An efficient algorithm for optimal route node sensing in smart tourism Urban traffic based on priority constraints

Wireless Networks, Journal Year: 2023, Volume and Issue: 30(9), P. 7189 - 7206

Published: Dec. 8, 2023

Language: Английский

---

Enhancing Urban Intersection Efficiency: Visible Light Communication and Learning-Based Control for Traffic Signal Optimization and Vehicle Management

Symmetry, Journal Year: 2024, Volume and Issue: 16(2), P. 240 - 240

Published: Feb. 16, 2024

This paper introduces a novel approach, Visible Light Communication (VLC), to optimize urban intersections by integrating VLC localization services with learning-based traffic signal control. The system enhances communication between connected vehicles and infrastructure using headlights, streetlights, signals transmit information. Through Vehicle-to-Vehicle (V2V) Infrastructure-to-Vehicle (I2V) interactions, joint data transmission collection occur via mobile optical receivers. goal is reduce waiting times for pedestrians vehicles, enhancing overall safety employing flexible adaptive measures accommodating diverse movements. cooperative mechanisms, range, relative pose concepts, queue/request/response interactions help balance flow improve road network performance. Evaluation in the SUMO mobility simulator demonstrates advantages, reducing travel both pedestrians. employs reinforcement learning scheme effective scheduling, utilizing VLC-ready communicate positions, destinations, routes. Agents at calculate optimal strategies, communicating flow. proposed decentralized scalable especially suitable multi-intersection scenarios, showcases feasibility of applying real-world scenarios.

Language: Английский

---

Exploiting Traffic Light Coordination and Auctions for Intersection and Emergency Vehicle Management in a Smart City Mixed Scenario

Sensors, Journal Year: 2024, Volume and Issue: 24(7), P. 2036 - 2036

Published: March 22, 2024

IoT (Internet-of-Things)-powered devices can be exploited to connect vehicles smart city infrastructure, allowing share their intentions while retrieving contextual information about diverse aspects of urban viability. In this paper, we place ourselves in a transient scenario which next-generation that are able communicate with the surrounding infrastructure coexist traditional limited or absent capabilities. We focus on intersection management, particular reusing existing traffic lights empowered by new management system. propose an auction-based system exchange and other nearby aim reducing average waiting times at intersections consequently overall trip times. use bid propagation improve standard vehicle emergency free up way ahead without needing ad hoc for such vehicle, only increase budget. The proposed is then tested against two baselines: classical Fixed Time Control currently adopted lights, auction strategy does not exploit light coordination. performed large set experiments using well known MATSim transport simulator both synthetic Manhattan map built area located Modena, Northern Italy. Our results show approach performs better than fixed time control coordination among lights.

Language: Английский

---

Optimizing Autonomous Intersection Control Using Single Agent Reinforcement Learning

Published: Jan. 2, 2025

Language: Английский

---

Optimizing Intelligent Transportation Systems with Multi-agent Reinforcement Learning: A Socio-economic Impact Assessment

Published: Jan. 1, 2025

Language: Английский

---

RDHNet: addressing rotational and permutational symmetries in continuous multi-agent systems

Frontiers of Computer Science, Journal Year: 2025, Volume and Issue: 19(11)

Published: April 3, 2025

Language: Английский

---

A survey of reinforcement and deep reinforcement learning for coordination in intelligent traffic light control

Journal Of Big Data, Journal Year: 2025, Volume and Issue: 12(1)

Published: April 7, 2025

Language: Английский

---

Corporate Social Responsibility and AI and Their Impact on Smart Cities

Advances in computational intelligence and robotics book series, Journal Year: 2025, Volume and Issue: unknown, P. 435 - 462

Published: March 7, 2025

Due to increasing urbanization, smart cities have developed rapidly, and they focus on technology driven infrastructure sustainable development. With becoming more digital, Corporate Social Responsibility (CSR) Artificial Intelligence (AI) are key issues in determining the urban habitat of future. This work investigates relationship between CSR, AI cities, their implications for Aiming from perspective role city making responsibility corporations enhancing environment, this chapter discusses opportunities difficulties combining CSR building liveable, efficient, cities. More specifically, study aims help extend understanding entanglement corporate responsibility, technological innovation, sustainability guide development resilient just

Language: Английский

---

A time-delay aggregation transformer model for traffic flow forecasting

Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: May 10, 2025

Forecasting traffic flow is vital for the efficient operation of modern transportation systems and plays a pivotal role in advanced intelligent management. Enhancing forecasting accuracy hinges on precisely grasping dynamic changes spatial-temporal relationships flow. This study mainly focuses such patterns as trends, periodicity, spatial heterogeneity proposes time-delay aggregation transformer model (short TDATF) to forecast The leverages self-attention mechanism extract trends periodicities effectively, graph convolution module dynamically captures dependency relationships. Meanwhile, position embedding matrix utilized, which constructed by Laplacian-smoothed vector derived from Graph Convolutional Network (GCN) layer, effectively heterogeneity. Experimental results datasets PEMS03/04/07/08 demonstrate that proposed TDATF outperforms baseline models terms accuracy.

Language: Английский

---

Resource allocation optimization for effective vehicle network communications using multi-agent deep reinforcement learning

Journal of Dynamics and Games, Journal Year: 2024, Volume and Issue: 0(0), P. 0 - 0

Published: Jan. 1, 2024

Language: Английский

---