Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Urban Air Mobility as a System of Systems: An LLM-Enhanced Holonic Approach

Ahmed R. Sadik, Muhammad Ashfaq, Niko Mäkitalo, Tommi Mikkonen

TL;DR

This paper tackles the complexity of Urban Air Mobility (UAM) as a System of Systems (SoS) by proposing an LLM-enhanced holonic architecture that enables decentralized, autonomous coordination among air taxis, ground transport, and vertiports. The approach combines a three-layer holon structure with specialized holons (Supervisor, Planner, Task, Resource) and an LLM-based Reasoning Layer to process natural language, reason about context, and adapt plans in real time. A multimodal, case-study-based demonstration with electric scooters and air taxis shows dynamic resource allocation, autonomous replanning, and resilience without centralized control. The authors discuss practical implications, limitations (latency, safety, privacy), and future directions including hybrid AI integration, security enhancements, and real-world validation.

Abstract

Urban Air Mobility (UAM) is an emerging System of System (SoS) that faces challenges in system architecture, planning, task management, and execution. Traditional architectural approaches struggle with scalability, adaptability, and seamless resource integration within dynamic and complex environments. This paper presents an intelligent holonic architecture that incorporates Large Language Model (LLM) to manage the complexities of UAM. Holons function semi autonomously, allowing for real time coordination among air taxis, ground transport, and vertiports. LLMs process natural language inputs, generate adaptive plans, and manage disruptions such as weather changes or airspace closures.Through a case study of multimodal transportation with electric scooters and air taxis, we demonstrate how this architecture enables dynamic resource allocation, real time replanning, and autonomous adaptation without centralized control, creating more resilient and efficient urban transportation networks. By advancing decentralized control and AI driven adaptability, this work lays the groundwork for resilient, human centric UAM ecosystems, with future efforts targeting hybrid AI integration and real world validation.

Urban Air Mobility as a System of Systems: An LLM-Enhanced Holonic Approach

TL;DR

This paper tackles the complexity of Urban Air Mobility (UAM) as a System of Systems (SoS) by proposing an LLM-enhanced holonic architecture that enables decentralized, autonomous coordination among air taxis, ground transport, and vertiports. The approach combines a three-layer holon structure with specialized holons (Supervisor, Planner, Task, Resource) and an LLM-based Reasoning Layer to process natural language, reason about context, and adapt plans in real time. A multimodal, case-study-based demonstration with electric scooters and air taxis shows dynamic resource allocation, autonomous replanning, and resilience without centralized control. The authors discuss practical implications, limitations (latency, safety, privacy), and future directions including hybrid AI integration, security enhancements, and real-world validation.

Abstract

Urban Air Mobility (UAM) is an emerging System of System (SoS) that faces challenges in system architecture, planning, task management, and execution. Traditional architectural approaches struggle with scalability, adaptability, and seamless resource integration within dynamic and complex environments. This paper presents an intelligent holonic architecture that incorporates Large Language Model (LLM) to manage the complexities of UAM. Holons function semi autonomously, allowing for real time coordination among air taxis, ground transport, and vertiports. LLMs process natural language inputs, generate adaptive plans, and manage disruptions such as weather changes or airspace closures.Through a case study of multimodal transportation with electric scooters and air taxis, we demonstrate how this architecture enables dynamic resource allocation, real time replanning, and autonomous adaptation without centralized control, creating more resilient and efficient urban transportation networks. By advancing decentralized control and AI driven adaptability, this work lays the groundwork for resilient, human centric UAM ecosystems, with future efforts targeting hybrid AI integration and real world validation.
Paper Structure (22 sections, 6 figures, 1 table)

This paper contains 22 sections, 6 figures, 1 table.

Table of Contents

  1. Introduction
  2. Background
  3. Federated Architectures in Urban Air Mobility
  4. Facilitator-based architecture
  5. Broker-based architecture
  6. Matchmaking-based architecture
  7. Mediator-based architecture
  8. Holonic architecture
  9. LLM-Enhanced Holonic Architecture
  10. Holon Structure
  11. Specialized Holons for UAM Coordination
  12. LLM-Enhanced Holonic Solution for UAM
  13. UAM-Specific Holon Implementation
  14. Specialized Holons for UAM
  15. Supervisor Holon
  16. ...and 7 more sections

Figures (6)

  • Figure 1: Urban Air Mobility as System of Systems.
  • Figure 2: Comparison of different federated architectures, illustrating (a) Facilitator, (b) Broker, (c) Matchmaking, (d) Mediator, and (e) Holonic approaches.
  • Figure 3: UAM-specific holon implementation showing the layers with specialized components for multimodal transportation coordination.
  • Figure 4: UAM Specialized holons and their workflow.
  • Figure 5: Holonic architecture of the UAM-SoS, showing coordination among supervisor, assistant, plan, task, and resource holons for electric scooters and air taxis.
  • ...and 1 more figures