What question did this study set out to answer?

To assess the macroscopic network impacts of vehicle-centric tourist bus routing strategies and evaluate an adaptive routing framework under near-critical traffic demand.

September 9, 2026Transportation EngineeringOpen Access

Macroscopic impacts of optimised tourist bus routes on urban road networks: a spatiotemporal analysis

View Full Paper

Ask AI

Bookmark

Authors

PLPhan Gia Bao Le SMSara Moridpour MDMinh Ngoc Dinh

Discussion

Member takes

Overview

Simulation study demonstrates adaptive reinforcement learning limits network throughput loss to 24% in tourist bus fleets, indicating real-time control mitigates urban congestion.

Key Points

To assess the macroscopic network impacts of vehicle-centric tourist bus routing strategies and evaluate an adaptive routing framework under near-critical traffic demand.
Constructed a microscopic traffic simulation of Nha Trang, Vietnam, in SUMO, calibrated with empirical signal timings and stochastic bus dwell times.
Benchmarked three routing paradigms—a fixed-route baseline, a Genetic Algorithm (GA) metaheuristic, and a Double Deep Q-Network (Double DQN) agent—across multiple random seeds under near-critical background traffic.
Uncoordinated static routing caused a 71% reduction in network throughput, while static genetic algorithm optimisation reduced throughput degradation to 37%.
The adaptive Double DQN agent suppressed average vehicle time loss by over 60% and restricted throughput degradation to 24% (p < 0.01) by dynamically redistributing traffic loads.

Cite This Study

Le et al. (2026) studied this question.

synapsesocial.com/papers/6aa8e59be29bd5f6edd2941b https://doi.org/10.1016/j.treng.2026.100461

View Full Paper

Ask AI

Bookmark

September 9, 2026Transportation EngineeringOpen Access

Macroscopic impacts of optimised tourist bus routes on urban road networks: a spatiotemporal analysis

View Full Paper

Ask AI

Bookmark

Authors

PLPhan Gia Bao Le SMSara Moridpour MDMinh Ngoc Dinh

Discussion

Member takes

Overview

Simulation study demonstrates adaptive reinforcement learning limits network throughput loss to 24% in tourist bus fleets, indicating real-time control mitigates urban congestion.

Key Points

To assess the macroscopic network impacts of vehicle-centric tourist bus routing strategies and evaluate an adaptive routing framework under near-critical traffic demand.
Constructed a microscopic traffic simulation of Nha Trang, Vietnam, in SUMO, calibrated with empirical signal timings and stochastic bus dwell times.
Benchmarked three routing paradigms—a fixed-route baseline, a Genetic Algorithm (GA) metaheuristic, and a Double Deep Q-Network (Double DQN) agent—across multiple random seeds under near-critical background traffic.
Uncoordinated static routing caused a 71% reduction in network throughput, while static genetic algorithm optimisation reduced throughput degradation to 37%.
The adaptive Double DQN agent suppressed average vehicle time loss by over 60% and restricted throughput degradation to 24% (p < 0.01) by dynamically redistributing traffic loads.

Cite This Study

Le et al. (2026) studied this question.

synapsesocial.com/papers/6aa8e59be29bd5f6edd2941b https://doi.org/10.1016/j.treng.2026.100461

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark