this paper, we address these gaps by considering three key factors: demand, safety, and implementation costs. The corridor network design is formulated as a multi-objective optimization problem. In practice, firstly, we define the travel time-saving rate, average population density, and total length of corridors as optimization objectives. Then, we propose a straightforward and efficient corridor network encoding scheme that supports a variable number of corridors, significantly enhancing the diversity and flexibility of corridor network designs. Finally, based on this encoding scheme, we solve the corridor network problem using the unified non-dominated sorting genetic algorithm III (U-NSGA-III). Based on a detailed analysis of the obtained Pareto front, a relatively optimal design scheme across three optimization objectives is determined. The case study conducted in Chengdu illustrates that the corridor network obtained by our method not only achieves a 37.8% reduction in ground risk and a 69.9% decrease in implementation costs, but also saves a comparable 4.7% in time relative to traditional methods.
BibTeX
@inproceedings{zhang2025designing,
  author = {Zhiyuan Zhang and Yuan Zheng and Chenglong Li and Bo Jiang and Yichao Li},
  title = {{Designing an Urban Air Mobility Corridor Network: A Multi-Objective Optimization Approach Using U-NSGA-III}},
  booktitle = {Aerospace},
  year = {2025},
  doi = {10.3390/aerospace12030229},
}
Figure