Alexander Genser

Last Name

Genser

First Name

Alexander

ORCID

0000-0002-7454-0443

Show all metadata

Search Results

Publications 1 - 10 of 31

Antifragile perimeter control
Sun, Linghang; Makridis, Michail; Genser, Alexander; et al. (2024)
arXiv
The optimal operation of transportation networks is often susceptible to unexpected disruptions, such as traffic incidents and social events. Many established control strategies rely on mathematical models that struggle to cope with real-world uncertainties, leading to a significant decline in effectiveness when faced with substantial disruptions. While previous research works have dedicated efforts to improving the robustness or resilience of transportation systems against disruptions, this paper applies the cutting-edge concept of antifragility to better design a traffic control strategy for urban road networks. Antifragility sets itself apart from robustness and resilience as it represents a system's ability to not only withstand stressors, shocks, and volatility but also thrive and enhance performance in the presence of such adversarial events. Hence, modern transportation systems call for solutions that are antifragile. In this work, we propose a model-free deep Reinforcement Learning (RL) scheme to control a two-region urban traffic perimeter network. The system exploits the learning capability of RL under disruptions to achieve antifragility. By monitoring the change rate and curvature of the traffic state with the RL framework, the proposed algorithm anticipates imminent disruptions. An additional term is also integrated into the RL algorithm as redundancy to improve the performance under disruption scenarios. When compared to a state-of-the-art model predictive control approach and a state-of-the-art RL algorithm, our proposed method demonstrates two antifragility-related properties: (a) gradual performance improvement under disruptions of constant magnitude; and (b) increasingly superior performance under growing disruptions.
A novel, modular validation framework for collision avoidance of automated vehicles at road junctions
Nitsche, Philippe; Welsh, Ruth H.; Genser, Alexander; et al. (2018)
2018 21st International Conference on Intelligent Transportation Systems (ITSC)
This paper presents a new validation method for automated driving systems at road junctions. The method comprises the clustering of critical traffic scenarios at junctions as well as a simulation and evaluation framework to validate those scenarios. The safety performance indicators selected and implemented in the framework can be seen as a new reference for conducting virtual tests at junctions. The applicability of the framework is demonstrated by an experiment based on a selected car-to-car collision scenario. Considering the current progression of automated transport, this work is highly relevant for virtual testing procedures and is an important step towards approval and certification of automated vehicles.
Exploring antifragility in traffic networks
Sun, Linghang; Makridis, Michail; Genser, Alexander; et al. (2024)
2024 TRB Annual Meeting Online Program Archive
The optimal operation of transportation networks is often susceptible to unexpected disruptions, such as traffic incidents and social events. Many established control strategies rely on mathematical models that often struggle to cope with real-world uncertainties, leading to a significant decline in their effectiveness when faced with substantial disruptions. While previous research works have dedicated efforts to enhancing the robustness or resilience of transportation systems against disruptions, in this paper, we use the concept of antifragility to better design a traffic control strategy for urban road networks. Antifragility represents a system's ability to not only withstand stressors, shocks, and volatility but also thrive and enhance performance in the presence of such disruptions. Hence, modern transport systems call for solutions that are antifragile. In this work, we propose a model-free deep Reinforcement Learning (RL) algorithm to regulate perimeter control in a two-region urban traffic network to exploit and strengthen the learning capability of RL under disruptions and achieve antifragility. By incorporating antifragility terms based on the change rate and curvature of the traffic state into the RL framework, the proposed algorithm further gains knowledge of the traffic state, which helps in anticipating imminent disruptions. An additional term is also integrated into the RL algorithm as redundancy to enhance the performance under disruption scenarios. When compared to a state-of-the-art model predictive control approach and a state-of-the-art RL algorithm, our proposed method demonstrates two antifragility-related properties: (a) gradual performance improvement under disruptions of similar magnitude; and (b) increasingly superior performance under growing disruptions.
Exploring antifragility in traffic networks
Sun, Linghang; Makridis, Michail; Genser, Alexander; et al. (2023)
Enhancement of SPaT-messages with machine learning based time-to-green predictions
Genser, Alexander; Ambühl, Lukas; Yang, Kaidi; et al. (2020)
The involvement of digital technology has changed the transportation domain significantly in the last decade. The availability of several new data sources (i.e., sensor technology or vehicle technology) postulates for data-driven methodologies that can be incorporated into well-established traffic management systems on a macro- and micro-scopic level. Furthermore, the upcoming developments,such as Vehicle-to-Infrastructure (V2I), open the door for new approaches that allow considering communication between vehicles and infrastructure. Recent evolution in traffic signal control of urban intersections (e.g., actuated signal control, self-control algorithms, etc.) influence the signal phases and result in variable green, red and cycle times. Hence, speed advisory systems would benefit from the information about when the next green phase starts so that vehicles do not have to stop when crossing an intersection. Nevertheless, predictions for residual times of these quantities are not trivial and require a sophisticated modeling approach.
Time-to-Green predictions for fully-actuated signal control systems with supervised learning
Genser, Alexander; Makridis, Michail; Yang, Kaidi; et al. (2022)
arXiv
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.
Identification of critical ride comfort sections by use of a validated vehicle model and Monte Carlo simulations
Genser, Alexander; Nitsche, Philippe; Kouvelas, Anastasios (2019)
2019 IEEE Intelligent Transportation Systems Conference (ITSC)
A coherent way to enhance the user acceptance of autonomous vehicles (AV) is to ensure maximum ride comfort along the driven route. This paper proposes a sub-microscopic simulation framework that can be utilized to assess the ride comfort based on data from vehicle dynamics. In a future connected vehicle environment, this work can be used to enable an optimized route and motion planning, by avoiding sections with poor ride comfort and/or adapting the driving style and behavior. The developed methodology proposes a process chain for producing accurate and representative comfort estimates, by utilizing a road surface model, a non-linear model optimization, and Monte Carlo simulations. A case study with three real road sites demonstrates the effective tuning of the framework with real data and achieves high-resolution comfort results. The simulation investigations of the developed framework provide results and insights that justify the importance of enhancing available data sources with ride comfort data.
Critical ride comfort detection for automated vehicles
Genser, Alexander; Spielhofer, Roland; Nitsche, Philippe; et al. (2021)
SVT Working Papers
In a future connected vehicle environment, an optimized route and motion planning should not only fulfill efficiency and safety constraints but also minimize vehicle motions and oscillations, causing poor ride comfort perceived by passengers. This work provides a framework for a large-scale and cost-efficient evaluation to address AV’s ride comfort and allow the comparison of different comfort assessment strategies. The proposed tool also gives insights to comfort data, allowing for the development of novel algorithms, guidelines, or motion planning systems incorporating passenger comfort. A vehicle-road simulation framework utilizable to assess the most common ride comfort determination strategies based on vehicle dynamics data is presented. The developed methodology encompasses a road surface model, a non-linear vehicle model optimization, and Monte Carlo simulations to allow for an accurate and cost-efficient generation of virtual chassis acceleration data. Ride comfort is determined by applying a commonly used threshold method and an analysis based on ISO 2631. The two methods are compared against comfort classifications based on empirical measurements of the International Roughness Index (IRI). A case study with three road sites in Austria demonstrates the framework’s practical application with real data and achieves high-resolution ride comfort classifications. The results highlight that ISO 2631 comfort estimates are most similar to IRI classifications and that the thresholding procedure detects preventable situations but also over- or underestimates ride comfort. Hence, the work shows the potential risk of negative ride comfort of AVs using simple threshold values and stresses the importance of a robust comfort evaluation method for enhancing AVs’ path and motion planning with maximal ride comfort.
Dynamic congestion pricing for multi-region networks: A traffic equilibria approach
Genser, Alexander; Kouvelas, Anastasios (2019)
The growing number of people living in cities results in rising mobility demand, and as aconsequence, the limited capacity of traffic networks gets more stressed. Hence, congested network links are causing travel delays and negative impacts on the environment, postulating for a methodology to overcome this challenge. Considering the broad range of traffic management systems, congestion pricing is a very effective tool to tackle today’s cities traffic problems. Different strategies are available in literature or even applied in real-world that show a positive effect on the traffic situation. This paper proposes a framework design that allows the testing of pricing policies and to evaluate their performance in alleviating congestion. The study implements a multi-regionurban network, where the urban regions are considered as homogeneous and replicated with a representative Macroscopic Fundamental Diagram (MFD). To assess the impact that different pricing policies may have on traffic behavior, a route choice algorithm is utilized and a concept for the computation of the dynamic user equilibrium, as well as the system optimum, are proposed. A case study is presented, where the modeling approach is applied to the heterogeneous road traffic network of the city of Zurich, Switzerland.
Real-time traffic state estimation with the application of deep learning techniques
Genser, Alexander (2022)

Publications 1 - 10 of 31

Alexander Genser

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results