Utilizing Lane-Based Strategy to Incorporate Mixed Traffic in Interchange Control for Connected and Autonomous Vehicles

Algomaiah, Majeed; Li, Zhixia

doi:10.1177/0361198119839341

Cited by 6 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yang et al [20] also found a 50% information level for CVs could significantly decrease the delay and stops by maximizing the speed entering the intersection. However, several studies also found that the intersection performance only improved after certain MPRs of CVs/CAVs are reached [10], [21], [22]. Moreover, several studies found that the models trained with only partial information and the interaction between CAVs and HDVs could result in a negative impact on the intersection system performance [8], [9].…”

Section: B Review Of Studies On Mixed Traffic At the Intersectionmentioning

confidence: 99%

Traffic Signal Control Under Mixed Traffic With Connected and Automated Vehicles: A Transfer-Based Deep Reinforcement Learning Approach

Song

Fan²

2021

IEEE Access

View full text Add to dashboard Cite

Backgrounds: The traffic signal control (TSC) system could be more intelligently controlled by deep reinforcement learning (DRL) and information provided by connected and automated vehicles (CAVs). However, the direct training procedure of the DRL is time-consuming and hard to converge. Methods: This study improves the training efficiency of the deep Q network (DQN) by transferring the well-trained action policy of a previous DQN model into a target model under similar traffic scenarios. Different reward parameters, exploration rates, and action step lengths are tested. The performance of the transfer-based DQN-TSC is analyzed by considering different traffic demands and market penetration rates (MPRs) of CAVs. The information level requirements of the DQN-TSC are also investigated. Results: Compared to directly trained DQN, transfer-based models could improve both the training efficiency and model performance. In high traffic scenarios with a 100% MPR of CAVs, the total waiting time, CO2 emission, and fuel consumption in the transfer-based TSC decrease about 38%, 34%, and 34% compared to pre-timed signal schemes. Also, the transfer-based TSC system requires more than 20% to 40% MPRs of CAVs under different traffic demands to perform better than pre-timed signal schemes. Conclusions: The proposed model could improve both the traffic performance of the TSC system and the training efficiency of the DQN model. The insights of this study should be helpful to planners and engineers in designing intelligent signal intersections and providing guidance for engineering applications of the DQN TSC systems.INDEX TERMS Deep reinforcement learning, traffic signal control, transfer learning, mixed traffic, connected and automated vehicles.

show abstract

Section: B Review Of Studies On Mixed Traffic At the Intersectionmentioning

confidence: 99%

Traffic Signal Control Under Mixed Traffic With Connected and Automated Vehicles: A Transfer-Based Deep Reinforcement Learning Approach

Song

Fan²

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…However, when a CAV is rejected, it stops at the advance stop line (ASL), which is an early stop line that allows CAV to accelerate and reach a particular speed before reaching the interchange terminal once CAV request is approved later on. The location of ASL is changeable in our NIC model and its effect on the model was tested by Algomaiah and Li [43].…”

Section: A Reservation-based Control For Autonomous Interchangementioning

confidence: 99%

Next-Generation Interchange Control Based on Centralized Management of Connected and Autonomous Vehicles

Algomaiah

2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

With the rapid advancement of connected and autonomous vehicles (CAV) in terms of testing and usage, the implementation of the autonomous interchange in the real world has become more realistic than before. Since the beginning of the last decade, the concept of autonomous intersection has been developed with slightly different techniques. This paper introduces a next-generation interchange control algorithm (NIC) that deals with service interchange terminals for the CAV with the ability to adjust the dimensions and geometric designs. It proposes six different geometric designs that have been modeled in a simulation software package (VISSIM) to employ the NIC algorithm. The system depicted a real-world scenario of an interchange with a slight modification on the geometric design to provide smoother entry to the interchange terminal. The analysis of the proposed designs in terms of throughput, capacity, delay, and volume-to-capacity (V/C) ratio indicated different performance measurements based on the analyzed traffic movements. Tight turn with one left dedicated turn provided the highest performance, while wide turn with two left shared turns indicated the lowest performance. Both NIC designs demonstrated significantly higher throughputs and significantly lower delays compared to a current traffic signal system. By applying the NIC with the existence of the CAV, the operation of highway interchange can be significantly improved. INDEX TERMS Autonomous vehicles, interchange traffic management, centralized control, reservationbased system, connected vehicles.

show abstract

Cooperative and Automated Traffic Control

Wei¹,

Kashyap²,

Li³

2022

Disruptive Emerging Transportation Technologies

View full text Add to dashboard Cite

Utilizing Lane-Based Strategy to Incorporate Mixed Traffic in Interchange Control for Connected and Autonomous Vehicles

Cited by 6 publications

References 15 publications

Traffic Signal Control Under Mixed Traffic With Connected and Automated Vehicles: A Transfer-Based Deep Reinforcement Learning Approach

Traffic Signal Control Under Mixed Traffic With Connected and Automated Vehicles: A Transfer-Based Deep Reinforcement Learning Approach

Next-Generation Interchange Control Based on Centralized Management of Connected and Autonomous Vehicles

Cooperative and Automated Traffic Control

Contact Info

Product

Resources

About