Monitoring and forecasting of road traffic conditions is a common practice for real traffic information system, and is of vital importance to traffic management and control. While dynamic traffic patterns can be intuitively represented by space-time diagrams, this study proposes a new concept of space-time image (ST-image) to incorporate physical meanings of traffic state variables. We therefore transform the forecasting problem for time-series traffic states into a conditional image generation problem. We explore the inherent properties of the ST images from the perspectives of physical meaning and traffic dynamics. An innovative deep learning based architecture is designed to process the ST-image, and a diffusion model is trained to obtain traffic forecasts by generating the future ST-images based on the historical patterns.

Accurate prediction of highway traffic is of vital importance to proactive traffic monitoring, operation and controls. In the data mining of highway traffic, abstracting temporal knowledge is often prioritized than exploring topological relationship. In this study, we propose a deep learning model, called Knowledge-Sequence-to-Sequence (K-Seq2Seq), to solve the short-term highway traffic prediction problem in two stages: representing temporal knowledge and predicting future traffic. Through computational experiment in a road section of a Swedish motorway, we show that our model outperforms the conventional Seq2Seq model significantly, more than 20% when predicting information of longer time step.

To meet policy requirements on increased transport energy efficiency and reduced emissions, smart control and management of vehicles and fleets have become important for the development of eco-friendly intelligent transportation systems (ITS). The emergence of new information and communication technologies and their applications, particularly vehicle-to-vehicle and vehicle-to-infrastructure communication, facilitates the implementation of autonomous vehicle concepts, and meanwhile serves as an effective means for control of vehicle fleet by continuously providing support and guidance to drivers. While convoy driving of trucks by longitudinal automation could save 5-15% of fuel consumption due to the reduction of airdrag resistance, this study attempts to investigate the energy saving potential of truck platoons by intelligent speed planning. Assuming that real-time traffic information is available because of communication, an efficient speed control algorithm is proposed based on optimal control theory. The method is faster than the conventional dynamic programming approach and hence applied in the study to analyze energy saving potential of simple platoon operations including acceleration and deceleration. The numerical result shows significant improvement on energy saving due to speed planning during platooning. It can be further applied for more complex platooning operations.

To meet policy requirements on increased transport energy eciency and reduced emissions, smart control and management of vehicles and eets have become important for the development of eco-friendly intelligent transportation systems (ITS). The emergence of new information and communication technologies and their applications, particularly vehicle to vehicle and vehicle-to-infrastructure communication, facilitates the implementation of autonomous vehicle concepts, and meanwhile serves as an eective means for control of vehicle eet by continuously providing support and guidance to drivers. While convoy driving of trucks by longitudinal automation could save 5-15% of fuel consumption due to the reduction of airdrag resistance, this study attempts to investigate the energy saving potential of truck platoons by intelligent speed planning. Assuming that real-time trac information is available because of communication, an ecient speed control algorithm is proposed based on optimal control theory. The method is faster than the conventional dynamic programming approach and hence applied in the study to analyze energy saving potential of simple platoon operations including acceleration and deceleration. The numerical result shows signicant improvement on energy saving due to speed planning during platooning. It can be further applied for more complex platooning operations.

The objective of the EU project COMPANION is to develop co-operative mobility technologies for supervised vehicle platooning, in order to improve fuel efficiency and safety for goods transport. The potential social and environmental benefits inducted by heavy-duty vehicle platoons have been largely proven. However, until now, the creation, coordination, and operation of such platoons have been mostly neglected. In addition, the regulation and standardization of coordinated platooning, together with its acceptance by the end-users and the society need further attention and research. In this paper we give an overview over the project and present the architecture of the off-board and onboard platforms of the COMPANION cooperative platoon management system. Furthermore, the consortium reports on the first results of the human factors for platooning, legislative analysis of platooning aspects, clustering and optimization of platooning plans and prediction of congestion due to planned special events. Finally, we present the method of validation of the system via simulation and trials.

The control algorithm used for deciding on the speed limit in variable speed limit systems is crucial for the performance of the systems. The algorithm is designed to fulfil the purpose of the variable speed limit system, which can be one or several of the following aspects: increasing safety, increasing efficiency and decreasing environmental impacts. Today, many of the control algorithms used in practice are based on fixed thresholds in speed and/or flow. Therefore, they are not necessarily reflecting the current traffic conditions. Control algorithms with a greater level of complexity can be found in the literature. In this paper, four existing control algorithms are investigated to conclude on important characteristics affecting the performance of the variable speed limit system. The purpose of the variable speed limit system and, consequently, the design of the control algorithm differ. Requirements of the investigated control algorithms are that they should be easy to interpret and the execution time should be short. The algorithms are evaluated through microscopic traffic simulation. Performance indicators related to traffic safety, traffic efficiency and environmental impacts are presented. The results show that the characteristics of the variable speed limit system and the design of the control algorithm will have effect on the resulting traffic performance, given that the drivers comply with the variable speed limits. Moreover, the time needed to trigger the system, the duration and the size of speed limit reductions, and the location of the congestion are factors of importance for the performance of variable speed limit systems.

Variable speed limit systems where variable message signs are used to show speed limits adjusted to the prevailing road or traffic conditions are installed on motorways in many countries. The objectives of variable speed limit system installations are often to decrease the number of accidents and to increase traffic efficiency. Currently, there is an interest in exploring the potential of cooperative intelligent transport systems including communication between vehicles and/or vehicles and the infrastructure. In this paper, we study the potential benefits of introducing infrastructure to vehicle communication, autonomous vehicle control and individualized speed limits in variable speed limit systems. We do this by proposing a cooperative variable speed limit system as an extension of an existing variable speed limit system. In the proposed system, communication between the infrastructure and the vehicles is used to transmit variable speed limits to upstream vehicles before the variable message signs become visible to the drivers. The system is evaluated by the means of microscopic traffic simulation. Traffic efficiency and environmental effects are considered in the analysis. The results of the study show benefits of the infrastructure to vehicle communication, autonomous vehicle control and individualized speed limits for variable speed limit systems in the form of lower acceleration rates and thereby harmonized traffic flow and reduced exhaust emissions.

Variable Speed Limit Systems (VSLS) where variable message signs show speed limits based on traffic or road conditions exist on motorways in many countries. The purpose of the VSLS is to decrease the number of accidents while increasing efficiency of traffic system. Cooperative systems are a type of intelligent transport system that has received increasing interest lately. The central part of a cooperative system is communication between vehicles and/or vehicles and the infrastructure. In this paper, a cooperative systems extension of a VSLS is proposed and evaluated by means of microscopic traffic simulation. In the proposed cooperative VSLS, communication between the vehicles and the infrastructure is made available via a roadside unit communicating the speed limits to vehicles upstream on the road. Both aggregate and micro-scale emission models are used to estimate emission from vehicle states in traffic flow. The results of the study show that the cooperative VSLS has a potential to contribute to flow harmonization and to reduce environmental impacts. The emission estimates in the study are dependent on the emission models being applied.

Wheel loader is one of the most widely used heavy-duty vehicles for transporting building materials in construction site. Improvement of its efficiency is important for sustainable transport and construction operations. This paper proposes a path optimization approach that allows us to plan loader trajectory and corresponding vehicle motions in construction site when the topological relief information is available. Vehicle dynamics is modeled for 3D motions considering the power balance of vehicle propulsion. The path planning problem is then formulated using a framework of constrained optimal control where vehicle dynamics is incorporated as system constraints. In order to solve the problem, a discrete search method is developed based on the principle of dynamic programming (DP), in which the states of the forward and backward movement paths of wheel loader are explored in parallel. A numerical study is then presented to demonstrate the application of the proposed approach for optimizing the loader path using terrain information.

Earthwork, as an essential part of almost all heavy construction projects, is an energy consuming procedure and pollution source for both transport and construction sectors. Due to the increasing need and interest to achieve sustainable development in construction, the evaluation of emission and energy impact in earthwork is of high importance for improving the environmental sustainability. This paper proposes an approach to estimate emissions and fuel usage of construction equipment by using experimental data collected from a project mainly carried out in China. In the experiment, emissions and operational parameters of two loaders and two hauler trucks were measured and analyzed. Based on the power efficiency and other factors, different operation cycles are defined for wheel loader and trucks in the real measurement. Then, through establishing an estimation approach, the emission and fuel rates for different operational cycles are finally calculated. The results show that there are remarkable differences for emissions under different working conditions. In order to evaluate and reduce the emissions and fuel values of the whole earthwork project, a discrete-event simulation (DES) is developed and employed to simulate the earthwork scenarios in a detailed case study. The model provides a basis for the integration of the emission calculation with earthwork simulation. During the evaluation, an alternative plan has been proposed and analyzed for lowering the environmental impacts of the earthmoving operations.

Quantification of nonroad machinery emissions is of high importance for improving heavy construction processes especially concerning environmental sustainability. In comparison to the substantial research effort on modeling dynamic emissions for road transport, there is, however, lack of knowledge on how to quantify dynamic emissions during construction operations. This paper proposes an approach to model dynamic NOx emission for nonroad construction machinery using recent experimental data collected by a wheel loader operated in the Chinese environment. In the experiment, emissions were measured during different operational cycles for wheel loader and the data is used for both model calibration and validation. Starting from an initial emission map built from in-lab engine bench test, the model prediction of dynamic NOx emission is calibrated by three real-time engine performance parameters highly correlated to the NOx generation. Considering the characteristics of the nonroad equipment, a dynamic module is added to represent engine state transition due to frequent switching of an operational mode in construction activities, making the whole model more accurate in predicting instantaneous emission levels. Compared to the validation data randomly selected from three different cycle tests, the model shows good performance concerning prediction accuracy and with the capacity of handling drastic changes of the working condition of the machine. While the study focuses on the engine-out NOx emission the resulting methodology can be generalized for emission modeling of other nonroad construction machines.

Air quality and fuel efficiency has become important factors in decision-makings on urban traffic planning and management. To support the process simulation models have potential to play essential roles in evaluation of planning alternatives and control strategies. However, traffic and its environmental impacts are different processes and often require various levels of models. With concerns on high computing performance and rich functionalities, it may be not appropriate to model emission inventory within traffic simulation. In this paper, we present a distributed simulation approach, and an independent emission/energy computing platform is built to simulate, visualize and analyze online emission outputs, given a microscopic traffic simulation tool, KTH-TPMA. Two distributed computing frameworks, common objects request broker architecture (CORBA) and service oriented architecture (SOA), are adopted in the distributed software design and implementation. Several emission models are implemented and generally evaluated in microsimulation runs of two road networks.

In this paper, we propose a numerical approach to calibrate dynamic emission models when on-road or in-lab instantaneous emission measurements are not fully available. Microscopic traffic simulation is applied to generate dynamic vehicle states in the second-by-second level. Using aggregate estimation of ARTEMIS as a standard reference, a numerical optimization scheme on the basis of a stochastic gradient approximation algorithm is applied to find optimal parameters for the dynamic emission model. The calibrated model has been validated on several road networks with traffic states generated by the same simulation model. The results show that with proper formulation of the optimization objective function the estimated dynamic emission model can reasonably capture the trends of online emissions of traffic fleets.

This paper proposes GraphPro, a short-term link speed prediction framework for signalized urban traffic networks. Different from other traditional approaches that adopt only reactive inputs (i.e., surrounding traffic data), GraphPro also accepts proactive inputs (i.e., traffic signal timing). This allows GraphPro to predict link speed more accurately, depending on whether or not there is a contextual change in traffic signal timing. A Wasserstein generative adversarial network (WGAN) structure, including a generator (prediction model) and a discriminator, is employed to incorporate unprecedented network traffic states and ensures a high level of generalizability for the prediction model. A hybrid graph block, comprised of a reactive cell and a proactive cell, is implemented into each neural layer of the generator. In order to jointly capture spatio-temporal influences and signal contextual information on traffic links, the two cells adopt several key neural network-based components, including graph convolutional network, recurrent neural architecture, and self-attention mechanism. The double-cell structure ensures GraphPro learns from proactive input only when required. The effectiveness and efficiency of GraphPro are tested on a short-term link speed prediction task using real-world traffic data. Due to the capabilities of learning from real data distribution and generating unseen samples, GraphPro offers a more reliable and robust prediction when compared with state-of-the-art data-driven models.

Road link speed is often employed as an essential measure of traffic state in the operation of an urban traffic network. Not only real-time traffic demand but also signal timings and other local planning factors are major influential factors. This paper proposes a short-term traffic speed prediction approach, called PL-WGAN, for urban road networks, which is considered an important part of a novel parallel learning framework for traffic control and operation. The proposed method applies Wasserstein Generative Adversarial Nets (WGAN) for robust data-driven traffic modeling using a combination of generative neural network and discriminative neural network. The generative neural network models the road link features of the adjacent intersections and the control parameters of intersections using a hybrid graph block. In addition, the spatial-temporal relations are captured by stacking a graph convolutional network (GCN), a recurrent neural network (RNN), and an attention mechanism. A comprehensive computational experiment was carried out including comparing model prediction and computational performances with several state-of-the-art deep learning models. The proposed approach has been implemented and applied for predicting short-term link traffic speed in a large-scale urban road network in Hangzhou, China. The results suggest that it provides a scalable and effective traffic prediction solution for urban road networks. 

This paper proposes a decentralized traffic light control system in a multi-agent framework. Each signal controller at an intersection is modeled as an intelligent agent capable of making actions for signal operations according to received detection information. The controller agent works with a turning movement based phasing scheme. Duration of turning movement is determined by a multi-criteria reinforcement learning algorithm. In the design of agent, both traffic mobility and energy efficiency are taken into account. Then, a case study is carried out to assess the performance of the proposed decentralized signal control system. The simulation results outperforms an optimized vehicle-actuated control system by reducing average travel delay and average fuel consumption for vehicles. In particular, the decentralized control system is queue responsive and able to adapt to demand in its green time allocation.

Group-based control is an advanced traffic signal strategy capable of dynamically generating phase sequences at intersections. Combined with the phasing scheme, vehicle actuated timing is often adopted to respond to the detected traffic. However, the parameters of a signal controller are often predetermined in practice, and the control performance may suffer from deterioration when dealing with highly fluctuating traffic demand. This study proposes a group-based signal control approach capable of making decisions based on its understanding of traffic conditions at the intersection level. In particular, the control problem is formulated using a framework of stochastic optimal control for multi-agent system in which each signal group is modeled as an intelligent agent. The agents learn how to react to traffic environment and make optimal timing decisions according to the perceived system states. Reinforcement learning, enhanced by multiple-step backups, is employed as the kernel of the intelligent control algorithm, where each agent updates its knowledge on-line based on a sequence of states during the process. In addition, the proposed system is designated to be compatible with the prevailing signal system. A case study was carried out in a simulation environment to compare the proposed control approach with a benchmark controller used in practice, group-based vehicle actuated (GBVA) controller, whose parameters were off-line optimized using a genetic algorithm. Simulation results show that the proposed adaptive group-based control system outperforms the optimized GBVA control system mainly because of its real-time adaptive learning capacity in response to the changes in traffic demand.

The operation of traffic signal control is of significant importance in traffic management and operation practice, especially under oversaturated condition during the morning and afternoon peak hours. However, the conventional signal control systems showed the limitations in signal timing and phasing under oversaturated situations. This paper proposes a multi-agent adaptive signal control system in the context of group-based phasing techniques. The adaptive signal control system is able to acquire knowledge on-line based on the perceived traffic states and the feedback from the traffic environment. Reinforcement learning with eligibility trace is applied as the learning algorithm in the multi-agent system. As a result, the signal controller makes an intelligent timing decision. Feature-based function approximation method is incorporated into reinforcement learning framework to improve the learning efficiency as well as the quality of signal timing decisions. The learning process of the learning-based signal control is carried out with the aid of a microscopic traffic simulation model. A benchmarking system, an optimized group-based vehicle actuated signal control system, is compared with the proposed adaptive signal control systems. The simulation results show that the proposed adaptive group-based signal control system has the potential to improve the mobility efficiency under different congested situations.

Traffic signal control plays a crucial role in traffic management and operation practice. In the past decade, adaptive signal control systems have shown the abilities to improve the effectiveness of the transportation system in many aspects. This paper proposes an adaptive signal control system in the context of group-based phasing techniques. The adaptive signal control system is modeled as a multi agent System capable of acquiring knowledge on-line based on the perceived traffic states and the feedback from the external environment,. Reinforcement learning is applied as the learning algorithm resulting in intelligent timing decisions. Feature based function approximation method is incorporated into the reinforcement learning framework for the purpose of improving learning efficiency as well as the quality of signal timing decisions. The assessment of such a learning-based signal control system is carried out by using an opensource microscopic traffic simulation software, SUMO. A benchmarking system, the optimized group-based vehicle actuated signal control system, compared with the learning-based signal control systems regarding mobility efficiency. The simulation results show that the proposed adaptive group based signal control system has the potential to improve the mobility efficiency regardless of the settings of traffic demands.

Traffic signal control plays a crucial role in traffic management and operation practices. In the past decade, adaptive signal control systems, capable of adjusting control schemes in response to traffic patterns, have shown the abilities to improve traffic mobility. On the other hand, the negative impacts on environments by increased vehicles attract increased attentions from traffic stakeholders and the general public. Most of the prevalent adaptive signal control systems do not address energy and environmental issues. The present paper proposes an adaptive signal control system capable of taking multi-criteria strategies into account. A general multi-agent framework is introduced for modeling signal control operations. The behavior of each cognitive agent is modeled by a Constrained Markov Decision Process (CMDP). Reinforcement learning algorithms are applied to solve the MDP problem. As a result, the signal controller makes intelligent timing decisions according to a pre-defined policy goal. A case study is carried out for the stage-based control scheme to investigate the effectiveness of the adaptive signal control system from two perspectives, traffic mobility and energy efficiency. The control approach can be further applied to a large network in a decentralized manner. 

Agent-based approaches have gained popularity in engineering applications, but its potential for advanced traffic controls has not been sufficiently explored. This paper presents a multi-agent framework that models traffic control instruments and their interactions with road traffic. A multi-objective Markov decision process is applied to model agent operations, allowing agents to form a decision in the context of multiple policy goals. The problem is reformulated by a constrained Markov decision process (CMDP) to enhance the computational efficiency. In the study, the policy goal with the highest priority becomes the optimization objective, but the other objectives are transferred as constraints for optimization. A reinforcement learning based approach is developed with different function approximation methods used to enhance the control algorithm. For implementation of multi-objective control, a threshold lexicographic ordering method is introduced and integrated with the learning algorithm. While the multi-objective intelligent control method could be potentially applied for different road traffic controls, this paper demonstrates a case study on traffic signal control in a road network in Stockholm. Intersections are modeled as agents that can make intelligent timing decisions according to the detected traffic states and update their knowledge from system feedback. The evaluation results show the benefits offered by the control approach especially when multiple policy requirements are introduced.

Agent-based approaches have gained popularity in engineering applications, but its potential for advanced traffic controls has not been sufficiently explored. This paper presents a multi-agent framework that models traffic control instruments and their interactions with road traffic. A constrained Markov decision process (CMDP) model is used to represent agent decision making in the context of multi-objective policy goals, where the policy goal with the highest priority becomes the single optimization objective and the other goals are transformed as constraints. A reinforcement learning-based computational framework is developed for control applications. To implement the multi-objective decision model, a threshold lexicographic ordering method is introduced and integrated with the learning-based algorithm. Moreover, a two-stage hybrid framework is established to improve the learning efficiency of the model. While the proposed approach is potentially applicable for different road traffic operations, this paper applies the framework for traffic signal control in a network of Stockholm based on traffic simulation. The computational results show that the proposed control approach can handle a complex case of multiple policy requirements. Meanwhile, the agent-based intelligent control has shown superior performance when compared to other optimized signal control methods.

This paper introduces a multi-objective multi-agent framework for traffic light control. In particular, each agent in the proposed framework applies a multi-objective Markov decision process. For intelligent control, a reinforcement learning (RL) algorithm is enhanced with multiple-step backups and a function approximation approach to build the agent's knowledge. Moreover, a thresholded lexicographic ordering (TLO) action policy is integrated with the enhanced RL algorithm to solve the multi-objective control problem, which is reformulated by a constrained Markov decision process. A case study of three intersections is carried out and demonstrates the approach with a conventional stage-based phasing strategy using traffic simulation. The simulation experiments elaborate the benefits brought by MAMOD-TL system compared with optimized fixed-time controllers. More importantly, the Pareto optimality is approximately obtained by setting different control parameters for TLO action policy, which can be considered as a performance metric for decision makers.

An accurate and practical traffic-state estimation (TSE) method for signalized intersections plays an important role in real-time operations to facilitate efficient traffic management. This paper presents a generalized modeling framework for estimating traffic states at signalized intersections. The framework is non-parametric and data-driven, without any requirement on explicit modeling of traffic flow. The Bayesian filter (BF) approach is the core of the framework and introduces a recursive state estimation process. The required transition and measurement models of the BFs are trained using Gaussian process (GP) regression models with respect to a historical dataset. In addition to the detailed derivation of the integration of BFs and GP regression models, an algorithm based on the extended Kalman filter is presented for real-time traffic estimation. The effectiveness of the proposed framework is demonstrated through several numerical experiments using data generated in microscopic traffic simulations. Both fixed-location data (i.e., loop detector) and mobile data (i.e., connected vehicle) are examined with the framework. As a result, the method shows good performance under the different traffic conditions in the experiment. In particular, the approach is suitable for short-term estimation, a challenging task in traffic control and operations.

An accurate and practical traffic-state estimation (TSE) method for signalized intersections plays an important role for real-time operations to facilitate efficient traffic management. This paper presents a generalized modeling framework for estimating traffic states at signalized intersections. The framework is non-parametric and data-driven, without the requirement on explicit models of traffic. Additionally, in principle, any type of data source together with any type of signal controller can be incorporated with the proposed framework. The Bayesian filter (BF) approach is the core of the framework and introduces a recursive state estimation process. The required transition and measurement models of the BFs are trained using Gaussian process (GP) regression models with respect to a set of historical data. A Gaussian process model uses kernel functions to describe the proximity among data points, and the hyper-parameters adopted in the GP model are optimized according to the training data. In addition to the detailed derivation of the integration of BFs and GP regression models, an algorithm based on the extended Kalman filter is presented for real-time traffic estimation. The effectiveness of the proposed framework is demonstrated through several numerical experiments using data generated in microscopic traffic simulations. Both fixed-location data (i.e., loop detector) and mobile data (i.e., connected vehicle) are examined with the framework. As a result, the method performs well for the tested traffic conditions. In particular, the estimator provides a competitive estimation accuracy merely using the position information of a small portion of vehicles at the intersection. The approach is suitable for a short-term estimation requirement, which is normally a challenging task in traffic control and operations.

Group-based signal control is one of the most prevalent control schemes in the European countries. The major advantage of group-based control is its capability in providing flexible phase structures. The current group-based control systems are usually implemented with rather simple timing logics, e.g. vehicle actuated logic. However, such a timing logic is not sufficient to respond to the traffic environment whose inputs, i.e. traffic demands, dynamically change over time. Therefore, the primary objective of this paper is to formulate the existing group-based signal controller as a multi-agent system. The proposed signal control system is capable of making intelligent timing decisions by utilizing machine learning techniques. In this regard, reinforcement learning is a potential solution because of its self-learning properties in a dynamic environment. This paper, thus, proposes an adaptive signal control system, enabled by a reinforcement learning algorithm, in the context of group-based phasing technique. Two different learning algorithms, Q-learning and SARSA, have been investigated and tested on a four-legged intersection. The experiments are carried out by means of an open-source traffic simulation tool, SUMO. Performances on traffic mobility of the adaptive group- based signal control systems are compared against those of a well-established group-based fixed time control system. In the testbed experiments, simulation results reveal that the learning-based adaptive signal controller outperforms group-based fixed time signal controller with regards to the improvements in traffic mobility efficiency. In addition, SARSA learning is a more suitable implementation for the proposed adaptive group-based signal control system compared to the Q-learning approach.

Group-based signal controllers are widely deployed on urban networks in the Nordic countries. However, group-based signal controls are usually implemented with rather simple timing logics, e.g. vehicle actuated timing. In addition, group-based signal control systems with pre-defined signal parameter settings show relatively poor performances in a dynamically changed traffic environment. This study, therefore, presents an adaptive group-based signal control system capable of changing control strategies with respect to non-stationary traffic demands. In this study, signal groups are formulated as individual agents. The signal group agent learns from traffic environments and makes intelligent timing decisions according to the perceived system states. Reinforcement learning with multiple-step backups is applied as the learning algorithm. Agents on-line update their knowledge based on a sequence of states during the learning process rather than purely on the basis of single previous state. The proposed signal control system is integrated into a software-in-the-loop simulation (SILS) framework for evaluation purpose. In the testbed experiments, the proposed adaptive group-based control system is compared to a benchmark signal control system, the well-established group-based fixed-time control system. The simulation results demonstrate that learning-based and adaptive group-based signal control system owns its advantage in dealing with dynamic traffic environments in terms of improving traffic mobility efficiency.

Increasing traffic congestion poses significant challenges for urban planning and management in metropolitan areas around the world. One way to tackle the problem is to resort to the emerging technologies in artificial intelligence. Traffic light control is one of the most traditional and important instruments for urban traffic management. The present study proposes a traffic light control system enabled by a hierarchical multi-agent modeling framework in a decentralized manner. In the framework, a traffic network is decomposed into regions represented by region agents. Each region consists of intersections, modeled by intersection agents who coordinate with neighboring intersection agents through communication. For each intersection, a collection of turning movement agents operate individually and implement optimal actions according to local control policies. By employing a reinforcement learning algorithm for each turning movement agent, the intersection controllers are enabled with the capability to make their timing decisions in a complex and dynamic environment. In addition, the traffic light control operates with an advanced phase composition process dynamically combining compatible turning movements. Moreover, the collective operations performed by the agents in a road network are further coordinated by varying priority settings for relevant turning movements. A case study was carried out by simulations to evaluate the performance of the proposed control system while comparing it with an optimized vehicle-actuated control system. The results show that the proposed traffic light system, after a collective machine learning process, not only improves the local signal operations at individual intersections but also enhances the traffic performance at the regional level through coordination of specific turning movements.

Over the past decades, group-based control has become one of the most popular signal technologies being applied in many cities around the world. LHOVRA control is one of such group-based controls widely employed in Scandinavian countries. While several previous studies showed that group-based control outperforms stage-based control in many aspects, implementation and evaluation of signal controllers are complicated in a real application. In addition, little effort has been put in optimizing such group-based controllers in traffic management practice. This study implements generic group-based control in an object-oriented software framework, while a software-in-the-loop simulation is developed to integrate the signal controller with an open-source traffic simulator, SUMO. Also, stochastic optimization is applied to generate optimal signal parameters according to different settings of objective. In particular, part of the study is to improve the computational performance of the optimization process by parallelized simulation runs. Test-based experiments are finally carried out to evaluate traffic and optimize its impact on a small traffic network in Stockholm.

In freight transport systems, fuel consumption can be significantly reduced by means of heavy-duty vehicle (HDV) platooning on highways. An HDV platoon refers to a group of HDVs with small intermediate distances enabled by the HDVs being equipped by sensors and controllers. It is of importance for transport authorities and industries to explore the effects on overall traffic systems by introducing HDV platooning. Although previous studies have investigated the potential benefits of HDV platooning, the control performance and effects in real traffic have barely been explored. In the present study, a simulation platform has been developed to model and analyze the effects of HDV platoons in real traffic conditions. The simulation model is based on an open-source microscopic traffic simulator, SUMO, and calibrated using data collected by a motorway control system (MCS). The current model incorporates the vehicle dynamics of HDVs in the simulation, while an HDV in a platoon is controlled by a proportional-integral-derivative (PID) controller for its longitudinal behavior. Furthermore, the PID control parameters have been optimized for a driving cycle, according to predefined criteria, while taking vehicle dynamics and stability conditions into account. A case study has been carried out by adopting HDV platooning on a highway stretch in Sweden. The performance of the HDV platoons and effects on the other vehicles on the highway have been evaluated for different scenarios through multiple simulation runs. As a result, it is found that substantial fuel reductions have been achieved for HDVs if they form platoons in the evaluation cases. The analysis of the other vehicles shows only rather small effects when HDV platooning is implemented.

Traffic flow is considered as a stochastic process in road traffic modeling. Computer simulation is a widely used tool to represent traffic system in engineering applications. The increased traffic congestion in urban areas and their impacts require more efficient controls and management. While the effectiveness of control schemes highly depends on accurate traffic model and appropriate control settings, optimization techniques play a central role for determining the control parameters in traffic planning and management applications. However, there is still a lack of research effort on the scientific computing framework for optimizing traffic control and operations and facilitating real planning and management applications. To this end, the present study proposes a model-based optimization framework to integrate essential components for solving road traffic control problems in general. In particular, the framework is based on traffic simulation models, while the solution needs extensive computation during the engineering optimization process. In this work, an advanced genetic algorithm, extended by an external archive for storing globally elite genes, governs the computing framework, and in application it is further enhanced by a sampling approach for initial population and utilizations of adaptive crossover and mutation probabilities. The final algorithm shows superior performance than the ordinary genetic algorithm because of the reduced number of fitness function evaluations in engineering applications. To evaluate the optimization algorithm and validate the whole software framework, this paper illustrates a detailed application for optimization of traffic light controls. The study optimizes a simple road network of two intersections in Stockholm to demonstrate the model-based optimization processes as well as to evaluate the presented algorithm and software performance.

This paper introduces an intelligent control system for traffic signal applications, called Fuzzy Intelligent Traffic Signal (FITS) control. It provides a convenient and economic approach to improve existing traffic light infrastructure. The control system is programmed on an intermediate hardware device capable of receiving messages from signal controller hardware as well as overriding traffic light indications during real-time operations. Signal control and optimization toolboxes are integrated into the embedded software in the FITS hardware device. A fuzzy logic based control has been implemented in FITS. In order to evaluate the effects of FITS system, this study attempts to develop a computational framework to evaluate FITS system using microscopic traffic simulation. A case study is carried out, comparing different commonly used signal control strategies with the FITS control approach. The simulation results show that the control system has the potential to improve traffic mobility, compared to all of the tested signal control strategies, due to its ability in generating flexible phase structures and making intelligent timing decisions. In addition, the effects of detector malfunction are also investigated in this study. The experiment results show that FITS exhibits superior performance than several other controllers when a few detectors are out-of-order due to its self-diagnostics feature.

This paper proposes a parallel recommendation engine, PRECOM, for traffic control operations to mitigate congestion of road traffic in the metropolitan area. The recommendation engine can provide, in real-time, effective and optimal control plans to traffic engineers, who are responsible for manually calibrating traffic signal plans especially when a road network suffers from heavy congestion due to disruptive events. With the idea of incorporating expert knowledge in the operation loop, the PRECOM system is designed to include three conceptual components: an artificial system model, a computational experiment module, and a parallel execution module. Meanwhile, three essential algorithmic steps are implemented in the recommendation engine: a candidate generator based on a graph model, a spatiotemporal ranker, and a context-aware re-ranker. The PRECOM system has been deployed in the city of Hangzhou, China, through both offline and online evaluation. The experimental results are promising, and prove that the recommendation system can provide effective support to the current human-in-the-loop control scheme in the practice of traffic control, operations, and management. 

Freight transport is a fast increasing transportation mode due to the economic growth in the world. Heavy-duty vehicles (HDV) have considerably greater fuel consumption, thus making them a suitable target when new policies in road transport emphasize increased energy efficiency and mitigated emission impacts. Intelligent transportation systems, based on emerging V2X communication technology, open new possibilities for developing fuel-efficient driving support functions considering real traffic information. This indicates a large potential of fuel saving and emission reduction for freight transport. This paper studies a dynamic programming-based optimal speed planning considering a maximum acceleration model for HDVs. The optimal speed control is applied for the deceleration case of HDV platoons due to received information on traffic speed reduction ahead. The control can optimize fuel consumption as well as travel time, and theoretical results for the two cases are presented. For maximal fuel saving, a microscopic traffic simulation study is performed for single HDVs and HDV platoons running in real traffic conditions. The results show a decrease in fuel consumption of more than 80% compared to simulations without applying optimal control, while the fuel consumption of other vehicles in the simulation is not significantly affected.

Freight transport is a fast increasing transportation mode due to the economic growth in the world. Heavy-duty vehicles (HDV) have considerably greater fuel consumption, thus making them a suitable target when new policies in road transport emphasize increased energy efficiency and mitigated emission impacts. Intelligent transportation systems, based on emerging V2X communication technology, open new possibilities for developing fuel-efficient driving support functions considering real traffic information. This indicates a large potential of fuel saving and emission reduction for freight transport. This paper studies a dynamic programming-based optimal speed planning considering a maximum acceleration model for HDVs. The optimal speed control is applied for the deceleration case of HDV platoons due to received information on traffic speed reduction ahead. The control can optimize fuel consumption as well as travel time, and theoretical results for the two cases are presented. For maximal fuel saving, a microscopic traffic simulation study is performed for single HDVs and HDV platoons running in real traffic conditions. The results show a decrease in fuel consumption of more than 80% compared to simulations without applying optimal control, while the fuel consumption of other vehicles in the simulation is not significantly affected.

Inspired by diverse organic systems, autonomic computing is a rapidly growing field in computing science. To highlight this advancement, this chapter summarises the autonomic features utilised in a traffic signal control in the form of an operational control system, not simply a simulation study. In addition, the real-time simulation is used to refine the raw sensor data into a comprehensive picture of the traffic situation. We apply the multi-agent approach both for controlling the signals and for modelling the prevailing traffic situation. In contrast to most traffic signal control studies, the basic agent is one signal (head) also referred to as a signal group. The multi-agent process occurs between individual signal agents, which have autonomy to negotiate their timing, phasing, and priorities, limited only by the traffic safety requirements. The key contribution of this chapter lies not in a single method but rather in a combination of methods with autonomic properties. This unique combination involves a real-time microsimulation together with a signal group control and fuzzy logic supported by self-calibration and self-optimisation. The findings here are based on multiple research projects conducted at the Helsinki University of Technology (now Aalto University). Furthermore, we outline the basic concepts, methods, and some of the results. For detailed results and setup of experiments, we refer to the previous publications of the authors.

In order to assess environmental impacts of local traffic flow, a two-stage parameter tuning approach is proposed for recalibration of the Comprehensive Modal Emission Model (CMEM) using on-road emission measurements collected in Chinese cities. Based on the procedure comprising of grid search and nonlinear simplex optimization, the fuel- and emission-related parameters in the model are estimated to minimize the Mean Square Error (MSE) between model outputs and real measurements. In addition, a regression-based emission model is calibrated using the same data samples to compare performance. It is shown from the numerical results that the tuning process is able of improving the model prediction accuracy, especially concerning the CO emission, when comparing with the original CMEM model and the regression-based model. In addition, the emission models are, after the tuning process, applied together with a traffic simulation model to evaluate dynamic environmental effects of traffic in a case study.

Heavy-duty vehicle (HDV) platooning is a mean to significantly reduce the fuel consumption for the trailing vehicle. By driving close to the vehicle in front, the air drag is reduced tremendously. Due to each HDV being assigned with different transport missions, platoons will need to be frequently formed, merged, and split. Driving on the road requires interaction with surrounding traffic and road users, which will influence how well a platoon can be formed. In this paper, we study how traffic may affect a merging maneuver of two HDVs trying to form a platoon. We simulate this for different traffic densities and for different HDV speeds. Even on moderate traffic density, a platoon merge could be delayed with 20% compared to the ideal case with no traffic. 

Drone-based system is an emerging technology for advanced applications in Intelligent Transport Systems (ITS). This paper presents our latest developments of a visual perception and analysis system, called AVIATOR, for drone-based road traffic management. The system advances from the previous SeeFar system in several aspects. For visual perception, deep-learning based computer vision models still play the central role but the current system development focuses on fast and efficient detection and tracking performance during real-time image processing. To achieve that, YOLOv7 and ByteTrack models have replaced the previous perception modules to gain better computational performance. Meanwhile, a lane-based traffic steam detection module is added for recognizing detailed traffic flow per lane, enabling more detailed estimation of traffic flow patterns. The traffic analytics module has been modified to estimate traffic states using lane-based data collection. This includes detailed lane-based traffic flow counting as well as traffic density estimation according to vehicle arrival patterns per lane.

A general framework is introduced to model driver behavior from real car-following data acquired on Swedish roads using an advanced instrumented vehicle. In early research, the data was classified into different car-following regimes based on fuzzy clustering methods and knowledge obtained from video analysis. In this paper, we propose a multi-regime framework based on the statistical property in each regime and mathematical models adopted in those regimes. This framework is an extension of TSK fuzzy inference system and can be expressed by a Neural-Fuzzy system. Genetic Algorithm (GA) is designed as the main learning method for this system. In practice, this model structure illustrates human knowledge of car-following in a more understandable manner and can be rather flexible as the regime parameters and model forms may vary according to the application context.

This thesis is concerned with modeling of driver behavior based on data collected from real traffic using an advanced instrumented vehicle. In particular, the focus is on driver-following behavior (often called car-following in transport science) for microscopic simulation of road traffic systems. In addition, the modeling methodology developed can be applied for the design of human-centered control algorithms in adaptive cruise control (ACC) and other longitudinal active-safety technologies.

Driver behavior is a constant research topic in the modeling of traffic systems and Intelligent Transportation Systems (ITS), which could be traced back to the work of GeneralMotor (GM) Co. in 1950’s. In the early time, researchers were only interested in the development of driver models fulfilling basic physical properties and producing reasonable flow dynamics on a macroscopic level. With the booming interest on driver modeling on a microscopic level and needs in ITS developments, researchers now emphasize modeling using microscopic data acquired from real world. To follow this research trend, a methodological framework on car-following data acquisition, analysis and modeling has been developed step by step in this thesis, and the basic idea is to build a computational model for car-following behavior by exploration of collected data. To carry out the work, different techniques within the field of modern Artificial Intelligence (AI), namely Computational Intelligence (CI)1, have been applied in the research subtasks e.g. information estimation, behavioral regime classification, regime model integration and model estimation. Therefore, a preliminary introduction of the CI methods being used in this thesis work is included in the text.

As a result of the continuous increase of motor vehicles in city areas, sustainability of road traffic in terms of energy and emission has become, in addition to mobility, one important aspect in the planning and management of transportation. This paper introduces a computational framework to model traffic impacts and optimize traffic control measures by integrating microscopic traffic simulator with instantaneous emission model and multi-objective evolutionary algorithm. The approach is applied for evaluation and improvement of traffic management measures mainly traffic signal plans, concerning not only travel delay but also energy and environmental consequences. A case study is presented to show the Pareto frontiers estimated using different strategies, or combination of optimization objectives.

Increased demand for transport, coupled with energy, climate and environmental concerns, has put more and more pressure for improved performance on traffic systems. The recent development in vehicle-to-infrastructure (V2I) communication provides an effective means for continuous management of vehicle driving. This study presents an essential step of the work towards a dynamic fleet management system that takes advantages of real-time traffic information and communication. Based on the optimal control theory, a methodological approach is developed to control the environmental impacts of live vehicle fleets. In particular, vehicle trajectories that minimize local environmental objectives are derived by applying a discrete dynamic programming method. Numerical examples show that the method is promising for local V2I based traffic management applications and can be further extended for more complex optimal control problems in dynamic fleet management.

In order to fulfill the policy requirements on increased transport energy efficiency and reduced emission impacts, smart control and management of vehicles and fleets have become important for the evolution of green intelligent transportation systems (ITS). The emergence of new information and communication technologies (ICT) and their applications, especially vehicle-to-vehicle and vehicle-to-infrastructure (V2I) communication, serves as an effective means for continuous management of real traffic fleet by providing vehicle driving support and guidance, and therefore affecting driver behavior. This study presents a recent Swedish R&D project for developing a dynamic fleet management system that incorporates real-time traffic information, eco-driving guidance and automated vehicle control in real-time heavy vehicle platooning. In addition to a general illustration of the main objectives of the project, the paper presents a methodological approach to developed local fleet control strategies so that the fuel and emissions of the managed vehicle fleet can be reduced. Speed trajectories minimizing predefined objectives are derived by applying a discrete dynamic programming method, and an instantaneous emission estimator is used for predicting fuel and emissions. Numerical examples show that the method is promising for real-time fleet management applications with support of V2I communication while the computational efficiency of the method needs to be enhanced. The adaptive speed control approach is implemented in a microscopic traffic simulation environment for further evaluation.

Travel time is important information for management and planning of road traffic. In the past decades, automated vehicle identification (AVI) systems have been deployed in many cities for collecting reliable travel time data. The fast technology advance has made the budget cost of such data collection system much cheaper than before. For example, bluetooth and WiFi-based systems have become economically a more feasible way for collecting interval travel time information in urban area. Due to increasing availability of such type of data, this paper aims to develop a travel time prediction approach that may take into account both online and historical measurements. Indeed, a statistical prediction approach for real-time application is proposed, modeling the deviation of live travel time from historical distribution estimated per time interval. An extended Kalman Filter (EKF) based algorithm is implemented to combine online travel time with historical patterns. In particular, the system delay due to vehicle re-identification is considered in the algorithm development. The methods are evaluated using Automated Number Plate Recognition (ANPR) data collected in Stockholm. The results show that the prediction performance is good and reliable in capturing major trends during congestion buildup and dissipation.