Dense Traffic Conditions Research Articles

Research on robust decision making for intelligent connected vehicle at highway on-ramp

Reinforcement learning has demonstrated its potential in the decision-making field of autonomous driving. By engaging in trial-and-error learning and interacting with the environment, we can adapt our behavioral strategies based on reward and enhance driving decisions. Nevertheless, real-world vehicle decision-making involves intricate and diverse information, and the limited state information hinders agents from making optimal decisions, which may result in catastrophic consequences like collisions. Therefore, this paper proposes a robust deep reinforcement learning method based on the Soft Actor-Critic (SAC) algorithm for highway intelligent connected vehicle ramp merging decision-making. The model represents the vehicle features of the target lane and its adjacent lanes as an environmental state space. Additionally, a hybrid action space is designed, which combines discrete lateral actions and continuous longitudinal actions. Finally, an on-ramp simulation platform is built using actual roads and SUMO to verify the feasibility of the model. Multiple sets of comparative analysis experimental results demonstrate that the proposed method outperforms others in terms of the average reward return value, robustness value, collision rate, and success rate. Moreover, the model exhibits a stable lane change success rate under various road traffic density conditions, which indicates its robustness. The code can be obtained at https://github.com/ColinFanghz/sac-on-ramp.git .

A dynamic priority bus lane strategy in heterogeneous traffic environments

Allowing connected and automated vehicles (CAVs) to drive in bus lanes can enhance the utilization efficiency of exclusive bus lanes. However, this could also lead to a certain degree of heightened bus operating delays. In a connected and automated environment, vehicle-to-vehicle (V2V) communication is essential for implementing dynamic management strategies for bus lanes. This study focuses on urban arterial roads as the research scenario. Based on the characteristics of the car-following and lane-changing behaviors of human-driven vehicles (HDVs) and CAVs, a simulation platform for heterogeneous traffic flow is established. Four strategies for bus lane control are proposed: exclusive bus lanes (EBLs), bus and CAV mixed lanes (BCMLs), dynamic bus lanes (DBLs), and dynamic priority bus lanes (DPBLs). Through simulation experiments, an analysis is conducted to compare traffic operation characteristics under different bus lane strategies, assess the advantages of these strategies, and determine the traffic density conditions for their implementation. The results indicate that in comparison to the EBL strategy, the other strategies enhance traffic flows but result in different levels of travel delays for buses. Compared to the DBL and BCML strategies, the DPBL strategy is applicable under a broader range of traffic density conditions. Additionally, sensitivity analysis revealed that the effects of the V2V communication distance and bus flows on the applicability of DPBL strategies are relatively minor. These results provide a theoretical basis and practical guidance for future bus lane management.

Electric vehicle eco-driving strategy at signalized intersections based on optimal energy consumption

Electric vehicles (EVs), which are a great substitute for gasoline-powered vehicles, have the potential to achieve the goal of reducing energy consumption and emissions. However, the energy consumption of an EV is highly dependent on road contexts and driving behavior, especially at urban intersections. This paper proposes a novel ecological (eco) driving strategy (EDS) for EVs based on optimal energy consumption at an urban signalized intersection under moderate and dense traffic conditions. Firstly, we develop an energy consumption model for EVs considering several crucial factors such as road grade, curvature, rolling resistance, friction in bearing, aerodynamics resistance, motor ohmic loss, and regenerative braking. For better energy recovery at varying traffic speeds, we employ a sigmoid function to calculate the regenerative braking efficiency rather than a simple constant or linear function considered by many other studies. Secondly, we formulate an eco-driving optimal control problem subject to state constraints that minimize the energy consumption of EVs by finding a closed-form solution for acceleration/deceleration of vehicles over a time and distance horizon using Pontryagin’s minimum principle (PMP). Finally, we evaluate the efficacy of the proposed EDS using microscopic traffic simulations considering real traffic flow behavior at an urban signalized intersection and compare its performance to the (human-based) traditional driving strategy (TDS). The results demonstrate significant performance improvement in energy efficiency and waiting time for various traffic demands while ensuring driving safety and riding comfort. Our proposed strategy has a low computing cost and can be used as an advanced driver-assistance system (ADAS) in real-time.

Exploring DQN-Based Reinforcement Learning in Autonomous Highway Navigation Performance Under High-Traffic Conditions

Driving in a straight line is one of the fundamental tasks for autonomous vehicles, but it can become complex and challenging, especially when dealing with high-speed highways and dense traffic conditions. This research aims to explore the Deep-Q Networking (DQN) model, which is one of the reinforcement learning (RL) methods, in a highway environment. DQN was chosen due to its proficiency in handling complex data through integrated neural network approximations, making it capable of addressing high-complexity environments. DQN simulations were conducted across four scenarios, allowing the agent to operate at speeds ranging from 60 to nearly 100 km/h. The simulations featured a variable number of vehicles/obstacles, ranging from 20 to 80, and each simulation had a duration of 40 seconds within the Highway-Env simulator. Based on the test results, the DQN method exhibited excellent performance, achieving the highest reward value in the first scenario, 35.6117 out of a maximum of 40, and a success rate of 90.075%.

Asphalt 60/70 Penetration Analysis of AC/BC Mixture With the Addition of Ethylene Vinyl Acetate (EVA) As Asphalt Raw Material

This study was conducted to determine how much influence EVA (Ethylene Vinyl Acetate) added to Laston AC-BC has on Marshall characteristic values. The Marshall test carried out will produce stability values at the optimum asphalt conditions that meet the 2018 Highways specifications. The stability value will be used to analyze changes in the characteristics of the Laston AC-BC (Asphalt Concrate – Binder Course) mixture after adding a mixture of EVA (Ethylene Vinyl Acetate) . To determine an aggregate gradation in the AC-BC mixed layer, coarse aggregate is used in the form of crushed stone with a maximum size of ” while for fine aggregate it is a mixture of crushed stone, stone ash and sand. The additive or modifier used is EVA (Ethylene Vinyl Acetate) polymer. Next, to obtain good asphalt concrete, the gradation of the aggregate must meet the general specifications of Bina Marga 2018 which have been determined through SNI-ASTM-C136-2012. In making the test object, ± 1200 gram of aggregate and asphalt are needed so that the specified height of the test object will be produced. Through the analysis of the aggregate sieve, the weight of the aggregate required for the test object can be calculated. Modification of asphalt with EVA aims to determine the stiffness and properties of asphalt in resisting loading with a certain penetration value so as to produce a Penetration Index value which will affect the characteristics of asphalt against weather changes. Research and knowledge related to the addition of a mixture of EVA (Ethylene Vinyl Acetate) to asphalt can be further developed so that it can be implemented on types of road pavements with higher traffic density conditions.

Analisis Proses Pengiriman Pesan VMS (Variable Message Sign) pada Lima Ruas Jalan Tol Jabodetabek

Precise, fast and accurate information regarding traffic density conditions is what toll road users need. Toll road users can choose a route that is faster, smoother and safer to pass through information on the traffic conditions of the toll road to be passed in front of them, which is conveyed from the Variable Message Sign (VMS). Given the very dynamic traffic conditions in Jabodetabek and Bandung, a very reliable media and information technology support is needed, so that it can provide information on real traffic conditions, precisely according to conditions in the field. This information can be retrieved from Google Maps periodically as needed to update information on traffic conditions in the segments that will be displayed on the VMS. The segment is usually the distance from gate 1 to the next gate, or Interchange 1 to the next Interchange. The period of retrieval of information via Google Maps depends on the dynamics of traffic conditions that will be displayed on the VMS. For example, information related to traffic conditions for the Tomang – Kebon Jeruk segment, which is very dynamic, requires a shorter period of change or information update than the Kunciran – Parigi or Kunciran – Serpong segments, the period of each information change is longer or infrequent, because the traffic conditions are still small. VMS will display the information generated through the distance and average travel time from 1 point to a certain point in 1 segment of the toll road which is processed so as to produce the average vehicle speed data which will be converted into text that will be displayed on the VMS. The text formatted information is sent to the VMS. The process of withdrawing Google Maps data to sending text to VMS can be done in less than 1 minute, even the process can be carried out for more than 1 VMS and even 10 VMS units in 1 minute. This results in fast and accurate information.

A Preliminary Comparison of Drivers’ Overtaking behavior between Partially Automated Vehicles and Conventional Vehicles

The study investigated drivers' overtaking behavior in partially automated vehicles and conventional vehicles under different traffic density conditions. Twelve participants "drove" a simulated vehicle on a 10-mile straight, two-way rural interstate highway in 4 scenarios (2 (traffic density: Low, High) x 2 (vehicle type: Partially automated vehicle, Conventional vehicle)) in random orders. Participants' driving performance, eye movement, brain activity, and workload were collected and analyzed. Results indicated that vehicle type significantly affects speed standard deviation, pupil dilation and workload. Results also showed that traffic density significantly affects average speed and workload. The findings should help improve the design of automated vehicles and thus improve traffic efficiency.

Analysis of Driver Behavior in Mixed Autonomous and Non-autonomous Traffic Flows

Autonomous vehicles are expected to improve road safety and efficiency in future transportation systems. A driving simulator study was designed to identify driving styles and the cooperation between human drivers and other AVs. The study captured driver’s following behavior in a fully autonomous driving environment at unsignalized intersections. Participants were asked to make a series of maneuvers (straight through intersection, left turn, and right turn) in two different speed conditions (30, 40 mph) and two different traffic density conditions (with or without other traffic). Analysis of Variance showed that drivers had a significantly larger deviation (defined as the area between two trajectories) during left turn maneuvers when they were traveling at higher speeds. Moreover, the first turning operation had smaller deviation than the second turning operation. The findings have implications for the design of driver-assistance guidance systems in future mixed autonomous and non-autonomous traffic flows.

Efficient routing and performance amelioration using Hybrid Diffusion Clustering Scheme in heterogeneous wireless sensor network

SummaryHeterogeneous wireless sensor networks (HWSNs) have a wide range of application in the contemporary world particularly in sensing and hunting of events without human interference. Due to this limitation of network resources and energy of sensor nodes, the contention of available resources for transmission will increase the energy consumption in the network and degrade the performance of Quality of Service. During dense traffic conditions, sensor nodes in close proximity to base station (BS) faces severe bottleneck resulting in congestion and energy hole problem. The efficient utilization of energy and packet loss is due to link break and by traffic analysis attack is a primary threat in HWSN applications. To sustain maximum energy in the network, two important aspects are considered, namely, flawless selection of path and concise clustering. This paper describes about a multi‐objective‐based Hybrid Diffusion Clustering Scheme (HDCS) through Jellyfish routing protocol with Time Division Multiple Access (JRP‐TDMA)‐based routing method in HWSN. Cluster head is elected based on multiple objectives such as residual energy, cost, and distance. Once CH selection is done, JRP‐TDMA based on available timeslot handpicks the best path for transmitting to BS. The proposed protocol is analyzed, simulated, and performance results are correlated with existing protocols namely, diffusion clustered routing protocol (DCRP), efficient unequal clustering (EEUC), Markov chain model‐based optimal cluster head (MOCH), and genetic algorithm (GA). The number of alive sensor nodes of proposed method has increased by 24.4% when compared with other approaches.

DEIT: Dempster Shafer Theory‐based edge‐centric Internet of Things‐specific trust model

AbstractThe potential benefits of edge‐centric Internet of Things (IoT) come with increased security threats and because the edge devices may be compromised into sending or forwarding wrong information. To negate the effect of wrong information on inference, such messages need to be identified. Identification and dropping of messages in the network as early as possible would minimize the communication overhead. Trust values of nodes help in the early identification of such messages. In this work, the Dempster Shafer Theory (DST)‐based edge‐centric IoT‐specific Trust Model (DEIT) is designed to compute trust to include the specific characteristics of IoT. Edge servers use DEIT to compute trust value of edge devices in the network. In DEIT, DST combines the available trust messages. DIET also uses the degradation variable, credibility variable, punishment variable, re‐compensating variable, and pardoning variable to compute final trust value. The computed trust value assists the edges in taking correct decisions. Simulation results demonstrate that it can immediately capture two major types of misbehavior, namely, information drop and modification under both sparse and dense traffic conditions. Through scenarios in the results section, the depiction of various possible misbehaviors has been discussed. Scenario 1 and 2 discuss a situation where a malicious edge device misbehaves in two ways, namely, dropping and modification of information, respectively. In scenario 3 and 4, situations are discussed when the trust opinion of the trusted and distrusted devices are neutralized with time using the degradation factor to illustrate and compare changes in trust values in two different situation.

Vehicle To Vehicle System For Congestion Control And Performance Validation

The vehicle-to-vehicle (V2V) communication is the inter vehicle communication model which is not more applied and systematize by governments. The important attribute of the V2V communication is that it does not depend on other reliable network like cellular network to communicate between other vehicles. It is an ad hoc communication spans up to 1km with 360 view of the near vehicles. Despite the wide range of benefit that V2V offered, it had to face a number of challenges in deployment. Due to the good rated by operator of V2V communication capability to solve road traffic critical safety around the world, increases interest in these technologies. However, in dense traffic conditions as the V2V deployment scales up, the resultant channel load increases and leads to channel congestion and may adversely affect the performance of the safety applications. The primary contribution of this paper is that using a congestion generation test bed that emulates channel congestion including a large number of remote vehicles. In this regard V2V communication is VANET is designed for automobile to interact with each other automatically, using a wireless network and increase the reach around the world.

The importance of public support in the implementation of green transportation in smart cities using smart vehicle bicycle communication transport

Purpose Smart mobility is a major guideline in the development of Smart Cities’ transport systems and management. The issue of transition into green, secure and sustainable transport modes, such as using bicycles, should be implemented in this case, along with the subjectivism of management. Design/methodology/approach The proposed technology reflects the Smart Bicycle vehicle model, which tracks cyclists and weather conditions and turns to electric motors in critical circumstances. Findings This reduces the physical load and battery consumption of cyclists which affects the Smart Cities’ ecology positively. Originality/value In Smart Vehicle Bicycle Communication Transport, the vehicle movement optimization technique is used for traffic scenarios to analyze traffic signaling systems that give better results in variable and dense traffic conditions.

A Performance-Based Airspace Model for Unmanned Aircraft Systems Traffic Management

Recent evolutions of the Unmanned Aircraft Systems (UAS) Traffic Management (UTM) concept are driving the introduction of new airspace structures and classifications, which must be suitable for low-altitude airspace and provide the required level of safety and flexibility, particularly in dense urban and suburban areas. Therefore, airspace classifications and structures need to evolve based on appropriate performance metrics, while new models and tools are needed to address UTM operational requirements, with an increasing focus on the coexistence of manned and unmanned Urban Air Mobility (UAM) vehicles and associated Communication, Navigation and Surveillance (CNS) infrastructure. This paper presents a novel airspace model for UTM adopting Performance-Based Operation (PBO) criteria, and specifically addressing urban airspace requirements. In particular, a novel airspace discretisation methodology is introduced, which allows dynamic management of airspace resources based on navigation and surveillance performance. Additionally, an airspace sectorisation methodology is developed balancing the trade-off between communication overhead and computational complexity of trajectory planning and re-planning. Two simulation case studies are conducted: over the skyline and below the skyline in Melbourne central business district, utilising Global Navigation Satellite Systems (GNSS) and Automatic Dependent Surveillance-Broadcast (ADS-B). The results confirm that the proposed airspace sectorisation methodology promotes operational safety and efficiency and enhances the UTM operators’ situational awareness under dense traffic conditions introducing a new effective 3D airspace visualisation scheme, which is suitable both for mission planning and pre-tactical UTM operations. Additionally, the proposed performance-based methodology can accommodate the diversity of infrastructure and vehicle performance requirements currently envisaged in the UTM context. This facilitates the adoption of this methodology for low-level airspace integration of UAS (which may differ significantly in terms of their avionics CNS capabilities) and set foundations for future work on tactical online UTM operations.

Adaptations in driver behaviour characteristics during control transitions from full-range Adaptive Cruise Control to manual driving: an on-road study

Adaptive Cruise Control (ACC) can reduce traffic congestion and accidents. In dense traffic flow conditions and when changing lanes, drivers prefer to deactivate the ACC. These control transitions between automation and manual driving could impact driver behaviour characteristics. However, few studies have analysed the magnitude and duration of these adaptations. This research aims at quantifying the adaptations in speed, acceleration, distance headway and relative speed when drivers resume manual control. We collected driver behaviour data in an on-road experiment with full-range ACC during peak hours in Munich. We analysed these data using linear mixed-effects models to identify statistically significant changes in driver behaviour characteristics after drivers resumed manual control (transition period). The results reveal that the speed decreased significantly after the system was deactivated and it increased significantly after the system was overruled by pressing the gas pedal. These adaptations might have a substantial impact on traffic efficiency and safety.

Self-Assessment Based Clustering Data Dissemination for Sparse and Dense Traffic Conditions for Internet of Vehicles

Internet of Vehicle (IoV) is a sub class of vehicular ad hoc networks with more advanced cloud and Internet-enabled services. These networks offer various types of safety and infotainment services and provide comfortability and safety to passengers as well as to the drivers. Due to the high mobility of nodes, the nodes are out from its communication range and the information becomes outdated and causes link disconnections and packet dropping. Most feasible routing protocols are needed to provide in-time data communication, handle high mobility of nodes, dynamic topologies and unpredictable environments of these networks. In this paper, we proposed SACBR (Self-Assessment Cluster-based Routing) protocol in which the Cluster Heads (CHs) can communicate with other CHs. Every vehicle node initiates a self-assessment approach based on more appropriate routing metrics and elects the CH for every cluster and then collects the data from member nodes and further forward the data to other CHs. The CH is responsible to manage its own and member nodes’ data forwarding process. The proposed protocol provides more stability and less overhead compared to the aggregation method where every node exchanges its data with a one-hop neighbor. Proposed protocol suites sparse and dense traffic scenarios where most of the time vehicle nodes are moving in platoons or snaking structures. The experimental results show the better performance of SACBR compared to state-of-the-art protocols.

Channel-Aware Congestion Control in Vehicular Cyber-Physical Systems

In vehicular cyber-physical systems, cars are connected to create a mobile network called a vehicular ad hoc network (VANET) to perform various functions, including improved awareness of the surrounding environment. Moving vehicles continually broadcast beacon signals containing information such as position, heading, acceleration, steering angle, vehicle size, and accident notification. However, channel congestion in dense traffic conditions adversely affects network performance. To resolve congestion in VANETs, several works in the literature have studied congestion control. However, they have considered packet loss only as an indication of channel congestion regardless of channel condition. In this paper, we present a channel-aware congestion control algorithm (CACC) that controls the transmission power and data rate. We take into account the received signal strength (RSS) when diagnosing packet loss to determine channel conditions, such as severe fading or channel congestion. In the case of severe fading, we decrease the data rate for a more robust modulation and coding scheme. Additionally, we adjust the transmission power to maintain a desirable packet error rate. Our simulation results show that CACC significantly outperforms other distributed congestion control algorithms by reducing the packet loss rate and increasing the packet delivery ratio.

Cycle-based queue length estimation considering spillover conditions based on low-resolution point detector data

Queue length is vitally important for signal control optimization and congestion management of urban arterials. Due to the existence of mutual influence of neighboring intersections, cycle-by-cycle estimation of queue length under spillover conditions remains a challenging problem given low-resolution detector data. On most urban arterials in China, point detectors are commonly installed at the intersection approaches and the upstream segments, providing volume, occupancy and speed data at a time interval of 1 min, i.e., a double-section low-resolution detection environment. Thus, the objective of this study is to propose a method to estimate the cycle-based queue length at signalized intersections considering spillover in the context of the above detection environment. Considering dense traffic conditions, uniform distribution is used to transform the low-resolution volume data into vehicle arrivals in 1 s. To deal with spillover conditions, mutual effects of neighboring intersections are classified into four different cases, based on the offsets between the neighboring intersections. Detector data at the upstream intersection approach are used to modify the volume data of the downstream intersection when long queue occurs, and the effect of spillover can thus be formulated analytically using the shockwave theory. Finally, the queue length can be calculated by accumulating queue lengths of all offset conditions within a cycle. Evaluation is done through an empirical case of two intersections, and a simulation case of seven intersections. Results show that the accuracy can reach 85.1% and 82.4% respectively. In both cases, spillover cycles can be recognized with stable and reliable performance.

V2V System Congestion Control Validation and Performance

Major international automakers have considered the deployment of the 5.9 GHz dedicated short-range communications (DSRC) on their vehicle fleets for wireless connectivity. DSRC-enabled vehicle-to-vehicle (V2V) communication through broadcast of basic safety messages enables safety applications for crash warning and avoidance. However, in dense traffic conditions as the V2V deployment scales up, the resultant channel load increases and leads to channel congestion and may adversely affect the performance of the safety applications. The Society of Automotive Engineers J2945/1 standard that builds atop Institute of Electrical and Electronics Engineers (IEEE) 802.11p and IEEE 1609 standards provides the minimum performance requirements for V2V safety communications. Specifically, it provides a congestion control protocol for transmission rate and power adaptations to achieve robust performance in dense vehicular networks. The primary contribution of this paper is that using a congestion generation testbed that emulates channel congestion including a large number of remote vehicles, we can validate and test any V2V equipped vehicle for compliance with the J2945/1 standard. Our paper also demonstrates that under heavy congestion, even with 600 ms of inter-transmit time, a moving vehicle can be tracked to a lane-level accuracy.

An Improved Multi-Object Adaptive Cruise Control Approach

Abstract Developments regarding driver assistant systems are one of the most active fields of research and development within the automotive industry. In the present paper, a longitudinal vehicle guidance concept for a multi-object Adaptive Cruise Control (ACC) will be introduced. The goal is to design a reliable, computationally efficient and intuitive approach for ACC which maximizes the drivers comfort in dense traffic conditions. Development of the control structure, as well as the target selection approach, are the central aspects of the paper. The results are verified with measurement data from test drives on the Boulevard Peripherique in Paris.

Cluster‐based data dissemination, cluster head formation under sparse, and dense traffic conditions for vehicular ad hoc networks

SummaryInformation and communication technologies have changed the way of operations in all fields. These technologies also have adopted for wireless communication and provide low cost and convenient solutions. Vehicular ad hoc networks are envisioned with their special and unique intercommunication systems to provide safety in intelligent transportation systems and support large‐size networks. Due to dense and sparse traffic conditions, routing is always a challenging task to establish reliable and effective communication among vehicle nodes in the highly transportable environment. Several types of routing protocols have been proposed to handle high mobility and dynamic topologies including topology‐based routing, position and geocast routing, and cluster‐based routing protocols. Cluster‐based routing is one of the feasible solutions for vehicular networks due to its manageable and more viable nature. In cluster‐based protocols, the network is divided into many clusters and each cluster selects a cluster head for data dissemination. In this study, we investigate the current routing challenges and trend of cluster‐based routing protocols. In addition, we also proposed a Cluster‐based Routing for Sparse and Dense Networks to handle dynamic topologies, the high‐mobility of vehicle nodes. Simulation results show a significant performance improvement of the proposed protocol.