Michail Makridis

Kevin Riehl, Justin Weiss, Anastasios Kouvelas et al.

Traffic signal control at intersections, especially in arterial networks, is a key lever for mitigating the growing issue of traffic congestion in cities. Despite the widespread deployment of SCOOTS and SCATS, which prioritize efficiency, fairness has remained largely absent from their design logic, often resulting in unfair outcomes for certain road users, such as excessive waiting times. Fairness however, is a major driver of public acceptance for implementation of new controll systems. Therefore, this work proposes FairSCOSCA, a fairness-enhancing extension to these systems, featuring two novel yet practical design adaptations grounded in multiple normative fairness definitions: (1) green phase optimization incorporating cumulative waiting times, and (2) early termination of underutilized green phases. Those extensions ensure fairer distributions of green times. Evaluated in a calibrated microsimulation case study of the arterial network in Esslingen am Neckar (Germany), FairSCOSCA demonstrates substantial improvements across multiple fairness dimensions (Egalitarian, Rawlsian, Utilitarian, and Harsanyian) without sacrificing traffic efficiency. Compared against Fixed-Cycle, Max-Pressure, and standard SCOOTS/SCATS controllers, FairSCOSCA significantly reduces excessive waiting times, delay inequality and horizontal discrimination between arterial and feeder roads. This work contributes to the growing literature on equitable traffic control by bridging the gap between fairness theory and the practical enhancement of globally deployed signal systems. Open source implementation available on GitHub.

Kevin Riehl, Omar Alami Badissi, Anastasios Kouvelas et al.

Ramp metering is a widely deployed traffic management strategy for improving freeway efficiency, yet conventional approaches often lead to highly uneven delay distributions across on-ramps, undermining user acceptance and long-term sustainability. While existing fairness-aware ramp metering methods can mitigate such disparities, they typically rely on centralized optimization, detailed traffic models, or data-intensive learning frameworks, limiting their real-world applicability, particularly in networks operating legacy ALINEA-based systems. This paper proposes C-EQ-ALINEA, a decentralized, coordinated, and equity-aware extension of the classical ALINEA feedback controller. The approach introduces lightweight information exchange among neighbouring ramps, enabling local coordination that balances congestion impacts without centralized control, additional infrastructure, or complex optimization. C-EQ-ALINEA preserves the simplicity and robustness of ALINEA while explicitly addressing multiple notions of fairness, including Harsanyian, Egalitarian, Rawlsian, and Aristotelian perspectives. The method is evaluated in a calibrated 24-hour microsimulation of Amsterdam's A10 ring road using SUMO. Results demonstrate that C-EQ-ALINEA substantially improves the equity of delay distributions across ramps and users, while maintaining (in several configurations surpassing) the efficiency of established coordinated strategies such as METALINE. These findings indicate that meaningful fairness gains can be achieved through minimal algorithmic extensions to widely deployed controllers, offering a practical and scalable pathway toward sustainable and socially acceptable freeway operations. Open source implementation available on GitHub.

Alexander Genser, Michail A. Makridis, Kaidi Yang et al.

Recently, efforts have been made to standardize signal phase and timing (SPaT) messages. These messages contain signal phase timings of all signalized intersection approaches. This information can thus be used for efficient motion planning, resulting in more homogeneous traffic flows and uniform speed profiles. Despite efforts to provide robust predictions for semi-actuated signal control systems, predicting signal phase timings for fully-actuated controls remains challenging. This paper proposes a time series prediction framework using aggregated traffic signal and loop detector data. We utilize state-of-the-art machine learning models to predict future signal phases' duration. The performance of a Linear Regression (LR), a Random Forest (RF), and a Long-Short-Term-Memory (LSTM) neural network are assessed against a naive baseline model. Results based on an empirical data set from a fully-actuated signal control system in Zurich, Switzerland, show that machine learning models outperform conventional prediction methods. Furthermore, tree-based decision models such as the RF perform best with an accuracy that meets requirements for practical applications.

Kevin Riehl, Anastasios Kouvelas, Michail Makridis

City road infrastructure is a public good, and over-consumption by self-interested, rational individuals leads to traffic jams. Congestion pricing is effective in reducing demand to sustainable levels, but also controversial, as it introduces equity issues and systematically discriminates lower-income groups. Karma is a non-monetary, fair, and efficient resource allocation mechanism, that employs an artificial currency different from money, that incentivizes cooperation amongst selfish individuals, and achieves a balance between giving and taking. Where money does not do its job, Karma achieves socially more desirable resource allocations by being aligned with consumers' needs rather than their financial power. This work highlights the value proposition of Karma, gives guidance on important Karma mechanism design elements, and equips the reader with a useful software framework to model Karma economies and predict consumers' behaviour. A case study demonstrates the potential of this feasible alternative to money, without the burden of additional fees.

Kevin Riehl, Michail Makridis, Anastasios Kouvelas

Advancements in computer science, artificial intelligence, and control systems of the recent have catalyzed the emergence of cybernetic societies, where algorithms play a significant role in decision-making processes affecting the daily life of humans in almost every aspect. Algorithmic decision-making expands into almost every industry, government processes critical infrastructure, and shapes the life-reality of people and the very fabric of social interactions and communication. Besides the great potentials to improve efficiency and reduce corruption, missspecified cybernetic systems harbor the threat to create societal inequities, systematic discrimination, and dystopic, totalitarian societies. Fairness is a crucial component in the design of cybernetic systems, to promote cooperation between selfish individuals, to achieve better outcomes at the system level, to confront public resistance, to gain trust and acceptance for rules and institutions, to perforate self-reinforcing cycles of poverty through social mobility, to incentivize motivation, contribution and satisfaction of people through inclusion, to increase social-cohesion in groups, and ultimately to improve life quality. Quantitative descriptions of fairness are crucial to reflect equity into algorithms, but only few works in the fairness literature offer such measures; the existing quantitative measures in the literature are either too application-specific, suffer from undesirable characteristics, or are not ideology-agnostic. Therefore, this work proposes a quantitative, transactional, distributive fairness framework, which enables systematic design of socially feasible decision-making systems. Moreover, it emphasizes the importance of fairness and transparency when designing algorithms for equitable, cybernetic societies.

Linghang Sun, Michail A. Makridis, Alexander Genser et al.

The optimal operation of transportation systems is often susceptible to unexpected disruptions. Many established control strategies reliant on mathematical models can struggle with real-world disruptions, leading to significant divergence from their anticipated efficiency. This study integrates the cutting-edge concept of antifragility with learning-based traffic control strategies to optimize urban road network operations under disruptions. Antifragile systems not only withstand and recover from stressors but also thrive and enhance performance in the presence of such adversarial events. Incorporating antifragile modules composed of traffic state derivatives and redundancy, a deep reinforcement learning algorithm is developed. Subsequently, it is evaluated in a cordon-shaped transportation network and a case study with real-world data. Promising results highlight that the proposed algorithm provides: (i) superior performance achieving up to 27.6% and 41.9% performance gain over baselines under increasing demand and supply disruptions, (ii) lower distribution skewness under disruptions, demonstrating its relative antifragility against baselines, (iii) effectiveness under limited observability due to real-world data availability constraints, and (iv) the robustness and transferability to be combined with various state-of-the-art RL frameworks. The proposed antifragile methodology is generalizable and holds potential for applications beyond traffic engineering, offering integration into control systems exposed to disruptions across various disciplines.

Linghang Sun, Yifan Zhang, Cristian Axenie et al.

Major cities worldwide experience problems with the performance of their road transportation systems, and the continuous increase in traffic demand presents a substantial challenge to the optimal operation of urban road networks and the efficiency of traffic control strategies. The operation of transportation systems is widely considered to display fragile property, i.e., the loss in performance increases exponentially with the linearly increasing magnitude of disruptions. Meanwhile, the risk engineering community is embracing the novel concept of antifragility, enabling systems to learn from historical disruptions and exhibit improved performance under black swan events. In this study, based on established traffic models, namely fundamental diagrams and macroscopic fundamental diagrams, we first conducted a rigorous mathematical analysis to prove the fragile nature of the systems theoretically. Subsequently, we propose a skewness-based indicator that can be readily applied to cross-compare the degree of fragility for different networks solely dependent on the MFD-related parameters. At last, by taking real-world stochasticity into account, we implemented a numerical simulation with realistic network data to bridge the gap between the theoretical proof and the real-world operations, to reflect the potential impact of uncertainty on the fragility of the systems. This work aims to demonstrate the fragile nature of road transportation systems and help researchers better comprehend the necessity to consider explicitly antifragile design for future traffic control strategies.

Kevin Riehl, Anastasios Kouvelas, Michail Makridis

Over the past few decades, efforts of road traffic management and practice have predominantly focused on maximizing system efficiency and mitigating congestion from a system perspective. This efficiency-driven approach implies the equal treatment of all vehicles, which often overlooks individual user experiences, broader social impacts, and the fact that users are heterogeneous in their urgency and experience different costs when being delayed. Existing strategies to account for the differences in needs of users in traffic management cover dedicated transit lanes, prioritization of emergency vehicles, transit signal prioritization, and economic instruments. Even though they are the major bottleneck for traffic in cities, no dedicated instrument that enables prioritization of individual drivers at intersections. The Priority Pass is a reservation-based, economic controller that expedites entitled vehicles at signalized intersections, without causing arbitrary delays for not-entitled vehicles and without affecting transportation efficiency de trop. The prioritization of vulnerable road users, emergency vehicles, commercial taxi and delivery drivers, or urgent individuals can enhance road safety, and achieve social, environmental, and economic goals. A case study in Manhattan demonstrates the feasibility of individual prioritization (up to 40\% delay decrease), and quantifies the potential of the Priority Pass to gain social welfare benefits for the people. A market for prioritization could generate up to 1 million \$ in daily revenues for Manhattan, and equitably allocate delay reductions to those in need, rather than those with a high income.

Qishen Zhou, Yifan Zhang, Michail A. Makridis et al.

Given a partially observed road network, how can we predict the traffic state of unobserved locations? While deep learning approaches show exceptional performance in traffic prediction, most assume sensors at all locations of interest, which is impractical due to financial constraints. Furthermore, these methods typically require costly retraining when sensor configurations change. We propose MoGERNN, an inductive spatio-temporal graph representation model, to address these challenges. Inspired by the Mixture of Experts approach in Large Language Models, we introduce a Mixture of Graph Expert (MoGE) block to model complex spatial dependencies through multiple graph message aggregators and a sparse gating network. This block estimates initial states for unobserved locations, which are then processed by a GRU-based Encoder-Decoder that integrates a graph message aggregator to capture spatio-temporal dependencies and predict future states. Experiments on two real-world datasets show MoGERNN consistently outperforms baseline methods for both observed and unobserved locations. MoGERNN can accurately predict congestion evolution even in areas without sensors, offering valuable information for traffic management. Moreover, MoGERNN is adaptable to dynamic sensing networks, maintaining competitive performance even compared to its retrained counterpart. Tests with different numbers of available sensors confirm its consistent superiority, and ablation studies validate the effectiveness of its key modules.

Kevin Riehl, Shaimaa K. El-Baklish, Anastasios Kouvelas et al.

Accurate prediction of road user movement is increasingly required by many applications ranging from advanced driver assistance systems to autonomous driving, and especially crucial for road safety. Even though most traffic accident fatalities account to bicycles, they have received little attention, as previous work focused mainly on pedestrians and motorized vehicles. In this work, we present the Great GATsBi, a domain-knowledge-based, hybrid, multimodal trajectory prediction framework for bicycles. The model incorporates both physics-based modeling (inspired by motorized vehicles) and social-based modeling (inspired by pedestrian movements) to explicitly account for the dual nature of bicycle movement. The social interactions are modeled with a graph attention network, and include decayed historical, but also anticipated, future trajectory data of a bicycles neighborhood, following recent insights from psychological and social studies. The results indicate that the proposed ensemble of physics models -- performing well in the short-term predictions -- and social models -- performing well in the long-term predictions -- exceeds state-of-the-art performance. We also conducted a controlled mass-cycling experiment to demonstrate the framework's performance when forecasting bicycle trajectories and modeling social interactions with road users.

Qishen Zhou, Yifan Zhang, Michail A. Makridis et al.

Network-wide Traffic State Estimation (TSE), which aims to infer a complete image of network traffic states with sparsely deployed sensors, plays a vital role in intelligent transportation systems. With the development of data-driven methods, traffic dynamics modeling has advanced significantly. However, TSE poses fundamental challenges for data-driven approaches, since historical patterns cannot be learned locally at sensor-free segments. Although inductive graph learning shows promise in estimating states at locations without sensor, existing methods typically handle unobserved locations by filling them with zeros, introducing bias to the sensitive graph message propagation. The recently proposed Dirichlet Energy-based Feature Propagation (DEFP) method achieves State-Of-The-Art (SOTA) performance in unobserved node classification by eliminating the need for zero-filling. However, applying it to TSE faces three key challenges: inability to handle directed traffic networks, strong assumptions in traffic spatial correlation modeling, and overlooks distinct propagation rules of different patterns (e.g., congestion and free flow). We propose DGAE, a novel inductive graph representation model that addresses these challenges through theoretically derived DEFP for Directed graph (DEFP4D), enhanced spatial representation learning via DEFP4D-guided latent space encoding, and physics-guided propagation mechanisms that separately handles congested and free-flow patterns. Experiments on three traffic datasets demonstrate that DGAE outperforms existing SOTA methods and exhibits strong cross-city transferability. Furthermore, DEFP4D can serve as a standalone lightweight solution, showing superior performance under extremely sparse sensor conditions.

Alexander Genser, Noel Hautle, Michail Makridis et al.

Accurate estimation of the traffic state over a network is essential since it is the starting point for designing and implementing any traffic management strategy. Hence, traffic operators and users of a transportation network can make reliable decisions such as influence/change route or mode choice. However, the problem of traffic state estimation from various sensors within an urban environment is very complex for several different reasons, such as availability of sensors, different noise levels, different output quantities, sensor accuracy, heterogeneous data fusion, and many more. To provide a better understanding of this problem, we organized an experimental campaign with video measurement in an area within the urban network of Zurich, Switzerland. We focus on capturing the traffic state in terms of traffic flow and travel times by ensuring measurements from established thermal cameras by the city's authorities, processed video data, and the Google Distance Matrix. We assess the different data sources, and we propose a simple yet efficient Multiple Linear Regression (MLR) model to estimate travel times with fusion of various data sources. Comparative results with ground-truth data (derived from video measurements) show the efficiency and robustness of the proposed methodology.