A MULTI-AGENT TRAFFIC AND ENVIRONMENTAL SIMULATOR AND ITS APPLICATION TO THE ANALYSIS OF TRAFFIC CONGESTION IN KASHIWA CITY

2007 ◽  
pp. 1925-1930
Author(s):  
Yutaka Nakama ◽  
Shinobu Yoshimura ◽  
Hideki Fujii
Keyword(s):  
Traffic Congestion ◽  
Multi Agent

scholarly journals Application of Multi-Agent Deep Reinforcement Learning to Optimize Real-World Traffic Signal Controls

2021 ◽  
Author(s):  
Maxim Friesen ◽  
Tian Tan ◽  
Jürgen Jasperneite ◽  
Jie Wang
Keyword(s):  
Reinforcement Learning ◽  
Real World ◽  
Traffic Congestion ◽  
Traffic Signal ◽  
Traffic Model ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Control Logic ◽  
Rule Based ◽  
Multi Agent

Increasing traffic congestion leads to significant costs associated by additional travel delays, whereby poorly configured signaled intersections are a common bottleneck and root cause. Traditional traffic signal control (TSC) systems employ rule-based or heuristic methods to decide signal timings, while adaptive TSC solutions utilize a traffic-actuated control logic to increase their adaptability to real-time traffic changes. However, such systems are expensive to deploy and are often not flexible enough to adequately adapt to the volatility of today's traffic dynamics. More recently, this problem became a frontier topic in the domain of deep reinforcement learning (DRL) and enabled the development of multi-agent DRL approaches that could operate in environments with several agents present, such as traffic systems with multiple signaled intersections. However, most of these proposed approaches were validated using artificial traffic grids. This paper therefore presents a case study, where real-world traffic data from the town of Lemgo in Germany is used to create a realistic road model within VISSIM. A multi-agent DRL setup, comprising multiple independent deep Q-networks, is applied to the simulated traffic network. Traditional rule-based signal controls, currently employed in the real world at the studied intersections, are integrated in the traffic model with LISA+ and serve as a performance baseline. Our performance evaluation indicates a significant reduction of traffic congestion when using the RL-based signal control policy over the conventional TSC approach in LISA+. Consequently, this paper reinforces the applicability of RL concepts in the domain of TSC engineering by employing a highly realistic traffic model.

scholarly journals Reversible Transitions in a Cellular Automata-Based Traffic Model with Driver Memory

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-8
Author(s):  
Tomoko Sakiyama ◽  
Ikuo Arizono
Keyword(s):  
Cellular Automata ◽  
Traffic Congestion ◽  
Traffic Model ◽  
Multi Agent Systems ◽  
Scale Free ◽  
Traffic System ◽  
Wide Range ◽  
Multi Agent ◽  
Reversible Transitions ◽  
The Relationship

Here, we develop a new cellular automata-based traffic model. In this model, individual vehicles cannot estimate global traffic flows but can only detect the vehicle ahead. Each vehicle occasionally adjusts its velocity based on the distance to the vehicle in front. Our model generates reversible phase transitions in the vehicle flux over a wide range of vehicle densities, and the traffic system undergoes scale-free evolution with respect to the flux. We thus believe that our model reveals the relationship between the macro-level flows and micro-level mechanisms of multi-agent systems for handling traffic congestion, and illustrates how drivers’ decisions impact free and congested flows.

scholarly journals AN EFFICIENT INTELLIGENT TRAFFIC LIGHT CONTROL AND DEVIATION SYSTEM FOR TRAFFIC CONGESTION AVOIDANCE USING MULTI-AGENT SYSTEM

Transport ◽  
2019 ◽  
Vol 35 (3) ◽  
pp. 327-335 ◽  
Author(s):  
Rajendran Sathiyaraj ◽  
Ayyasamy Bharathi
Keyword(s):  
Traffic Congestion ◽  
Traffic Management ◽  
Ad Hoc ◽  
Road Traffic ◽  
Smart Cities ◽  
Multi Agent System ◽  
Traffic Light ◽  
Traffic Light Control ◽  
Multi Agent ◽  
Hoc Networks

An efficient and intelligent road traffic management system is the corner stone for every smart cities. Vehicular Ad-hoc NETworks (VANETs) applies the principles of mobile ad hoc networks in a wireless network for Vehicle-to-vehicle data exchange communication. VANETs supports in providing an efficient Intelligent Transportation System (ITS) for smart cities. Road traffic congestion is a most common problem faced by many of the metropolitan cities all over the world. Traffic on the road networks are widely increasing at a larger rate and the current traffic management systems is unable to tackle this impediment. In this paper, we propose an Efficient Intelligent Traffic Light Control and Deviation (EITLCD) system, which is based on multi-agent system. This proposed system overcomes the difficulties of the existing traffic management systems and avoids the traffic congestion problem compare to the prior scenario. The proposed system is composed of two systems: Traffic Light Controller (TLC) system and Traffic Light Deviation (TLD) system. The TLC system uses three agents to supervise and control the traffic parameters. TLD system deviate the vehicles before entering into congested road. Traffic and travel related information from several sensors are collected through a VANET environment to be processed by the proposed technique. The proposed structure comprises of TLC system and makes use of vehicle measurement, which is feed as input to the TLD system in a wireless network. For route pattern identification, any traditional city map can be converted to planar graph using Euler’s path approach. The proposed system is validated using Nagel–Schreckenberg model and the performance of the proposed system is proved to be better than the existing systems in terms of its time, cost, expense, maintenance and performance.

scholarly journals Application of Multi-Agent Deep Reinforcement Learning to Optimize Real-World Traffic Signal Controls

2021 ◽  
Author(s):  
Maxim Friesen ◽  
Tian Tan ◽  
Jürgen Jasperneite ◽  
Jie Wang
Keyword(s):  
Reinforcement Learning ◽  
Real World ◽  
Traffic Congestion ◽  
Traffic Signal ◽  
Traffic Model ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Control Logic ◽  
Rule Based ◽  
Multi Agent

Increasing traffic congestion leads to significant costs associated by additional travel delays, whereby poorly configured signaled intersections are a common bottleneck and root cause. Traditional traffic signal control (TSC) systems employ rule-based or heuristic methods to decide signal timings, while adaptive TSC solutions utilize a traffic-actuated control logic to increase their adaptability to real-time traffic changes. However, such systems are expensive to deploy and are often not flexible enough to adequately adapt to the volatility of today's traffic dynamics. More recently, this problem became a frontier topic in the domain of deep reinforcement learning (DRL) and enabled the development of multi-agent DRL approaches that could operate in environments with several agents present, such as traffic systems with multiple signaled intersections. However, most of these proposed approaches were validated using artificial traffic grids. This paper therefore presents a case study, where real-world traffic data from the town of Lemgo in Germany is used to create a realistic road model within VISSIM. A multi-agent DRL setup, comprising multiple independent deep Q-networks, is applied to the simulated traffic network. Traditional rule-based signal controls, currently employed in the real world at the studied intersections, are integrated in the traffic model with LISA+ and serve as a performance baseline. Our performance evaluation indicates a significant reduction of traffic congestion when using the RL-based signal control policy over the conventional TSC approach in LISA+. Consequently, this paper reinforces the applicability of RL concepts in the domain of TSC engineering by employing a highly realistic traffic model.

Sign in / Sign up

Export Citation Format

Share Document