Search

Machine learning (ML) methods, particularly Reinforcement Learning (RL), have gained widespread attention for optimizing traffic signal control in intelligent transportation systems. However, existing ML approaches often exhibit limitations in scalability and adaptability, particularly within large traffic networks. This paper introduces an innovative solution by integrating decentralized graph-based multi-agent reinforcement learning (DGMARL) with a Digital Twin to enhance traffic signal optimization, targeting the reduction of traffic congestion and network-wide fuel consumption associated with vehicle stops and stop delays. In this approach, DGMARL agents are employed to learn traffic state patterns and make informed decisions regarding traffic signal control. The integration with a Digital Twin module further facilitates this process by simulating and replicating the real-time asymmetric traffic behaviors of a complex traffic network. The evaluation of this proposed methodology utilized PTV-Vissim, a traffic simulation software, which also serves as the simulation engine for the Digital Twin. The study focused on the Martin Luther King (MLK) Smart Corridor in Chattanooga, Tennessee, USA, by considering symmetric and asymmetric road layouts and traffic conditions. Comparative analysis against an actuated signal control baseline approach revealed significant improvements. Experiment results demonstrate a remarkable 55.38% reduction in Eco_PI, a developed performance measure capturing the cumulative impact of stops and penalized stop delays on fuel consumption, over a 24 h scenario. In a PM-peak-hour scenario, the average reduction in Eco_PI reached 38.94%, indicating the substantial improvement achieved in optimizing traffic flow and reducing fuel consumption during high-demand periods. These findings underscore the effectiveness of the integrated DGMARL and Digital Twin approach in optimizing traffic signals, contributing to a more sustainable and efficient traffic management system. [ABSTRACT FROM AUTHOR]

Smart cities can effectively improve urban life quality. But, with the rise in population size, there is an increase in the use of vehicles for transportation. In smart city development, traffic control and route planning are the primary tasks to address the problem of travel time estimation. It has become complex due to concerns of wrapped spatio-temporal data on dynamic real-time traffic conditions. The existing methods failed to estimate travel time efficiently due to not considering the spatio-temporal features and lack of computing resources. There is a need for a system like intelligent transportation system to monitor and accurately predict traffic flow to avoid traffic congestion and reduce the impact on the ecological system. This paper developed a novel hybrid deep learning model to estimate optimized travel time and possible trajectories. In this work, U-Net used to reduce the number of feature points for each temporal data and GNN is used to build the graph with connectivity between vehicular nodes. This hybrid model helps us predict traffic flow and aims to estimate accurate travel time from one location (node) to another. The model's performance is evaluated on the standard benchmark datasets Q-Traffic, TaxiBJ, and Chengdu. The experimental results show that the proposed framework significantly improves performance in extracting travel patterns and provides an optimal route with an estimated travel time than existing methods with RMSE 4%, MAE 20.49%, and MAPE 18%. The proposed model has accurately predicted the estimation of travel time of the vehicle for the given urban traffic data. [ABSTRACT FROM AUTHOR]

Intelligent Transportation Systems (ITS) face the formidable challenge of large-scale missing data, particularly in the imputation of traffic data. Existing studies have mainly relied on modeling network-level spatiotemporal correlations to address this issue. However, these methods often overlook the rich semantic information (e.g., road infrastructure, sensor location, etc.) inherent in road networks when capturing network-wide spatiotemporal correlations. We address this limitation by presenting the Graph Transformer-based Traffic Data Imputation (GT-TDI) model, which imputes missing values in extensive traffic data by leveraging spatiotemporal semantic understanding of road networks. The proposed model leverages semantic descriptions that capture the spatial and temporal dynamics of traffic across road networks, enhancing its capacity to infer comprehensive spatiotemporal relationships. Moreover, to augment the model's capabilities, we employ a Large Language Model (LLM) and prompt engineering to enable natural and intuitive interactions with the traffic data imputation system, allowing users to query and request in plain language, without requiring expert knowledge or complex mathematical models. The proposed model, GT-TDI, utilizes Graph Neural Networks (GNN) and Transformer architectures to perform large-scale traffic data imputation using deficient observations, sensor social connectivity, and semantic descriptions as inputs. We evaluate the GT-TDI model on the PeMS freeway dataset and benchmark it against cutting-edge models. The experimental evidence demonstrates that GT-TDI surpasses the cutting-edge approaches in scenarios with intricate patterns and varying rates of missing data. • A novel semantic description for traffic data imputation that captures spatiotemporal correlations flexibly. • A pioneering application of prompt engineering to ITS that bridges the gap between LLMs and ITS. • The proposed model leverages LLMs and semantic prompts for traffic data imputation. • Extensive experiments on real-world traffic data show the superiority. • A potential framework for integrating LLMs and semantic prompts into other ITS tasks. [ABSTRACT FROM AUTHOR]