Similar articles

Abstract: The development of urban air mobility (UAM) systems requires scalable, regulation-aware planning of low-altitude airspace and supporting infrastructure. This study proposes an end-to-end framework for the design, simulation, and iterative optimization of a structured UAM corridor over ord'>ont color=#2f4a8b>brasiliaont>’s central road axis (ord'>ont color=#2f4a8b>eixãont>;o-UAM), aligned with the Brazilian unmanned aircraft traffic management (BR-UTM) ecosystem. In addition, this study proposes a multilayered aerial configuration stratified by unmanned aerial vehicle class, supported by a modular ground infrastructure composed of vertihubs, vertiports, and vertistops. A takeoff-scheduling simulator is developed to evaluate platform allocation strategies under realistic traffic and weather conditions. Initial experiments compare a round-robin (RR) baseline with a genetic algorithm (GA), and results reveal that RR outperforms GA v1 in terms of the average waiting time. To address this gap, a large language model (LLM) assisted optimization loop is implemented using GPT-4o Mini and Gemini 2.5 Pro. The LLMs act as reasoning partners, supporting the root-cause diagnoses, fitness function redesign, and rapid prototyping of five GA variants. Among these, GA v5 achieves a 59.62% reduction in maximum waiting time and an approximately 10% reduction in average waiting time over GA v1, thereby approaching the robustness of RR. In contrast, GA v2–v4 and GA v6 perform less consistently, showing an importance of fitness function design. These results underscore the role of an iterative, LLM-guided development in enhancing classical optimization, demonstrating that generative artificial intelligence (AI) can contribute to simulation acceleration and the cocreation of operational logic. The proposed method provides a replicable blueprint for integrating LLMs into early-stage UAM planning, offering both theoretical insights and architectural guidance for future low-altitude airspace systems.

Eix?o-UAM：基于大语言模型迭代的巴西利亚低空城市空中交通走廊设计

[1]Abdellaoui R, Naser F, Velieva A, et al., 2025. Applying a comparative performance assessment framework to different airspace management concepts for urban air mobility. CEAS Aeronaut J, 16(3):827-847.

[2]Alolaiwy M, Hawsawi T, Zohdy M, et al., 2023. Multi-objective routing optimization in electric and flying vehicles: a genetic algorithm perspective. Appl Sci, 13(18):10427.

[3]ANAC, 2017a. Classes de Drones (in Portuguese). https://www.gov.br/anac/pt-br/assuntos/drones/classes-de-drones [Accessed on July 30, 2025].

[4]ANAC, 2017b. Requisitos Gerais para aeronaves não tripuladas de uso civil (RBAC-E 94) (in Portuguese). https://www.anac.gov.br/assuntos/legislacao/legislacao-1/rbha-e-rbac/rbac/rbac-e-94 [Accessed on July 30, 2025].

[5]Bayer DM, Bayer F, 2015. Previsão da umidade relativa do ar de brasília por meio do modelo beta autorregressivo de médias móveis. Rev Bras Meteorol, 30(3):319-326 (in Portuguese).

[6]Chan YY, Ng KKH, Lee CKM, et al., 2023. Wind dynamic and energy-efficiency path planning for unmanned aerial vehicles in the lower-level airspace and urban air mobility context. Sustain Energy Technol Assess, 57:103202.

[7]Cheng AW, Witzberger KE, Isaacson DR, et al., 2022. National Campaign (NC)-1 Strategic Conflict Management Simulation (X4) Final Report. NASA/TM-2022-0018159, NASA, Moffett Field.

[8]Cohen AP, Shaheen SA, Farrar EM, 2021. Urban air mobility: history, ecosystem, market potential, and challenges. IEEE Trans Intell Transp Syst, 22(9):6074-6087.

[9]da Silva R, do Sul Milholi da Silva R, de Almeida Regis J, et al., 2020. Acesso ao espaço aéreo brasileiro por aeronaves não tripuladas. Rev CIAAR, 1(1):23-40 (in Portuguese).

[10]DECEA, 2023. Remotely piloted aircraft systems and access to Brazilian airspace. Brazilian Airspace Control Department, ICA 100-40.

[11]Deniz S, Wang ZB, 2024. Autonomous conflict resolution in urban air mobility: a deep multi-agent reinforcement learning approach. Proc AIAA Aviation Forum and Ascend, Article 4005.

[12]de Vasconcellos E, Regis JM, 2022. Brazil’s DECEA Launches UTM Sandbox and Publishes Implementation Programme. Unmanned Airspace. https://www.unmannedairspace.info/uncategorized/brazils-decea-launches-brazils-utm-sandbox-and-published-implementation-programme [Accessed on July 30, 2025].

[13]EASA, 2017. Drones and air mobility basics explained. https://www.easa.europa.eu/en/domains/drones-air-mobility/drones-air-mobility-landscape/basics-explained [Accessed on July 30, 2025].

[14]FAA, 2023a. Advanced Air Mobility (AAM) Implementation Plan. https://www.faa.gov/sites/faa.gov/files/AAM-I28-Implementation-Plan.pdf [Accessed on July 30, 2025].

[15]FAA, 2023b. Urban Air Mobility (UAM) Concept of Operations. https://www.faa.gov/sites/faa.gov/files/Urban-Air-Mobility-Concept-of-Operations-2.0.pdf [Accessed on July 30, 2025].

[16]Ferreira DM, Rosa LP, Ribeiro VF, et al., 2014. Genetic algorithms and game theory for airport departure decision making: GeDMAN and CoDMAN. Proc 9^th Int Conf on Knowledge Management in Organizations, p.3-14.

[17]Garcia CP, Weigang L, Hirata NST, et al., 2023. ISUAM: intelligent and safe UAM with deep reinforcement learning. Proc 29^th Int Conf on Parallel and Distributed Systems, p.378-383.

[18]Gong YW, Fan JC, Zhang RC, et al., 2025. Safe and economical UAV trajectory planning in low-altitude airspace: a hybrid DRL-LLM approach with compliance awareness.

[19]Goodrich KH, Theodore CR, 2021. Description of the NASA urban air mobility maturity level (UML) scale. Proc AIAA Scitech Forum, Article 1627.

[20]Halder S, Ghosal A, Conti M, 2023. Dynamic super round-based distributed task scheduling for UAV networks. IEEE Trans Wirel Commun, 22(2):1014-1028.

[21]ICAO, 2015. Manual on Remotely Piloted Aircraft System (RPAS). International Civil Aviation Organization, Montrèal.

[22]Jasper FNH, Nunes AF, 2022. Soberania e controle do espaço aéreo: uma visão brasileira. Rev Tempo Mundo, (28):345-366 (in Portuguese).

[23]Jiang YH, Li XY, Zhu GX, et al., 2023. 6G non-terrestrial networks enabled low-altitude economy: opportunities and challenges.

[24]Korringa M, Snyder P, Ullrich M, et al., 2025. Optimal air corridor design for efficient integration of AAM vehicles into the NAS. Proc Integrated Communications, Navigation and Surveillance Conf, p.1-7.

[25]Lascara B, Spencer T, DeGarmo M, et al., 2018. Urban Air Mobility Landscape Report. McLean, VA, USA. https://www.mitre.org/publications/technical-papers/urban-air-mobility-landscape-report

[26]Lavezzi G, Guye K, Cichella V, et al., 2023. Comparative analysis of nonlinear programming solvers: performance evaluation, benchmarking, and multi-UAV optimal path planning. Drones, 7(8):487.

[27]Leite GMC, Marcelino CG, Wanner EF, et al., 2021. Pattern classification applying neighbourhood component analysis and swarm evolutionary algorithms: a coupled methodology. Proc IEEE Congress on Evolutionary Computation, p.319-326.

[28]Liang M, Li WG, Delahaye D, et al., 2019. Policy optimization in automated point merge trajectory planning: an artificial intelligence-based approach. Proc 38^th Digital Avionics Systems Conf, p.1-8.

[29]Liao XH, Xu CC, Ye HP, 2024. Benefits and challenges of constructing low-altitude air route network infrastructure for developing low-altitude economy. Bull Chin Acad Sci, 39(11):1966-1981 (in Chinese).

[30]Liu CL, Layland JW, 1973. Scheduling algorithms for multiprogramming in a hard-real-time environment. J ACM, 20(1):46-61.

[31]Liu S, Liu MM, 2025. Research on the security risk governance roadmap in low-altitude economic field based on the economic externality theory. Eng Proc, 80(1):14.

[32]Maia JA, Weigang L, Stenzel E, et al., 2025. Model of a corridor for urban mobility of unmanned aircraft in the “Eixão” of Brasília. Proc Brazilian Air Transport Symp (in Portuguese).

[33]Moon H, Park J, Kim J, 2024. Development of decision support systems for regional air mobility (RAM) operations in South Korea: dynamic corridor network generation. Proc AIAA Aviation Forum and Ascend, Article 4255.

[34]Moraga Á, de Curtò J, de Zarzà I, et al., 2025. AI-driven UAV and IoT traffic optimization: large language models for congestion and emission reduction in smart cities. Drones, 9(4):248.

[35]Muna SI, Mukherjee S, Namuduri K, et al., 2021. Air corridors: concept, design, simulation, and rules of engagement. Sensors, 21(22):7536.

[36]Neufert E, 2013. Neufert: Arte de Proyectar en Arquitectura. Gustavo Gili, Barcelona (in French).

[37]Pagotto LG, Rodrigues J, Henrique FH, et al., 2021. Analysis of variance and means tests: a study applied in experiments with cotton varieties and citrumelo selections. Brazilian Appl Sci Revi, 5(3):1287-1296.

[38]Pruekprasert S, Nakadai S, 2024. Enhancing safety in UAM corridors: a self-separation scheme utilizing estimated arrival times at constraint waypoints. Proc Int Workshop on ATM/CNS, p.187.

[39]Roberge V, Tarbouchi M, Labonte G, 2013. Comparison of parallel genetic algorithm and particle swarm optimization for real-time UAV path planning. IEEE Trans Ind Inform, 9(1):132-141.

[40]Sadik AR, Ashfaq M, Mäkitalo N, et al., 2025. Urban air mobility as a system of systems: an LLM-enhanced holonic approach. Proc 20^th Annual System of Systems Engineering Conf, p.1-7.

[41]Turchetti JV, Murça MCR, 2024. Analysis and prediction of airspace availability for urban air mobility operations in the Sao Paulo Metropolitan Region. Transportes, 32(1):1-20.

[42]van Nguyen T, 2020. Dynamic delegated corridors and 4D required navigation performance for urban air mobility (UAM) airspace integration. J Aviat Aerosp Educ Res, 29(2):57-72.

[43]Varun Kumar KA, Priyadarshini R, Kathik PC, et al., 2023. Self-co-ordination algorithm (SCA) for multi-UAV systems using fair scheduling queue. Sens Rev, 43(4):233-242.

[44]Verma S, Dulchinos V, Dan Wood R, et al., 2022. Design and analysis of corridors for UAM operations. Proc IEEE/AIAA 41^st Digital Avionics Systems Conf, p.1-10.

[45]Wang BH, Wang DB, Ali ZA, et al., 2019. An overview of various kinds of wind effects on unmanned aerial vehicle. Meas Contr, 52(7-8):731-739.

[46]Xu L, Cao XB, Du WB, et al., 2025. Robust path planning for multiple UAVs considering position uncertainty. Chin J Electron, 34(4):1120-1135.

[47]Yang JL, Yang JF, Liu DX, et al., 2024. Competition pattern and coping strategies in near space. Strat Study CAE, 26(5):137-145 (in Chinese).

[48]Zou LY, Munir S, Hassan SS, et al., 2024. Imbalance cost-aware energy scheduling for prosumers towards UAM charging: a matching and multi-agent DRL approach. IEEE Trans Veh Technol, 73(3):3404-3420.