Pasar al contenido principal

UN MARCO DE NEGOCIACION MULTI-AGENTE PARA LA PLANIFICACION DE ESCENARIOS U-SPACE LIBRES DE CONFLICTOS

PID2020-116377RB-C22

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2020
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD AUTONOMA DE BARCELONA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 4
Encontrada(s) 1 página(s)

Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Flying Like Geese, Green, Sustainable, and Efficient

  • Bracons Escarre, Oriol|||0009-0003-6882-708X
  • de Urrengoechea Cantavenera, Tomás|||0009-0002-4153-6226
  • Piera, Miquel Àngel|||0000-0002-7227-7944
  • Gigante, Gabriella|||0000-0002-0701-0549
  • Gargiulo, Francesco
Formation flights hold significant potential for reducing the environmental impact of aviation and offer a means to streamline airspace complexity. The selection of candidates for formation pairing among the intense traffic of continental routes (Europe to Asia) plays an important role in savings. This article enables a better understanding of how deviations from the initially planned route may impact the performance of aircraft. The fuel consumption assessment is made by trajectory simulations, allowing a comparison considering different air traffic scenarios.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Impact assessment of the Strategic Planning performance in Shared U-space volumes

  • Ramos González, Juan José|||0000-0002-0881-7205
  • Liu, Zhiqiang|||0009-0006-8034-0364
  • Munoz-Gamarra, Jose Luis|||0000-0003-3213-0558
  • Pastor, Enric|||0000-0002-7587-8702
  • Barrado, Cristina|||0000-0003-0100-724X
Este trabajo analiza cómo los distintos proveedores de servicios de espacio aéreo (USSP) que gestionan un volumen de espacio aéreo compartido influyen en el rendimiento de los demás. El trabajo demuestra cómo las distintas capacidades de planificación estratégica de los USSP, que van desde los procedimientos y políticas hasta la representación de trayectorias, así como las estrategias de deconflicto, repercuten en el uso de este recurso común en términos de capacidad efectiva del espacio aéreo. El documento pone en práctica el concepto de tiempo razonable para reaccionar proponiendo un calendario de planificación con hitos comunes para la aplicación de los procedimientos de autorización requeridos antes del vuelo. Además, se compara la política de planificación por orden de llegada con una política de planificación por lotes más eficaz, en la que los lotes de planes de vuelo se procesan para mitigar los posibles conflictos existentes en la fase estratégica. Además, el artículo muestra cómo las capacidades de la USSP para representar la trayectoria y su incertidumbre asociada serán también clave para optimizar el uso del espacio aéreo. Basándose en un escenario CORUS-XUAM VLD, un análisis de simulación evaluará cómo las capacidades de los USSP para gestionar las actividades de planificación de vuelos repercuten en la ocupación efectiva del espacio aéreo, poniendo en peligro en algunos casos no sólo el rendimiento propio, sino también el de otros usuarios del espacio aéreo., This work analyses how the different U-space service providers (USSPs) managing a shared airspace volume will impact on the other's performance. The paper demonstrates how the various strategic planning USSPs capabilities, ranging from procedures and policies, trajectory representation, as well as the deconflicting strategies, impact on the use of this common resource in terms of effective airspace capacity. The paper brings to practice the concept of Reasonable Time to React by proposing a planning timeline with common milestones for the implementation of the required authorization procedures prior to the flight. The paper analyses how these milestones impact on the effective airspace capacity. Also, the First-Come First-Served planning policy is compared with respect to a more efficient batch planning policy, where flight plan batches are processed to mitigate the potential conflicts existing at the strategic phase. Furthermore, the paper discusses how the capabilities supported by the USSP to represent the trajectory and its associated uncertainty will be also key to optimize the use the airspace. Based on a CORUS-XUAM VLD scenario, a simulation analysis will assess how the USSPs' capabilities to manage flight planning activities impact on the effective occupation of airspace, jeopardizing in some cases not just the own performance but also that of other airspace users.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Deep reinforcement learning-based multi-agent negotiation framework for conflict-free U-Space scenarios

  • Liu, Zhiqiang|||0009-0006-8034-0364
  • Ramos González, Juan José|||0000-0002-0881-7205
  • Çetin, Ender|||0000-0002-9258-1919
  • Munoz-Gamarra, Jose Luis|||0000-0003-3213-0558
Very-Low Level urban airspace is expected to accommodate large numbers of simultaneous drone missions in the near future, posing acute challenges for the strategic planning and deconfliction services mandated by U-space regulations. The current strategic planner algorithm relies on the first-come-first-served or batch policy that rejects nearly half of the submitted flight plans in large-scale scenarios. This paper presents a novel study that integrates a Deep Reinforcement Learning-based Multi-Agent Negotiation Framework into the U-space strategic planning and deconfliction service. The framework reallocates rejected flight plans through an iterative sealed-bid auction mechanism in a fully competitive auction environment. Four role-specific drone operator agents were constructed: Achiever, Optimizer, Economizer and Normalizer, to learn bidding policies with the Proximal Policy optimization algorithm. Each round's reward combines individual profit, bidding cost and a global utilisation signal, guiding agents towards system-efficient yet self-interested behaviour. The simulation experiments show that the Deep Reinforcement Learning-based Multi-Agent Negotiation Framework lifts the mission re-accommodation ratio to a notable level while converging to a final allocation within a short strategic planning time. Analysis of reward distribution and bidding patterns confirms that agents adapt their strategies to heterogeneous operational objectives without explicit coordination. These findings indicate that learning-enabled auctions can reconcile operator competition with network-level efficiency, offering a scalable path towards conflict-free, high-density U-space operations.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

A STAM Model Based on Spatiotemporal Airspace Sector Interdependencies to Minimize Tactical Flow Management Regulations

  • Martín López, Gonzalo
  • Calvet, Laura|||0000-0001-8425-1381
  • Piera, Miquel Àngel|||0000-0002-7227-7944
The lack of airspace capacity poses a significant challenge for a sustainable air transport system, particularly in scenarios of future growing demand. Air traffic management digitalization opens pathways for innovative and efficient solutions to tackle existing inefficiencies arising from spatially fragmented airspace. While research has focused on digitalized ATM services to improve airspace capacity, synergies among adjacent sectors to utilize latent capacity remain unexplored. Using a sector network model, in this study, we analyze spatiotemporal sector interdependencies, quantify time-stamp topological interdependencies, and evaluate capacity enhancement possibilities for sectors unable to meet dynamic demand. The occupancy count dynamic evolution and poor correlation among the over-loaded sectors with the occupancy count of its adjacent sectors provide opportunities for a short-term ATM mechanism, ensuring sector-level capacity invulnerability and enhancing airspace capacity at the network level. A computational experiment using real data from the European airspace is carried out to illustrate and validate this innovative solution.