<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
Max-Pressure (MP) control is a decentralized real-time traffic signal control method that is popular for its simplicity and theoretical stability. However, most existing MP controllers prioritize throughput for private vehicles without accounting for the specific needs of transit services that are essential for sustainable urban mobility. This oversight can exacerbate transit delays and undermine the effectiveness of public transportation systems. To address these challenges, this study introduces a Priority-MP framework that integrates transit signal priority and driver advisory systems into MP control for multi-modal traffic networks. By weighting pressures based on real-time vehicle occupancy and considering more realistic scenarios that account for the presence of transit stations, Priority-MP prioritizes high-occupancy transit vehicles while ensuring network queue stability. In addition, the framework integrates driver advisory systems to provide speed and dwell time recommendations for transit vehicles. Experiments on a real-world multi-modal traffic corridor in Amsterdam show that compared to existing MP control methods: 1) Priority-MP highlights an important trade-off: it significantly reduces average passenger delay by prioritizing high-occupancy transit vehicles, even though this may lead to increased average vehicle delay when the impact of transit stations are ignored; 2) Priority-MP considering transit stations reduces both vehicle delay and passenger delay while maintaining the network stability; and 3) Priority-MP integrating driver advisory systems further improves the travel smoothness of transit vehicles by reducing transit queuing counts.
...
Max-Pressure (MP) control is a decentralized real-time traffic signal control method that is popular for its simplicity and theoretical stability. However, most existing MP controllers prioritize throughput for private vehicles without accounting for the specific needs of transit services that are essential for sustainable urban mobility. This oversight can exacerbate transit delays and undermine the effectiveness of public transportation systems. To address these challenges, this study introduces a Priority-MP framework that integrates transit signal priority and driver advisory systems into MP control for multi-modal traffic networks. By weighting pressures based on real-time vehicle occupancy and considering more realistic scenarios that account for the presence of transit stations, Priority-MP prioritizes high-occupancy transit vehicles while ensuring network queue stability. In addition, the framework integrates driver advisory systems to provide speed and dwell time recommendations for transit vehicles. Experiments on a real-world multi-modal traffic corridor in Amsterdam show that compared to existing MP control methods: 1) Priority-MP highlights an important trade-off: it significantly reduces average passenger delay by prioritizing high-occupancy transit vehicles, even though this may lead to increased average vehicle delay when the impact of transit stations are ignored; 2) Priority-MP considering transit stations reduces both vehicle delay and passenger delay while maintaining the network stability; and 3) Priority-MP integrating driver advisory systems further improves the travel smoothness of transit vehicles by reducing transit queuing counts.
Smart traffic systems, like those using wellestablished methods such as SCOOT, SCATS and TUC, aim to improve traffic flow by dynamically adjusting signal timings based on real-time traffic conditions. Traffic engineers need to understand the objective functions behind traffic signal control to analyze, improve, and optimize network performances. However, different jurisdictions, different operators and competing interests imply that the underlying objective functions governing traffic signal control might not be publicly known with sufficient detail (e.g. to preserve Intellectual Property Rights). A method for discovering these functions is therefore needed, particularly to enable better cooperation among stakeholders. In this work, we train computer models to mimic the decisions made by smart traffic light systems. Using data from a simulated traffic network (with virtual sensors tracking vehicles), we test a variety of supervised models, ranging from simple decision trees to more complex neural networks. Our results show these models can accurately mimic the underlying system's actions, achieving up to 99% accuracy. This work demonstrates that supervised learning can serve as a powerful tool for uncovering hidden traffic control functions by training models to replicate the system's decisions. By analyzing these models, we can then infer the key factors influencing signal control, thereby gaining insights into the underlying objective function.
...
Smart traffic systems, like those using wellestablished methods such as SCOOT, SCATS and TUC, aim to improve traffic flow by dynamically adjusting signal timings based on real-time traffic conditions. Traffic engineers need to understand the objective functions behind traffic signal control to analyze, improve, and optimize network performances. However, different jurisdictions, different operators and competing interests imply that the underlying objective functions governing traffic signal control might not be publicly known with sufficient detail (e.g. to preserve Intellectual Property Rights). A method for discovering these functions is therefore needed, particularly to enable better cooperation among stakeholders. In this work, we train computer models to mimic the decisions made by smart traffic light systems. Using data from a simulated traffic network (with virtual sensors tracking vehicles), we test a variety of supervised models, ranging from simple decision trees to more complex neural networks. Our results show these models can accurately mimic the underlying system's actions, achieving up to 99% accuracy. This work demonstrates that supervised learning can serve as a powerful tool for uncovering hidden traffic control functions by training models to replicate the system's decisions. By analyzing these models, we can then infer the key factors influencing signal control, thereby gaining insights into the underlying objective function.
