Neighboring Vehicles Research Articles

Multi-vehicle tracking with microscopic traffic flow model-based particle filtering

This paper addresses the problem of tracking multiple vehicles on multi-lane roads with consideration for interactions among vehicles. Due to limited lane resources and traffic heterogeneity, vehicles have to interact with neighboring vehicles while moving along roads to improve their navigability and safety, resulting in highly dependent motions. However, multitarget tracking algorithms generally assume that targets move independently of one another. To address this limitation, using the microscopic traffic flow (MTF) model for modeling vehicle dynamics in the presence of interactions with surrounding traffic, an MTF-based tracking algorithm is proposed under the particle filter (PF) framework. The recursive maximum likelihood (RML) method is integrated into the PF to estimate unknown parameters in the MTF model. The posterior Cramer–Rao lower bound (PCRLB) is also derived for this problem. The performance of the proposed MTF-PF algorithm is compared with those of existing algorithms for multi-vehicle tracking on multi-lane roads. Numerical results show that the proposed algorithm requires less prior information while yielding more accurate and consistent tracks.

The priority assignment of messages effects on delay performance in VANET

Low delay performance between neighbor vehicles in VANT need to an indepth research. In this paper, we conceived a novel priority assignment plan to reduce transmission delay. A priority was assigned to each message based on static and dynamic factors and size of the message. Dynamic scheduling sequence was carried out based on the messages priority assigned. The performance of proposed method was analysed in highway scenario on the average delay and waiting delay in queue. Simulation results are consistent with theoretical deriving. Therefore, low latency environments can be provided in Vehicular Ad-hoc Network using the novel plan.

Fuzzy-Based Hybrid Location Algorithm for Vehicle Position in VANETs via Fuzzy Kalman Filtering Approach

Location information is very critical to VANETs such as navigation, routing, network management, and road congestion. In this paper, the vehicle location problem under urban road conditions is investigated by employing the GPS, WiFi, and Cellular Network (CN) positioning systems and by developing neighbor vehicle utilization in VANETs. Since GPS is possibly affected by satellite signal in real urban environment, while WiFi is only suitable for urban and CN is affected by the number of Base Stations (BSs) and signal strength, then a fuzzy-based hybrid location algorithm is developed. The algorithm has some advantages that it can enhance these positioning features by establishing a new fuzzy-weighting location mechanism (FLM) and also can adjust dynamically the measurement noise covariance by making use of a novel fuzzy Kalman filtering method. Finally, experiment results are given to show effectiveness and merit of the proposed approach.

Optimization and non-cooperative game of anonymity updating in vehicular networks

In vehicular ad-hoc networks, a large number of vehicles in mix-zones can increase privacy but at the expense of losing communication quality. Thus, it is necessary to harmonize these two conflicting goals for privacy protection. In this study, we propose an internal optimization model and an external anonymity updating game to cross-layer joint the physical layers transmit power and MAC layers delay into a two-step non-cooperative game model, by which the communication and privacy players respectively enjoy one utility function. The first step is to establish an internal optimal model aiming to balance privacy and delay, where we can obtain the optimal transmit power. The optimal number of neighbor vehicles can be obtained by selecting the transmitting power, which can be used as the input of the second step. For the second step, we present a non-cooperative external anonymity updating game model to analyze the non-cooperative behavior of vehicles, all of which together strive to maximize the utility function at the minimum cost. We analyze the Nash equilibrium in n-player complete information game, we also derive the pure strategy Nash equilibrium. Extensive numerical calculations are conducted to comprehensively investigate the reaction of the Nash equilibrium to various combinations of parameters. The results show that the two-step non-cooperative game of anonymity updating is capable of self-adapting to the vehicular context and improving the privacy without compromising on communication quality.

Content accessibility preference approach for improving service optimality in internet of vehicles

The Internet of Vehicles (IoV) is an application of Internet of Things that provides a solution for traffic and safety management in technology-dependent cities. The most competent resource for IoV functionalities is the distributed Information System (IS). Services outsourced from the IS are not sustained over a long period of time, owing to unpredictable network dynamics and localization errors. Considering that the IS is the backbone for the IoV, this manuscript proposes a low-delay information accessing technique for improving the service optimality of vehicle-assisted smart applications. The vehicles for gaining access to information by selecting optimal gateways exploit the benefits of epidemic spread routing (ESR). The greedy behavior of ESR is confined by designing a content accessibility preference (CAP) model that facilitates precise vehicle selection. This selection relies on the information relevance, granted by the neighboring vehicles to deliver improved service optimality. The reliability of the vehicle with regard to the relevance and information retrieval time is verified by the cooperative on-demand relationship between the service requesting on-board unit and the roadside unit. Both gateway selection and neighbor vehicle selection are assimilated for providing better service via distributed information access and relevant information retrieval. The performance of the proposed CAP model is evaluated using the following metrics: throughput, access delay, vehicle service ratio, and optimality ratio. The results show the proficiency of the proposed CAP method.

CNVPS: Cooperative Neighboring Vehicle Positioning System Based on Vehicle-to-Vehicle Communication

One of the key components of the intelligent transport system is to provide a safe driving environment. The ability to quickly and accurately recognize the surrounding environments and neighboring vehicles is essential for the development of safety-related services to provide a safe driving environment. Currently, research in this field is being conducted based on the global positioning system (GPS), light detection and ranging, camera, and ranging sensors. However, the currently used sensors cannot recognize a wide range of vehicles because of their limited range of recognition. Moreover, GPS-based studies are highly affected by the surrounding environment because of the nature of GPS and have relatively high error rates and low rate of location information updates. The use of GPS-based location information for safety-related services can result in negative consequences. In this paper, we propose a new positioning system, called cooperative neighboring vehicle positioning system (CNVPS). The CNVPS rapidly identifies the locations of neighboring vehicles based on their information obtained through various sensors and shares this information with a wide range of neighboring vehicles over vehicle-to-vehicle communications. The CNVPS also compensates the position of a neighboring vehicle by applying the maximum likelihood estimation to the duplicated position observation of the other neighboring vehicles. The simulation results show that the CNVPS achieves approximately 370% improvement in location errors over GPS, assuming that the root-mean-squared error of GPS is 15 m. In addition, the proposed system has a location refresh cycle ten times faster than the existing GPS-based system.

Cooperative Localization of a Networked Multi-Vehicle System

Abstract Cooperative localization has been considered to be a suitable solution for accurate and robust localization in the field of autonomous driving. This paper considers a scenario, where a vehicle is not able to access any GNSS measurements, other than through vehicle-to-vehicle (V2V) communication. Using the V2V communication, the accurate absolute position of the neighbor vehicles can be received. Assisted with distance sensors and local inertial sensors, the local absolute position can be determined. We propose a novel estimation scheme which integrates the measurements of distance sensors, inertial sensors and neighboring vehicles’ information. A graph matching method based on the concept random sample consensus (RANSAC) is proposed to match the neighbor position with a clustered object from a LIDAR distance sensor. Sorted information is then fused into a multirate EKF to update the vehicle states, which are predicted using a strap down propagation. The proposed algorithm is evaluated in simulation and subsequent in a real-world experiment. A 2D error of less than 0.5m can be achieved in simulation as well as in the real world. The accuracy can be improved to approximately 0.2m if more neighbor vehicles are networked.

MmWave Vehicular Beam Selection With Situational Awareness Using Machine Learning

Establishing and tracking beams in millimeter-wave (mmWave) vehicular communication is a challenging task. Large antenna arrays and narrow beams introduce significant system overhead configuring the beams using exhaustive beam search. In this paper, we propose to learn the optimal beam pair index by exploiting the locations and types of the receiver vehicle and its neighboring vehicles (situational awareness), leveraging machine learning classification and past beam training data. We formulate the mmWave beam selection as a multi-class classification problem based on hand-crafted features that capture the situational awareness in different coordinates. We then provide a comprehensive comparison of the different classification models and various levels of situational awareness. Furthermore, we examine several practical issues in the implementation: localization is susceptible to inaccuracy; situational awareness at the base station (BS) can be outdated due to vehicle mobility and limited location reporting frequencies; the situational awareness may be incomplete since vehicles could be invisible to the BS if they are not connected. To demonstrate the scalability of the proposed beam selection solution in the large antenna array regime, we propose two solutions to recommend multiple beams and exploit an extra phase of beam sweeping among the recommended beams. The numerical results show that situational awareness-assisted beam selection using machine learning is able to provide beam prediction, with accuracy that increases with more complete knowledge of the environment.

Online Algorithm for Opportunistic Handling of Received Packets in Vehicular Networks

In vehicular ad-hoc networks, due to high mobility, vehicles usually communicate for short periods of time with several neighboring vehicles and are required to process data fast; sometimes in the order of few milliseconds. This urgency of data processing is further heightened in safety-critical scenarios that involve many vehicles. Such scenarios require data to be prioritized and processed with minimum delay. While packet scheduling has been extensively studied, these studies focus on channel scheduling, our work focuses on processing received packets by a vehicle in dense scenarios. In this paper, we formulate the prioritized data processing problem as an integer linear program given a prior knowledge of the request sequence and prove that it is NP-complete. Due to the difficulty of predicting the traffic patterns and obtaining the request sequence in advance, we propose an online algorithm that does not require the prior knowledge of the request sequence and achieves an O(1) competitive ratio. The proposed online algorithm strives to accept higher severity packets for processing in order to maximize the cumulative severity given vehicular communications/computation capacity constraints. Using real traffic traces, we evaluate the performance of the online algorithm against three online algorithms, in which two of them use an exponentially weighted moving average-based threshold while the other one accepts requests as capacity permits. Our evaluation shows that our algorithm achieves up to 492% more cumulative severity compared to the three other baseline algorithms.

Packet Rate Adaptation Protocol Based on Bloom Filter for Hidden Node Avoidance in Vehicular Ad-Hoc Networks

Most of the vehicular ad-hoc networks (VANETs) use the medium access control (MAC) layer of IEEE 802.11p, which is an extension of IEEE 802.11a standard. One of the critical issues with IEEE 802.11 networks is the hidden terminal problem. IEEE 802.11 networks use Request To Send (RTS) and Clear To Send (CTS) mechanism to alleviate the hidden terminal problem. The RTS/CTS mechanism, however, is inapplicable in broadcast communication. Since the safety data in VANET is transmitted over broadcast, the hidden terminal collision is still a critical problem. In this paper, we propose a hidden terminal collision mitigation protocol for broadcast communication of safety data, called Packet Rate Adaptation based on the Bloom filter (PRAB). The protocol derives the optimal packet generation rate as a function of the average number of hidden terminals. To estimate the number of hidden terminals, we introduce a notion of Bloom filter, which piggybacks the neighbor vehicles’ information at a low overhead of packet size. We implemented the proposed protocol and evaluated with various vehicular networks. The simulation results exhibit that the proposed protocol provides 90% or higher packet reception probability even for high vehicle density networks, which correspond to 15% ~24% improvement over the previous protocols considered.

Multi-Vehicle Tracking Using Microscopic Traffic Models

In this paper, the multi-vehicle tracking problem is revisited, with greater consideration being given to the interactions between vehicles. Traditionally, algorithms for tracking multiple vehicles in the multi-lane case assume that vehicles move independently of one another and that longitudinal and lateral vehicle dynamics are mutually independent. However, due to traffic volume, limited lane resources, and traffic heterogeneity, vehicles have to interact with neighboring vehicles for the purposes of maintaining a safe distance from the leading vehicle or improving their navigability by passing slower vehicles. To address the limitations in the literature, this paper proposes a novel multi-vehicle tracking algorithm that integrates the microscopic traffic models (MTM) for modeling interaction behaviors among vehicles in a 2-D road coordinate system. Due to the dependence between the longitudinal and later motions, their corresponding estimates are updated sequentially in a recursive manner. An adaptive deferred decision logic is proposed to improve the accuracy of lateral state estimates and thus improve overall performance. Simulation results show that the proposed MTM-based tracking algorithm can achieve better performance than a conventional multi-lane vehicle tracking algorithm with extension to multi-vehicle tracking, which does not consider interactions among vehicles but updates the longitudinal and lateral motion estimates independently.

Multiobjective Optimized Routing Protocol for VANETs

Vehicular ad hoc network (VANET) routing protocols have been attracting a considerable attention of both research and industrial communities, due to their significant role in intelligent transportation system applications. The present paper adopts an optimized integrated multicast, multicriteria, adaptive route lifetime as a routing protocol for VANETs. Whereby only an optimal subset of neighbor vehicles is chosen to relay route request (RREQ) messages based on distance, direction, speed, and future direction information in a combined sender-receiver manner. Among those selected optimal paths for route discovery, the best route with lowest cost will be chosen for forwarding data packets for a specified duration assigned depending on the obtained cost and number of intermediate vehicles of that route. Fuzzy controllers were employed to assess routes’ costs and their lifetimes. Furthermore, artificial bee colony (ABC) algorithm was used to concurrently optimize all used fuzzy systems and obtain the optimal highest rank of links’ cost values within which the neighbors could be selected as relay nodes in route discovery process. Simulation results prove that the proposed routing scheme significantly improves the network performance in both urban and highway scenarios, under different situations of vehicle density.

FAGA: Feedback-Aided Greedy Algorithm for Periodic Messages in LTE V2V Communications

Vehicle-to-vehicle (V2V) communication based on the device-to-device (D2D) communication in long term evolution (LTE) system is emerging as a key enabler for connected vehicles today. In this paper, we consider safety-related messages periodically transmitted by vehicle to announce its current status to other neighboring vehicles. The current state-of-the-art LTE V2V communication uses greedy algorithm for the transmission of such periodic messages. Greedy algorithm is known to have decent performance, but the performance is limited due to the lack of a collision–detection mechanism. In this paper, we propose feedback-aided greedy algorithm (FAGA) to complement the drawback of greedy algorithm. We evaluate FAGA via realistic simulations to show that it outperforms comparison schemes in terms of overall message reception ratio (MRR). As a result, it is shown that FAGA operates well even with small amount of feedback and its performance is close to the performance of centralized scheduling method. Moreover, FAGA outperforms greedy algorithm by up to 23.7% in terms of MRR performance.

A filter model for intrusion detection system in Vehicle Ad Hoc Networks: A hidden Markov methodology

Although Vehicle Ad Hoc Network (VANETs) as a new technology is being used in wide range of applications to improve the driving experience as well as safety, it is vulnerable to various type of network attacks. Literature studies have revealed several reliable approaches based on intrusion detection system (IDS), to protect VANETs against attacks. However, by those solutions, the overheads of IDSs are serious which cause too long detection time, especially when the number of vehicles increases. In this paper, we propose a novel filter model based hidden Markov model (HMM) (FM-HMM) for IDS to reduce the overhead and time for detection without impairing detection rate. To the best of our knowledge, this is the first work in the literature to model the state pattern of each vehicle in VANETs as a HMM to quickly filter the messages from the vehicles instead of detecting these messages. The FM-HMM consists of three modules, i.e., schedule, filter and update. In the schedule module, Baum–Welch algorithm is used to produce a HMM and its parameters for each neighbor vehicle. In the filter module, multiple HMMs are used with their parameters to forecast the future states of neighbor vehicles with which the messages from them are filtered. In the update module, a timeliness method is used to update HMMs and their parameters. Experiments show that the IDS with FM-HMM has a better performance in terms of detection rate, detection time and overhead.

Distributed transmission power control for communication congestion control and awareness enhancement in VANETs.

The vehicular ad hoc network (VANET) has been identified as one of the most promising technologies for managing future intelligent transportation systems. This paper proposes a distributed transmission power adjustment algorithm for communication congestion control and awareness enhancement to address communication congestion problems that can arise in VANETs. The objective of the proposed algorithm is to provide maximum awareness of surrounding vehicles’ status while maintaining a communications channel load below the allowed threshold. The proposed algorithm accomplishes this by adjusting the transmission range of each vehicle in the network progressively and gradually, while monitoring the communications channel load of each vehicle. By changing the transmission range of a vehicle little by little according to the communications channel load of its neighboring vehicles, the algorithm finds the optimal transmission range that provides maximum awareness without resulting in communications congestion. In addition, the proposed algorithm appropriately controls the channel load in a fair manner without sacrificing awareness of specific vehicles in the congested situation. This allows nearby vehicles to obtain more peripheral information to help them stay away from potential hazards and maintain safety. The proposed algorithm was implemented in a simulation environment, and its performance was validated in various traffic scenarios. The simulation results show that the proposed algorithm can deal with communication congestion by controlling the transmission power fairly to a target threshold in various traffic situations.

RA-eV2V: relaying systems for LTE-V2V communications

Emerging Long Term Evolution-based vehicle-to-vehicle (LTE-V2V) communication will support exchange of safety-related broadcast messages among vehicles. Such messages are generated periodically to announce one's own current state to other neighboring vehicles. The message reception performance in LTE-V2V drops sharply as communication distance increases if the communication channel is in a non-line-of-sight (NLOS) situation. To alleviate the problem, we propose a relaying system, called relayassisted enhanced V2V (RA-eV2V). In RA-eV2V, Road side unit (RSU) is in charge of relaying messages, received from vehicular user equipments (V-UEs). The operation of RSU is fully independent from other entities, meaning that the deployment of RSU on the road has no constraint at all. Moreover, there is no change from the current 3GPP standard operation on V-UE side either. In our realistic simulation, RA-eV2V hugely outperforms the 3GPP baseline scheme, e.g., by up to 36.5% in terms of message reception ratio in NLOS situations. Moreover, the feasibility of RA-eV2V is proven through real-map based simulation, which realistically reflects the actual situations on the roads.

On vehicular safety message transmissions through LTE-Advanced networks

Long Term Evolution Advanced (LTE-A), which provides high data rates with low latencies, can be an alternative to IEEE 802.11p for supporting vehicular applications. In this paper, we propose two solutions for the uplink transmission of safety messages: a new scheduler and a safety message generation rate adaptation. These solutions consider the speed of vehicles for resource allocation or selection of message generation rates, to provide the same level of location information accuracy on the central server for all vehicles. For downlink, we investigate the possible methods for delivering safety messages to the relevant vehicles, and propose a resource-efficient scheme based on broadcasting.We also propose a scheme that uses both LTE-D2D and LTE-cellular communication for transmission of safety messages. Vehicles transmit their safety messages with longer periods to the central server. This location information is used to determine the possible D2D pairs, as well as centralized resource allocation for the following period. Vehicles use the allocated resources for transmission of their safety messages to their neighboring vehicles using D2D communication. The simulation results show the effectiveness of our solutions in the cellular-only approach. These results also show that the proposed D2D-cellular scheme can reduce the required resources, while satisfying the requirements of safety applications.

Mobility-Adaptive Beacon Broadcast for Vehicular Cooperative Safety-Critical Applications

Beacon broadcast is an essential mechanism to improve the awareness of driving situations by broadcasting vehicle kinematics to its neighbor vehicles at a regular rate. However, the current design of beacon broadcast does not fulfill the awareness requirement of many emerging safety-critical applications. In this paper, we present the mobility-adaptive beacon broadcast (MAB <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ) scheme for guaranteed tracking of degree (GTD) K. In the GTD K, a neighbor vehicle can estimate the position of the sending vehicle within a fixed threshold, given that the former receives at least one of the K latest beacons of the latter. To aim this, we characterize the feasible kinematics of the sending vehicle in the subsequent time, address how the MAB <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> scheme defers a new beacon broadcast as long as the tracking condition meets, and present several rigorous proofs on the correctness and optimality of the MAB <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> scheme. Numerical results show that the MAB <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> scheme achieves an outstanding GTD-K tracking performance, in terms of the timeliness of beacon broadcast, the reliability of vehicle tracking, and the tracking accuracy, while minimizing the DSRC CCH congestion.

Formation control of multirotor aerial vehicles using decentralized MPC

In this work, the authors propose a formation control strategy of a group of three multirotor aerial vehicles being able to avoid multiple obstacles and collisions. To deal with this problem, a decentralized architecture is proposed which has one model predictive controller per vehicle including a set of convex constraints on the vehicle’s position to prevent collisions with other agents and different shapes of obstacles. The resulting decentralized scheme controls the formation based on a virtual structure approach. For the purpose of avoiding collisions, each local controller considers the predicted position of every neighbor vehicles. The effectiveness of the developed scheme is demonstrated through numerical simulations considering a “figure-of-eight” as the reference trajectory, and the results show its capability to handle thrust force, obstacle and collision avoidance constraints.

Reinforcement Learning Based Mobility Adaptive Routing for Vehicular Ad-Hoc Networks

Vehicular ad-hoc networks (VANETs) is drawing more and more attentions in intelligent transportation system to reduce road accidents and assist safe driving. However, due to the high mobility and uneven distribution of vehicles in VANETs, multi-hops communication between the vehicles is still particularly challenging. Considering the distinctive characteristics of VANETs, in this paper, an adaptive routing protocol based on reinforcement learning (ARPRL) is proposed. Through distributed Q-Learning algorithm, ARPRL constantly learns and obtains the fresh network link status proactively with the periodic HELLO packets in the form of Q table update. Therefore, ARPRL's dynamic adaptability to network changes is improved. Novel Q value update functions which take into account the vehicle mobility related information are designed to reinforce the Q values of wireless links by exchange of HELLO packets between neighbor vehicles. In order to avoid the routing loops caused in Q learning process, the HELLO packet structure is redesigned. In addition, reactive routing probe strategy is applied in the process of learning to speed up the convergence of Q learning. Finally, the feedback from the MAC layer is used to further improve the adaptation of Q learning to the VANETs environment. Through simulation experiment result, we show that ARPRL performs better than existing protocols in the form of average packet delivery ratio, end-to-end delay and number hops of route path while network overhead remains within acceptable ranges.