Simulation Of Urban Mobility Research Articles

A Rear Anti-Collision Decision-Making Methodology Based on Deep Reinforcement Learning for Autonomous Commercial Vehicles

Driving decision-making determines the safety and rationality of autonomous commercial vehicles. Aiming at the issue of safe driving decision-making, herein, a rear anti-collision decision-making methodology based on deep reinforcement learning (RAD-DRL) was creatively proposed. Firstly, aiming at the dynamic coupling of rear anti-collision factors for safe driving, a driving decision network based on an actor-critic framework was proposed for sensor data processing. Then, inspired by the idea of multi-objective optimization, a refined reward function is developed. It comprehensively considers the impact of backward target types, safety clearance, and vehicle roll stability on the rear collision. Finally, the RAD-DRL was trained (with different values of random seeds), tested, and verified in a simulation environment where road network and traffic situations were built-in SUMO (Simulation of Urban Mobility). After 30,000 training episodes, effective and reliable rear anti-collision driving decisions were achieved by our proposed RAD-DRL. The simulated results indicated that the RAD-DRL has remarkable superiority in generalization and effectiveness in expressway scenarios with different driving cases. Especially, it maintained good decision performance in the corner case in which the backward vehicle suddenly accelerates.

Intelligent Traffic Light via Policy-based Deep Reinforcement Learning

Intelligent traffic lights in smart cities can optimally reduce traffic congestion. In this study, we employ reinforcement learning to train the control agent of a traffic light on a simulator of urban mobility. As a difference from existing works, a policy-based deep reinforcement learning method, Proximal Policy Optimization (PPO), is utilized rather than value-based methods such as Deep Q Network (DQN) and Double DQN (DDQN). First, the obtained optimal policy from PPO is compared to those from DQN and DDQN. It is found that the policy from PPO performs better than the others. Next, instead of fixed-interval traffic light phases, we adopt light phases with variable time intervals, which result in a better policy to pass the traffic flow. Then, the effects of environment and action disturbances are studied to demonstrate that the learning-based controller is robust. Finally, we consider unbalanced traffic flows and find that an intelligent traffic light can perform moderately well for the unbalanced traffic scenarios, although it learns the optimal policy from the balanced traffic scenarios only.

An ASP Framework for Efficient Urban Traffic Optimization

Avoiding congestion and controlling traffic in urban scenarios is becoming nowadays of paramount importance due to the rapid growth of our cities' population and vehicles. The effective control of urban traffic as a means to mitigate congestion can be beneficial in an economic, environmental and health way. In this paper, a framework which allows to efficiently simulate and optimize traffic flow in a large roads' network with hundreds of vehicles is presented. The framework leverages on an Answer Set Programming (ASP) encoding to formally describe the movements of vehicles inside a network. Taking advantage of the ability to specify optimization constraints in ASP and the off-the-shelf solver Clingo, it is then possible to optimize the routes of vehicles inside the network to reduce a range of relevant metrics (e.g., travel times or emissions). Finally, an analysis on real-world traffic data is performed, utilizing the state-of-the-art Urban Mobility Simulator (SUMO) to keep track of the state of the network, test the correctness of the solution and to prove the efficiency and capabilities of the presented solution.

Combined Control of Freeway Traffic Involving Cooperative Adaptive Cruise Controlled and Human Driven Vehicles Using Feedback Control Through SUMO

In this study, we propose and test through micro-simulation a novel controller for the combined control of freeway traffic by adopting coordinated Ramp Metering (RM) and Variable Speed Limiting (VSL) strategies. In order to figure out the performance of the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$H_\infty $ </tex-math></inline-formula> State Feedback Controller we have designed, field observations on a real freeway segment with four on-ramps and an off-ramp in the city of Istanbul are used to calibrate the Intelligent Driver Model at SUMO (Simulation of Urban MObility). Scenarios with varying penetration rates of vehicles with Cooperative Adaptive Cruise Control (CACC) in mixed traffic are simulated through SUMO specific to the cases of no control, only coordinated RM control, and the combined coordinated RM + VSL control. Performance of the controller we have proposed has been analyzed considering a number of measures on traffic flow dynamics and emissions exhausted. We define three critical levels for penetration rates of vehicles with CACC in freeway traffic.

ACO-based traffic routing method with automated negotiation for connected vehicles

Most traffic control systems are centralized, where all the collected data can be analyzed to make a decision. However, there are problems with computational complexity and, more seriously, real-time decision-making. This paper proposes a decentralized traffic routing system based on a new pheromone model of ant colony optimization algorithm and an automated negotiation technique in a connected vehicle environment. In particular, connected vehicles utilize a new pheromone model, namely the inverted pheromone model, which generates a repulsive force between vehicles and gives negative feedback to the congested roads. They also perform a collective learning-based negotiation process for distributing traffic flows throughout the road networks, reducing traffic congestion. Via extensive simulations based on the Simulation of Urban Mobility, the proposed system shows that it can significantly reduce travel time and fuel consumption compared to existing systems.

Vehicular connectivity algorithm for cooperative transportation systems

Vehicular Ad-hoc Network (VANET) means connectivity between wireless interface and mobile vehicle equipment which could be of either homogeneous or heterogeneous nature. VANET is an emerging part of research due to its ability to create intelligent transport systems. Roadside fixed equipment (RSU), and on-board unit (OBU) can be either public means of transport service providers or private (belonging to companies or individuals). In this infrastructure, messages flow from vehicle to vehicle and vehicle to roadside via wireless technologies such as IEEE 8.02.11.P and IEEE 1609 WAVE. The main issue in VANET implementation is the design of routing topology that gives accurate vehicle-to-vehicle transmission. In VANET, every participating vehicle node works as a single-vehicle node or wireless router, allowing vehicles that are 100–500 m far from creating a network and connected to each other by a large range using dynamic source routing (DSR) protocol. In this paper, we focus on improving connectivity by integrating simulation of urban mobility (SUMO) with NETSIM and present a new algorithm for packet delivery in different dense environments. In this work, we propose a vehicle connectivity algorithm for less (40), moderate (50), and more (60) number of vehicles and also analyze the threshold value of successfully delivered packets through simulation and the proposed algorithm. In the simulations and proposed method, the overall link and application throughput in VANET is enhanced, and the outcome shows that the connectivity is better than in the other techniques. This study has achieved good throughput in a dense vehicle environment. Performance of the networks has been measured through throughput, delay, packet delivery ratio (PDR), overhead head transmission for less (40), moderate (50), or more (60) number of vehicles on different road paths.

What is the Root Cause of Congestion in Urban Traffic Networks: Road Infrastructure or Signal Control?

Identifying the root cause of congestion and taking appropriate strategies to improve traffic network performance are important goals of Advanced Traffic Management Systems (ATMS). On many occasions, the causes of congestion are not necessarily attributable to road infrastructures themselves. Instead, signal control strategies at intersections are very often the major contributors of congestion. In lieu of this, in this paper, a root cause identification method is developed with consideration of the impact from both road infrastructure and traffic signal control. Firstly, we differentiate congestion effects between road segments and intersections to attribute the causes of congestion to road infrastructure and signal control respectively. Then, we construct causal congestion trees to model congestion propagation and quantify congestion costs for each road segment and intersection in the whole road network. A Markov model is utilized to capture congestion spatio-temporal correlation among multiple road segments and intersections simultaneously, with which the most critical root cause can be located. Furthermore, a gradient boosting decision tree based method is presented to predict the root cause of congestion according to traffic flows, signal control strategies and road topology in traffic networks. Finally, simulations based on Simulation of Urban Mobility (SUMO) validate the effectiveness of our proposed method in identifying and predicting the congestion root cause. Experiments are further conducted using inductive loop detector data to identify the root cause for the road network of Taipei.

An Information Fusion Approach to Intelligent Traffic Signal Control Using the Joint Methods of Multiagent Reinforcement Learning and Artificial Intelligence of Things

With the development of communication technology and artificial intelligence of things (AIoT), transportation systems have become much smarter than ever before. However, the volume of vehicles and traffic flows have rapidly increased. Optimizing and improving urban traffic signal control is a potential way to relieve traffic congestion. In general, traffic signal control is a sequential decision process that conforms to the characteristics of reinforcement learning, in which an agent constantly interacts with its environment, thus providing strategy for optimizing behavior in accordance with feedback in response. In this paper, we propose multiagent reinforcement learning for traffic signals (MARL4TS) to support the control and deployment of traffic signals. First, information on traffic flows and multiple intersections is formalized as input environments for performing reinforcement learning. Second, we design a new reward function to continuously select the most appropriate strategy as control during multiagent learning to track actions for traffic signals. Finally, we use a supporting tool, Simulation of Urban MObility (SUMO), to simulate the proposed traffic signal control process and compare it with other methods. The experimental results show that our proposed MARL4TS method is superior to the baselines. In particular, our method can reduce vehicle delay.

A Trajectory Evaluation Platform for Urban Air Mobility (UAM)

Nowadays, there is an increase in the demand for optimized services in urban environments. However, ground transportation in big urban centers has been facing challenges for many years (e.g., resilience and congestion) and new paradigms have been proposed, such as the Urban Air Mobility (UAM) concept. UAM aims to enhance the urban transportation system using manned and unmanned aerial vehicles (i.e., Electric Vertical Takeoff and Landing - eVTOL - vehicles). Although UAM offers many benefits (e.g., cost reduction and increase in transportation capacity), many challenges need to be faced to enable safe and efficient operations. Furthermore, trajectory planning is challenging in the National Airspace System (NAS) and UAM operations due to several factors. Finally, new initiatives concerning UAM trajectory planning can be accelerated with the support of an automatic what-if platform capable of evaluating trajectories feasibility and efficiency. This research aims to propose a simulation platform for enabling trajectory evaluation in UAM operations. This platform, named Trajectory-Based Urban Air Mobility Simulator (TUS), focuses on simulating trajectories in the urban aerial environment. TUS enables users to test new UAM algorithms (e.g., flow management strategies, real-time evaluation of maneuvers effectiveness, airspace configurations) and simulate both manned and unmanned vehicles. Furthermore, TUS operation relies on a set of inputs and evaluates the trajectories generated from efficiency and safety perspectives. This process is performed using a Discrete Event Simulation (DES) approach. The experiments performed showed that TUS can perform a realistic evaluation of UAM trajectories and can be effortlessly used to simulate hundreds of scenarios.

Simulation of Demand Responsive Transport using a dynamic scheduling tool with SUMO

Demand responsive transport (DRT) has been increasingly tested and applied in recent years as a new form of transportation that seeks to address mobility problems in cities and rural areas. The planning of DRT systems is a challenging task for transport planners since the performance of the service depends significantly on the demand, how the scheduling is made, and how the routes are computed. Transport simulations are a useful option to evaluate these systems. The paper presents a Python tool, which aims to simulate diverse DRT services using the software package for microscopic simulations Eclipse SUMO (Simulation of Urban MObility) as a framework. The fleet and requests of the DRT are handled dynamically by the scheduling module of the tool. This module is also responsible for calling a solver algorithm for the Dial-a-Ride-Problem (DARP), processing its results, and dispatching the DRT vehicles according to them. The tool also enables easier implementation of other methods to solve the DARP. To demonstrate the use of the tool, a DRT service operating in two central neighborhoods of the city of Brunswick (Germany) is presented. The tool is called drtOnline.py and is included in SUMO since version 1.9.0.

A Study of Applying Eco-Driving Speed Advisory System on Transit Signal Priority

Transit Signal Priority (TSP) has long been seen as a cost-effective way to reduce bus delays at intersections. With Connected Vehicle (CV) technology, a speed advisory system guides buses to pass intersections in an energy-saving way. The integration of TSP and speed advisory may reduce bus delays and enhance energy consumption performances. This study proposed a system of integrating eco-driving speed advisory on TSP under CV environment. A TSP strategy based on intersections passing probability is designed. In addition to signal priority, this study designed and implemented an eco-driving speed advisory algorithm. A real electric bus route in Tainan City, Taiwan is used for the case study. Intersection layout and traffic related parameters are established in microscopic traffic simulation software SUMO (Simulation of Urban Mobility) to verify the effectiveness of the proposed model. The results provide an insight into how cooperation between signals and vehicles can enhance performances of energy consumption and signal-incurred traffic delays.

Extending the Intelligent Driver Model in SUMO and Verifying the Drive Off Trajectories with Aerial Measurements

Connected and automated driving functions are key components for future vehicles. Due to implementation issues and missing infrastructure, the impact of connected and automated vehicles on the traffic flow can only be evaluated in accurate simulations. Simulation of Urban Mobility (SUMO) provides necessary and appropriate models and tools. SUMO contains many car-following models that replicate automated driving, but cannot realistically imitate human driving behavior. When simulating queued vehicles driving off, existing car-following models are neither able to correctly emulate the acceleration behavior of human drivers nor the resulting vehicle gaps. Thus, we propose a time-discrete 2D Human Driver Model to replicate realistic trajectories. We start by combining previously published extensions of the Intelligent Driver Model (IDM) to one generalized model. Discontinuities due to introduced reaction times, estimation errors and lane changes are conquered with new approaches and equations. Above all, the start-up procedure receives more attention than in existing papers. We also provide a first evaluation of the advanced car-following model using 30 minutes of an aerial measurement. This dataset contains three hours of drone recordings from two signalized intersections in Stuttgart, Germany. The method designed for extracting the vehicle trajectories from the raw video data is outlined. Furthermore, we evaluate the accuracy of the trajectories obtained by the aerial measurement using a specially equipped vehicle.

Simulation of a Demand Responsive Transport feeder system: A case study of Brunswick

Public transport systems in rural and peri-urban areas are in many cases characterized by long travel times, low frequencies and irregular services. Because of this, motorized private transport is often the only practicable mode of mobility in these regions. The use of Demand Responsive Transport (DRT) as feeder systems to mass public transport modes presents a great potential for improvement. This paper investigates the potential of such a system applied to a case-study of a peri-urban area of Brunswick, Germany. For that, the current bus line was replaced by a Bus Rapid Transit (BRT) line with DRT as feeder systems. In order to evaluate the performance of the proposed system and provide a benchmark against the current public transport o er, multiple trips to the city center with the different transport modes were simulated. The agent-based microscopic simulation Eclipse SUMO (Simulation of Urban MObility) was used as a framework. The scenario of the DRT systems was simulated by SUMO coupled to a developed dispatching algorithm. The results show the potential of the proposed system due to the lower travel times, higher frequency and greater service area. Travel times were even comparable with the travel times of private car-based modes, which could lead to a potential increase in demand.

A Microscopic Platoon Stability Model Using Vehicle-to-Vehicle Communication

With Vehicle-to-Vehicle (V2V) communication capability, vehicle platoon on the highway helps to reduce traffic congestion. However, the dynamic nature of vehicles imposes challenges on the V2V-based platoon management. In this paper, by considering the characteristics of a Vehicular Ad-hoc Network (VANET), a microscopic platoon management scheme is proposed to deal with three basic dynamic platoon maneuvers, namely merging, splitting, and speed-change. The congestion detection feature of VANET is used as a scale for platoon merging, splitting, and speed selection. Real-time congestion is detected if the number of vehicles in a given road segment exceeds the occupancy rate or the time headway is less than the thresholds. In the proposed platoon management scheme, platoon maintenance is triggered in congestion detection. Finally, a VANET-based platoon platform is built by using Network Simulator Version 2 (NS2) network simulation to assess the performance over some real road traces generated by Simulation of Urban MObility (SUMO). It is shown that V2V-based dynamic vehicle platoon management provides an inexpensive technique to cope with the dynamic platoon management requirement.

Feudalistic Platooning: Subdivide Platoons, Unite Networks, and Conquer Efficiency and Reliability.

Cooperative intelligent transportation systems (C-ITSs) such as platooning rely on a robust and timely network that may not always be available in sufficient quality. Out of the box hybrid networks only partly eliminate shortcomings: mutual interference avoidance, data load balancing, and data dissemination must be sophisticated. Lacking network quality may lead to safety bottlenecks that require that the distance between the following vehicles be increased. However, increasing gaps result in efficiency loss and additionally compromise safety as the platoon is split into smaller parts by traffic: maneuvers, e.g., cut-in maneuvers bear safety risks, and consequently lower efficiency even further. However, platoons, especially if they are very long, can negatively affect the flow of traffic. This mainly applies on entry or exit lanes, on narrow lanes, or in intersection areas: automated and non-automated vehicles in traffic do affect each other and are interdependent. To account for varying network quality and enable the coexistence of non-automated and platooned traffic, we present in this paper a new concept of platooning that unites ad hoc—in form of IEEE 802.11p—and cellular communication: feudalistic platooning. Platooned vehicles are divided into smaller groups, inseparable by surrounding traffic, and are assigned roles that determine the communication flow between vehicles, other groups and platoons, and infrastructure. Critical vehicle data are redundantly sent while the ad hoc network is only used for this purpose. The remaining data are sent—relying on cellular infrastructure once it is available—directly between vehicles with or without the use of network involvement for scheduling. The presented approach was tested in simulations using Omnet++ and Simulation of Urban Mobility (SUMO).

A Systematic Cooperation Method for In-Car Navigation Based on Future Time Windows

Traffic congestion has become a severe problem, af-fecting travellers both mentally and economically. To al-leviate traffic congestion, this paper proposes a method using a concept of future time windows to estimate the future state of the road network for navigation. Through our method, we can estimate the travel time not only based on the current traffic state, but the state that ve-hicles will arrive in the future. To test our method, we conduct experiments based on Simulation of Urban MO-bility (SUMO). The experimental results show that the proposed method can significantly reduce the overall travel time of all vehicles, compared to the benchmark Dijkstra algorithm. We also compared our method to the Dynamic User Equilibrium (DUE) provided by SUMO. The experimental results show that the performance of our method is a little better than the DUE. In practice, the proposed method takes less time for computation and is insensitive to low driver compliance: with as low as 40% compliance rate, our method can significantly im-prove the efficiency of the unsignalised road network. We also verify the effectiveness of our method in a signalised road network. It also demonstrates that our method can assign traffic efficiently.

A New Multivariate Approach for Real Time Detection of Routing Security Attacks in VANETs

Routing security attacks in Vehicular Ad hoc Networks (VANETs) represent a challenging issue that may dramatically decrease the network performances and even cause hazardous damage in both lives and equipment. This study proposes a new approach named Multivariate Statistical Detection Scheme (MVSDS), capable of detecting routing security attacks in VANETs based on statistical techniques, namely the multivariate normality tests (MVN). Our detection approach consists of four main stages: first, we construct the input data by monitoring the network traffic in real time based on multiple metrics such as throughput, dropped packets ratio, and overhead traffic ratio. Secondly, we normalize the collected data by applying three different rescaling techniques, namely the Z-Score Normalization (ZSN), the Min-Max Normalization (MMN), and the Normalization by Decimal Scaling (NDS). The resulting data are modeled by a multivariate dataset sampled at different times used as an input by the detection step. The next step allows separating legitimate behavior from malicious one by continuously verifying the conformity of the dataset to the multivariate normality assumption by applying the Rao–Ali test combined with the Ryan–Joiner test. At the end of this step, the Ryan–Joiner correlation coefficient (R–J) is computed at various time windows. The measurement of this coefficient will allow identifying an attacker’s presence whenever this coefficient falls below a threshold corresponding to the normal critical values. Realistic VANET scenarios are simulated using SUMO (Simulation of Urban Mobility) and NS-3 (network simulator). Our approach implemented in the Matlab environment offers a real time detection scheme that can identify anomalous behavior relying on multivariate data. The proposed scheme is validated in different scenarios under routing attacks, mainly the black hole attack. As far as we know, our proposed approach unprecedentedly employed multivariate normality tests to attack detection in VANETs. It can further be applied to any VANET routing protocol without making any additional changes in the routing algorithm.

Decision Making for Self-Driving Vehicles in Unexpected Environments Using Efficient Reinforcement Learning Methods

Deep reinforcement learning (DRL) enables autonomous vehicles to perform complex decision making using neural networks. However, previous DRL networks only output decisions, so there is no way to determine whether the decision is proper. Reinforcement learning agents may continue to produce wrong decisions in unexpected environments not encountered during the learning process. In particular, one wrong decision can lead to an accident in autonomous driving. Therefore, it is necessary to indicate whether the action is a reasonable decision. As one such method, uncertainty can inform whether the agent’s decision is appropriate for practical application where safety must be guaranteed. Therefore, this paper provides uncertainty in the decision by proposing DeepSet-Q with Gaussian mixture (DwGM-Q), which converges the existing DeepSet-Q and mixture density network (MDN). Calculating uncertainty with the Gaussian mixture model (GMM) produced from MDN made it possible to calculate faster than the existing ensemble method. Moreover, it verified how the agent responds to the unlearned situation through the Simulation of Urban MObility (SUMO) simulator and compared the uncertainty of the decision between the learned and nontrained situation.

Enhancing OLSR Protocol by an Advanced Greedy Forwarding Mechanism for VANET in Smart Cities

The future Intelligent Transport System "ITS" is one of the major challenges of the smart city. It requires fast and efficient communication between vehicles (vehicle-to-vehicle “V2V”), to ensure information exchange in order to improve safety, which reduces accidents and consequently save lives, hence the need of the Vehicular Ad Hoc Network “VANET”, which makes possible the inter-vehicle communication. This network is characterized by a variable topology. Therefore, MANET (Mobile Adhoc NETwork) routing protocols need a few tweaks to be available for the vehicle environment. In this paper, we start by exposing some works related to the evaluation of the most well-known protocols. After a comparative study, we deduce that the OLSR (Optimized Link State Routing) protocol outperforms other routing protocols in terms of End-to-End Delay (EED) and Packet Delivery Ratio (PDR). In addition, we note that the Greedy forwarding “GF” mechanism is suited for the VANET environment, which has been improved and called Greedy forwarding Advanced “GFA”, to overcome the stationary node problem. Our approach improves the OLSR protocol to be more suitable and efficient for VANET by introducing the GFA mechanism. Moreover, we compare our approach to the OLSR classic version. In this work, we use a realistic scenario from Open Street Map (OSM), and simulations are performed using SUMO (Simulation of Urban MObility). The trace files generated from SUMO are used for further simulation in NS-3 (Network Simulator) to validate our proposition. The simulation results are analyzed and discussed. Our approach performs best compared to OLSR in terms of EED and PDR, especially for dense traffic.

Infrastructure enabled eco-approach for transit system: A simulation approach

This paper develops an infrastructure-enabled eco-approach specifically for transit systems, where a two-stage simulation approach is proposed to include the impact of bus stops, and can further quantify the effects of infrastructure-enabled eco-approach on transit operating and service. The developed system is then embedded into a well-developed simulation environment, i.e., Simulation of Urban Mobility (SUMO), and a series of real-world-based cases are designed to compare the proposed system with traditional method and non-control case at segment-, line-, and network-level service respectively. Results reveal that the proposed method outperforms the traditional eco approach and can significantly improve the energy efficiency and reduce CO2 emission by up to 54.33%, where the environmental benefits are more clearly seen when more transit services are involved. In particular, it has the capability of marginalizing the speed fluctuations around the bus stop.