InterTwin: Deep Learning Approaches for Computing Measures of Effectiveness for Traffic Intersections

Microscopic simulation-based approaches are extensively used for determining good signal timing plans on traffic intersections. Measures of Effectiveness (MOEs) such as wait time, throughput, fuel consumption, emission, and delays can be derived for variable signal timing parameters, traffic flow patterns, etc. However, these techniques are computationally intensive, especially when the number of signal timing scenarios to be simulated are large. In this paper, we propose InterTwin, a Deep Neural Network architecture based on Spatial Graph Convolution and Encoder-Decoder Recurrent networks that can predict the MOEs efficiently and accurately for a wide variety of signal timing and traffic patterns. Our methods can generate probability distributions of MOEs and are not limited to mean and standard deviation. Additionally, GPU implementations using InterTwin can derive MOEs, at least four to five orders of magnitude faster than microscopic simulations on a conventional 32 core CPU machine.

Influence of Strong Light on the Performance of Piezoresistive Pressure Sensor

It is found that the strong light in the explosion field has great interference to the piezoresistive pressure sensor, then the shock wave data obtained by the sensor is distorted badly. To study the influence mechanism of the strong light on the piezoresistive pressure sensor, a strong light experimental platform is built. The positions of the sensor and the light source are adjusted, and the outputs of the piezoresistive pressure sensor are observed. Through microscopic simulation, the influence of different light intensities on the piezoresistive pressure sensor is analyzed. In order to reduce the influence of strong light on the performance of piezoresistive pressure sensor, we propose to add a reflective layer on the pressure surface of the sensor. The light reflection effects of different film thicknesses are analyzed through film simulation software. At the same time, the reflection effect is verified through experiments. To explain the effect of the reflective layer on the suppression of strong light, a simulation model is established, and the suppression effect of the reflective layer is verified.

Microscopic Kinetics in Poly(Methyl Methacrylate) Exposed to a Single Ultra-Short XUV/X-ray Laser Pulse

We study the behavior of poly(methyl methacrylate) (PMMA) exposed to femtosecond pulses of extreme ultraviolet and X-ray laser radiation in the single-shot damage regime. The employed microscopic simulation traces induced electron cascades, the thermal energy exchange of electrons with atoms, nonthermal modification of the interatomic potential, and a triggered atomic response. We identify that the nonthermal hydrogen decoupling triggers ultrafast fragmentation of PMMA strains at the absorbed threshold dose of ~0.07 eV/atom. At higher doses, more hydrogen atoms detach from their parental molecules, which, at the dose of ~0.5 eV/atom, leads to a complete separation of hydrogens from carbon and oxygen atoms and fragmentation of MMA molecules. At the dose of ~0.7 eV/atom, the band gap completely collapses indicating that a metallic liquid is formed with complete atomic disorder. An estimated single-shot ablation threshold and a crater depth as functions of fluence agree well with the experimental data collected.

Unconventional Intersection Designs for Improving Traffic Operation Along Arterial Roads

The main objective of this paper is to evaluate the effect of implementing four Unconventional Arterial Intersection Designs (UAIDs) including median U-Turn, Superstreet, Jughandle and Single Quadrant Intersection on a major arterial road using SYNCHRO microscopic simulation software. For this purpose, Wadi Saqra Signalized Intersection on Shaker Bin Zaid major arterial road in Amman, Jordan was selected. The simulation results showed that only the Jughandle improved the intersection Level of Service (LOS) slightly, F–E. Nevertheless, the intersection delay was significantly reduced by 64.81%, 76.6%, 91.28% and 75.60% on the proposed Median U-Turn, Superstreet, Jughandle and Single Quadrant unconventional intersection design, respectively. This indicated that these UAIDs don't perform well under heavy traffic volumes. Also, since the Jughandle was the only UAID which improved the LOS on the main intersection, the operational performance of Prince Shaker Bin Zaid arterial after implementing the Jughandle at the main intersection was evaluated including the main intersection: Wadi Saqra intersection, one prior to the main intersection and one after the main intersection. It was found that the use of the Jughandle increased the average travel speed by 35% and decreased the average stopped delay by 28.68% on the arterial road. Also, this paper evaluated the current transportation system and road user's attitude towards UAIDs' implementation through a questionnaire survey. The results indicated high acceptance of UAIDs. Finally, the construction cost for each UAID type was estimated. It was found that the Jughandle had the highest construction cost due to its high acquisition cost.

Performance Evaluation of a Hybrid Roundabout Using a Microscopic Simulation

Roundabouts are one of the safest types of intersections. There are a number of roundabout types in literature. Each roundabout type is distinguished by some characteristics. To design more efficient junctions, hybrid roundabouts can be created by combining their required characteristics geometrically. In this study, the safety feature of the turbo junction type and the easing up the traffic density feature of the hamburger junction have been combined. Some geometric parameters and layout details of the proposed hybrid roundabout are given, and its performance was simulated in a signalised 4-leg roundabout as the most frequently used intersection in Antalya. The performance of the proposed hybrid roundabout was compared with the status in 2016 and the current status in 2017 and beyond of the roundabout through AIMSUN transport simulation software. In regard to performance analysis, delay time, travel time, speed, density, fuel consumption, number of stops, queuing, carbon emission were analysed for all statuses and compared. In addition, traffic safety analysis has been performed for all statuses and compared. Results show that the overall average performance of the proposed roundabout increases by 40% and 41.8% in comparison with the statutes in 2016, 2017 and beyond, respectively. The proposed roundabout is 41% safer than the status in 2016, and the accident risk is lower by 18.5% than the current status.

Change in Microscopic Traffic Simulation Practice with Respect to the Emerging Automated Driving Technology

It is believed that autonomous vehicles will replace conventional human drive vehicles in the next decades due to the emerging autonomous driving technology, which will definitely bring a massive transformation in the road transport sector. Due to the high complexity of traffic systems, efficient traffic simulation models for the assessment of this disruptive change are critical. The objective of this paper is to justify that the common practice of microscopic traffic simulation needs thorough revision and modification when it is applied with the presence of autonomous vehicles in order to get realistic results. Two high-fidelity traffic simulators (SUMO and VISSIM) were applied to show the sensitivity of microscopic simulation to automated vehicle’s behavior. Two traffic evaluation indicators (average travel time and average speed) were selected to quantitatively evaluate the macro-traffic performance of changes in driving behavior parameters (gap acceptance) caused by emerging autonomous driving technologies under different traffic demand conditions.

Parameter Sensitivity Analysis of a Cooperative Dynamic Bus Lane System With Connected Vehicles

This paper aims to evaluate the sensitivity of the proposed cooperative dynamic bus lane system with microscopic traffic simulation models. The system creates a flexible bus priority lane that is only activated on demand at an appropriate time with advanced information and communication technologies, which can maximize the use of road space. A decentralized multi-lane cooperative algorithm is developed and implemented in a microscopic simulation environment to coordinate lane changing, gap acceptance, and car-following driving behavior for the connected vehicles (CVs) on the bus lane and the adjacent lanes. The key parameters for the sensitivity study include the penetration rate and communication range of CVs, considering the transition period and gradual uptake of CVs. Multiple scenarios are developed and compared to analyze the impact of key parameters on the system’s performance, such as total saved travel time of all passengers and travel time variation among buses and private vehicles. The microscopic simulation models showed that the cooperative dynamic bus lane system is significantly sensitive to the variations of the penetration rate and the communication range in a congested traffic state. With a CV system and a communication range of 150 m, buses obtain maximum benefits with minimal impacts on private vehicles in the study simulation. The safety concerns induced by cooperative driving behavior are also discussed in this paper.