Reinforcement Learning Based Variable Speed Limit Control for Mixed Traffic Flows

2021 ◽  
Author(s):  
Filip Vrbanic ◽  
Edouard Ivanjko ◽  
Sadko Mandzuka ◽  
Mladen Miletic
Keyword(s):  
Reinforcement Learning ◽  
Speed Limit ◽  
Mixed Traffic ◽  
Traffic Flows ◽  
Variable Speed ◽  
Variable Speed Limit ◽  
Variable Speed Limit Control

scholarly journals Variable Speed Limit and Ramp Metering for Mixed Traffic Flows: A Review and Open Questions

2021 ◽  
Vol 11 (6) ◽  
pp. 2574
Author(s):  
Filip Vrbanić ◽  
Edouard Ivanjko ◽  
Krešimir Kušić ◽  
Dino Čakija
Keyword(s):  
Traffic Control ◽  
Ramp Metering ◽  
Transport Infrastructure ◽  
Control Algorithms ◽  
Speed Limit ◽  
Mixed Traffic ◽  
Traffic Flows ◽  
Variable Speed ◽  
Variable Speed Limit ◽  
Traffic Demand

The trend of increasing traffic demand is causing congestion on existing urban roads, including urban motorways, resulting in a decrease in Level of Service (LoS) and safety, and an increase in fuel consumption. Lack of space and non-compliance with cities’ sustainable urban plans prevent the expansion of new transport infrastructure in some urban areas. To alleviate the aforementioned problems, appropriate solutions come from the domain of Intelligent Transportation Systems by implementing traffic control services. Those services include Variable Speed Limit (VSL) and Ramp Metering (RM) for urban motorways. VSL reduces the speed of incoming vehicles to a bottleneck area, and RM limits the inflow through on-ramps. In addition, with the increasing development of Autonomous Vehicles (AVs) and Connected AVs (CAVs), new opportunities for traffic control are emerging. VSL and RM can reduce traffic congestion on urban motorways, especially so in the case of mixed traffic flows where AVs and CAVs can fully comply with the control system output. Currently, there is no existing overview of control algorithms and applications for VSL and RM in mixed traffic flows. Therefore, we present a comprehensive survey of VSL and RM control algorithms including the most recent reinforcement learning-based approaches. Best practices for mixed traffic flow control are summarized and new viewpoints and future research directions are presented, including an overview of the currently open research questions.

scholarly journals An Overview of Reinforcement Learning Methods for Variable Speed Limit Control

2020 ◽  
Vol 10 (14) ◽  
pp. 4917
Author(s):  
Krešimir Kušić ◽  
Edouard Ivanjko ◽  
Martin Gregurić ◽  
Mladen Miletić
Keyword(s):  
Reinforcement Learning ◽  
Machine Learning Techniques ◽  
Future Research ◽  
Speed Limit ◽  
Variable Speed ◽  
Variable Speed Limit ◽  
Promising Alternative ◽  
Learning Techniques ◽  
Comprehensive Survey ◽  
Variable Speed Limit Control

Variable Speed Limit (VSL) control systems are widely studied as solutions for improving safety and throughput on urban motorways. Machine learning techniques, specifically Reinforcement Learning (RL) methods, are a promising alternative for setting up VSL since they can learn and react to different traffic situations without knowing the explicit model of the motorway dynamics. However, the efficiency of combined RL-VSL is highly related to the class of the used RL algorithm, and description of the managed motorway section in which the RL-VSL agent sets the appropriate speed limits. Currently, there is no existing overview of RL algorithm applications in the domain of VSL. Therefore, a comprehensive survey on the state of the art of RL-VSL is presented. Best practices are summarized, and new viewpoints and future research directions, including an overview of current open research questions are presented.

Assessing the mobility benefits of proactive optimal variable speed limit control during recurrent and non-recurrent congestion

2015 ◽  
Vol 42 (7) ◽  
pp. 477-489 ◽  
Author(s):  
Ying Luo ◽  
M. Hadiuzzaman ◽  
Jie Fang ◽  
Tony Z. Qiu
Keyword(s):  
Traffic Control ◽  
Propagation Speed ◽  
Speed Limit ◽  
Variable Speed ◽  
Variable Speed Limit ◽  
Detection Delay ◽  
Traffic Performance ◽  
Total Travel Time ◽  
Variable Speed Limit Control ◽  
The Impact

Over the past few decades, several active traffic control methods have been proposed to improve freeway efficiency at bottleneck locations. Variable speed limit (VSL) is one of these effective controls. Previous studies have evaluated VSL control, but primarily during recurrent congestion only. This study focuses on evaluating the performance of VSL control for both recurrent and non-recurrent congestion. To assess the effectiveness of a previously proposed VSL control in a real-world situation, this study has three evaluation objectives: (1) examine the control performance when recurrent and (or) non-recurrent congestion occurs; (2) assess the effectiveness of the control when a queue encounters the VSL sign; and (3) consider the impact of system detection delay in VSL control. Comparative experiments for Whitemud Drive in Edmonton, Alberta, Canada, are simulated in the VISSIM platform, and traffic performance is compared among scenarios with and without control. The simulation results show that VSL improves mobility for both recurrent and non-recurrent congestion. The VSL control reduces total travel time, and improves total travel distance and total flow. Furthermore, it slows down the shockwave propagation speed, improves the average speed on most of the freeway segments, and reduces the duration of traffic recovery.

Sign in / Sign up

Export Citation Format

Share Document