Home / Current Issue / Paper 1718018
UMAF: Unified Multi-Agent Framework for Real-Time Public Transport Dispatching
Subject area: Science,Engineering and Technology · Area of research: Real Time Public Transport
DOI: https://doi.org/10.64388/IREV9I11-1718018
Abstract
This paper proposes a Unified Multi-Agent Framework (UMAF) for real-time public transport dispatching in smart cities. The framework integrates eight critical technical domains: spatial flux modeling, 5G V2X communication, battery State-of-Health (SoH) monitoring, human-centric automation, federated edge privacy, adversarial AI defense, behavioral economics, and multi-agent reinforcement learning. Current dispatching systems suffer from fragmentation — they optimize for traffic flow while ignoring hardware constraints or cybersecurity threats. By utilizing a Multi-Agent Reinforcement Learning (MARL) engine cross-verified against chemistry-aware battery models and lightweight adversarial filters, the proposed system demonstrates a 15–18% reduction in deadheading and a 20% extension in electric vehicle (EV) fleet longevity. Furthermore, the implementation of a federated edge architecture ensures 100% privacy compliance with minimal computational latency, providing a secure and sustainable foundation for next-generation smart city mobility. This research uniquely bridges the gap between academic AI theory and real-world operational constraints by proposing a framework that is simultaneously technically rigorous, privacy-preserving, and economically viable. The results indicate that UMAF outperforms existing state-of-the-art dispatch systems across all evaluated performance metrics.
How to cite this paper
@article{1718018,
author = {Hemanth Kumar H},
title = {UMAF: Unified Multi-Agent Framework for Real-Time Public Transport Dispatching},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {11},
pages = {2941-2951},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1718018.pdf},
abstract = {This paper proposes a Unified Multi-Agent Framework (UMAF) for real-time public transport dispatching in smart cities. The framework integrates eight critical technical domains: spatial flux modeling, 5G V2X communication, battery State-of-Health (SoH) monitoring, human-centric automation, federated edge privacy, adversarial AI defense, behavioral economics, and multi-agent reinforcement learning. Current dispatching systems suffer from fragmentation — they optimize for traffic flow while ignoring hardware constraints or cybersecurity threats. By utilizing a Multi-Agent Reinforcement Learning (MARL) engine cross-verified against chemistry-aware battery models and lightweight adversarial filters, the proposed system demonstrates a 15–18% reduction in deadheading and a 20% extension in electric vehicle (EV) fleet longevity. Furthermore, the implementation of a federated edge architecture ensures 100% privacy compliance with minimal computational latency, providing a secure and sustainable foundation for next-generation smart city mobility. This research uniquely bridges the gap between academic AI theory and real-world operational constraints by proposing a framework that is simultaneously technically rigorous, privacy-preserving, and economically viable. The results indicate that UMAF outperforms existing state-of-the-art dispatch systems across all evaluated performance metrics.},
month = {May},
doi = {https://doi.org/10.64388/IREV9I11-1718018}
}