Vehicle Platoon Research Articles

A Reinforcement Learning-Based Vehicle Platoon Control Strategy for Reducing Energy Consumption in Traffic Oscillations.

The vehicle platoon will be the most dominant driving mode on future roads. To the best of our knowledge, few reinforcement learning (RL) algorithms have been applied in vehicle platoon control, which has large-scale action and state spaces. Some RL-based methods were applied to solve single-agent problems. If we need to tackle multiagent problems, we will use multiagent RL algorithms since the parameters space grows exponentially with the increasing number of agents involved. Previous multiagent RL algorithms generally may provide redundant information to agents, indicating a large amount of useless or unrelated information, which may cause to be difficult for convergence training and pattern extractions from shared information. Also, random actions usually contribute to crashes, especially at the beginning of training. In this study, a communication proximal policy optimization (CommPPO) algorithm was proposed to tackle the above issues. In specific, the CommPPO model adopts a parameter-sharing structure to allow the dynamic variation of agent numbers, which can well handle various platoon dynamics, including splitting and merging. The communication protocol of the CommPPO consists of two parts. In the state part, the widely used predecessor-leader follower typology in the platoon is adopted to transmit global and local state information to agents. In the reward part, a new reward communication channel is proposed to solve the spurious reward and "lazy agent" problems in some existing multiagent RLs. Moreover, a curriculum learning approach is adopted to reduce crashes and speed up training. To validate the proposed strategy for platoon control, two existing multiagent RLs and a traditional platoon control strategy were applied in the same scenarios for comparison. Results showed that the CommPPO algorithm gained more rewards and achieved the largest fuel consumption reduction (11.6%).

Communication Topology Assignment and Control Co-design for Vehicle Platoons in LTE-V2V Network

In this study, we investigate the problem of inter-vehicle communication topology (IVCT) assignment and control for vehicular platoons in LTE-V2V networks based on the cooperative awareness message dissemination mechanism. A sampled-data feedback controller is proposed for platoons to eliminate the effect of stochastic packet dropouts and external disturbance, where the controller gain depends on the IVCT. To guarantee the stability requirement of a platoon with the minimized cost function, a unified control framework is established to jointly determine the optimal IVCT from all the available ones and the associated feedback controller gain. This co-design procedure is based on the optimal control and dynamic programming technique, where both fixed and periodic switching IVCTs are available. A useful algorithm is proposed to implement the established co-design framework. Furthermore, we present numerical examples to demonstrate the effectiveness of the proposed method.

Cooperative Startup Control for Heterogeneous Vehicle Platoons: A Finite-Time Output Tracking-Based Approach

The connected vehicle (CV) technology has emerged in recent years. This article studies cooperative startup control of heterogeneous CVs in a platoon. First, from the perspective of cooperative tracking of heterogeneous multiagent systems, a hierarchical finite-time control framework is established, which consists of an upper-level interactive observer layer and a lower-level local controller layer. By separating neighboring information interaction from local dynamics control, the proposed framework allows to design upper-level observers and lower-level local controllers separately. Second, by introducing a potential function related to the consensus and observing errors, a distributed finite-time observer is designed for each CV to observe a startup reference trajectory available for only part of the CVs. Third, a distributed local finite-time controller is designed for each CV to track its observed startup reference trajectories. Within the proposed framework, finite-time observing and tracking of the startup reference trajectory are strictly proved to guarantee cooperative startup control. Numerical simulations are carried out to demonstrate the effectiveness of the proposed methods.

A Hybrid Deep Reinforcement Learning For Autonomous Vehicles Smart-Platooning

The development of Autonomous Vehicles (AVs) envisions the promising technology of future Intelligent Transportation Systems (ITS). However, the complex road structures and increased vehicles cause traffic congestion and road safety, which eventually leads to horrible accidents. Cooperative driving of AVs, a groundbreaking initiative of vehicle platooning, epitomizes the next wave in vehicular technology through minimizing accident risks, transport times, costs, energy, and fuel consumption. However, the traditional machine learning-based platooning approaches fail to regulate the policy with the dynamic feature of AVs. This paper proposes a hybrid Deep Reinforcement learning and Genetic algorithm for Smart-Platooning (DRG-SP) the AVs. The leverage of the deep reinforcement learning mechanism addresses the computational complexity and accommodates the high dynamic platoon environments. Adopting the Genetic Algorithm in Deep Reinforcement learning overcomes the slow convergence problem and offers long-term performance. The simulation results reveal that the Smart-Platooning effectively forms and maintains the platoons by minimizing traffic congestion and fuel consumption.

Safety impact of cooperative adaptive cruise control vehicles’ degradation under spatial continuous communication interruption

Cooperative adaptive cruise control is recognised as an effective means to reduce the rear-end collision caused by the delayed reaction and improper driving behaviours of manually driven vehicles. However, vehicle-to-vehicle communication, as the key to collect information for the cooperative adaptive cruise control system, is likely to be interrupted by malicious attacks and equipment failures. When communication interruption occurs, sensors of the adaptive cruise control system will replace vehicle-to-vehicle communication for information collection, that is, cooperative adaptive cruise control vehicles degrade to adaptive cruise control vehicles automatically, causing an increased rear-end collision risk. This study aims to investigate the safety impact of cooperative adaptive cruise control vehicles’ degradation under spatial continuous communication interruption. A mixed platoon, consisting of cooperative adaptive cruise control vehicles, adaptive cruise control vehicles, manually driven vehicles, and improved manually driven vehicles with information-sending devices, is simulated with the realistic cooperative adaptive cruise control and adaptive cruise control model, and the intelligent driver model. Different platoon forms are discussed by adjusting the quantity and position of manually driven vehicles in the mixed platoon. The results show that manually driven vehicles can effectively block the backward extension of speed fluctuation and reduce the rear-end collision risk under the spatial continuous communication interruption. Nevertheless, equipping manually driven vehicles with information-sending devices weakens the ability to defend against communication interruption.

Modelling multi-lane heterogeneous traffic flow with human-driven, automated, and communicating automated vehicles

A new set of lane changing rules is introduced with that the model introduced in Vranken et al. (2021) is able to simulate multi lane heterogeneous traffic where human driven vehicles mix with automated or communicating automated vehicles. The model predicts that (communicating) automated vehicles will increase road capacity and traffic flow in all traffic situations more strongly than on one lane traffic even though they behave more passive while lane changing and following human driven vehicles. The main reason for this improvement was found to be the creation of automated vehicle platoons naturally organised by the system.

Optimal control of interconnected systems with time-correlated noises: Application to vehicle platoon

This paper studies the optimal state-feedback LQG control (OSLC) of interconnected systems (ISs) with time-correlated process noises. In an IS, the information is transmitted among subsystems via the network, and the transmission time is proportional to the distance of the corresponding subsystem pairs. This means that the information received by a subsystem includes the non-real-time information, and that the information from different subsystems may be of different time indexes. This makes the optimal controller design challenging. The OSLC of ISs with time-uncorrelated process noises is studied by an independence decomposition method in the existing literature. However, the existing independence decomposition method strongly relies on the condition that the process noises are time-uncorrelated, and fails for the time-correlated process noises case. In this paper, the globally optimal LQG controller of ISs with time-correlated process noises is successfully designed. In particular, a new cost function decomposition is obtained based on the Bellman equation. Both the system state and the control input are decomposed into two independent parts by the orthogonal decomposition technique. The proposed decomposition method leads to the successful design of the globally optimal controller. The proposed theoretical results are applied to a vehicle platoon system. The simulation shows that the platoon maintains a desired state and achieves a good performance under the proposed controller.

Ecological control strategy for cooperative autonomous vehicle in mixed traffic considering linear stability

Purpose This paper aims to present a cooperative adaptive cruise control, called stable smart driving model (SSDM), for connected and autonomous vehicles (CAVs) in mixed traffic streams with human-driven vehicles. Design/methodology/approach Considering the linear stability, SSDM is able to provide smooth deceleration and acceleration in the vehicle platoons with or without cut-in. Besides, the calibrated Virginia tech microscopic energy and emission model is applied in this study to investigate the impact of CAVs on the fuel consumption of the vehicle platoon and traffic flows. Under the cut-in condition, the SSDM outperforms ecological SDM and SDM in terms of stability considering different desired time headways. Moreover, single-lane vehicle dynamics are simulated for human-driven vehicles and CAVs. Findings The result shows that CAVs can reduce platoon-level fuel consumption. SSDM can save the platoon-level fuel consumption up to 15%, outperforming other existing control strategies. Considering the single-lane highway with merging, the higher market penetration of SSDM-equipped CAVs leads to less fuel consumption. Originality/value The proposed rule-based control method considered linear stability to generate smoother deceleration and acceleration curves. The research results can help to develop environmental-friendly control strategies and lay the foundation for the new methods.

The Effect of Afterbody Geometry on Passenger Vehicles in Platoon

It is well known that platoons of closely spaced passenger cars can reduce their aerodynamic drag yielding substantial savings in energy consumption and reduced emissions as a system. Most published research has focused on platoons of identical vehicles which can arguably be justified by some evidence that geometric variety has little to no effect on the overall flow characteristics in platoons of three vehicles or more. It is known that much of the aerodynamic benefit from platooning is gained by the leading two cars, so operating as vehicle pairs could potentially achieve similar environmental benefits whilst addressing many of the practical challenges associated with the safe operation of long platoons on public roads. However, it has been reported that unlike long platoons, the effect of geometry and arrangement is critical if the drag reduction of a pair is to be optimised. This paper describes a parametric study based on three geometric variants of the popular DrivAer model with different combinations and spacings. It is confirmed that vehicle geometry crucially affects the results with the best combinations matching those of long platoons and others creating a net drag increase.

Development of a Numerical Investigation Framework for Ground Vehicle Platooning

This paper presents a study on the flow dynamics involving vehicle interactions. In order to do so, this study first explores aerodynamic prediction capabilities of popular turbulence models used in computational fluid dynamics simulations involving tandem objects and thus, ultimately presents a framework for CFD simulations of ground vehicle platooning using a realistic vehicle model, DrivAer. Considering the availability of experimental data, the simulation methodology is first developed using a tandem arrangement of surface-mounted cubes which requires an understanding on the role of turbulence models and the impacts of the associated turbulence model closure coefficients on the prediction veracity. It was observed that the prediction accuracy of the SST k−ω turbulence model can be significantly improved through the use of a combination of modified values for the closure coefficients. Additionally, the initial validation studies reveal the inability of the Unsteady Reynolds-Averaged Navier-Stokes (URANS) approach to resolve the far wake, and its frailty in simulating tandem body interactions. The Improved Delayed Detached Eddy Simulations (IDDES) approach can resolve the wakes with a reasonable accuracy. The validated simulation methodology is then applied to the fastback DrivAer model at different longitudinal spacing. The results show that, as the longitudinal spacing is reduced, the trailing car’s drag is increased while the leading car’s drag is decreased which supports prior explanations of vortex impingement as the reason for drag changes. Additionally, unlike the case of platooning involving Ahmed bodies, the trailing model drag does not return to an isolated state value at a two car-length separation. However, the impact of the resolution of the far wake of a detailed DrivAer model, and its implication on the CFD characterization of vehicle interaction aerodynamics need further investigations.

Delay margin comparison in a velocity-only versus headway-only connected vehicle model

Two different connected vehicle models are considered: one based on only using velocity measurements and the other using only headway, where each model is affected by delays due to human reaction times and sensing and communication lines. The presence of delays is established between any two vehicles that are neighbors as determined by the underlying network topology. The main focus here is to put light into our understanding of how much of time delay can the equilibrium of these models tolerate before becoming unstable. To this end, we compute, using the parallel processing computational tool Delay Margin Finder (parDMF), the delay margin of the equilibrium dynamics and discuss design trade-offs. We report that delay margin in the headway-only model is much less sensitive against the presence/absence of links in the network and that this model can have larger delay margin when larger number of vehicles are capable of communicating with other vehicles in the platoon.

Bidirectional asymmetric delay feedback for cooperative adaptive cruise control of vehicle platoons with unreliable communication

AbstractThis paper considers the cooperative adaptive cruise control (CACC) problem of vehicle platoons under unreliable vehicle‐to‐everything (V2X) communication network. A bidirectional asymmetric delay feedback CACC method is presented to cope with the time delay and packet dropout induced by the unreliable network. The concept of equivalent delays is used to compensate the packet dropout of the network with the bidirectional communication topology. Using the asymmetric PD structure and the longitudinal models with varying time delay, the CACC controller of the platoon in a centralized mode is computed by solving linear matrix inequalities. To guarantee string stability of the platoon with the controller under the unreliable network, some sufficient conditions on the parameters of the controller and the time delay and packet dropout are derived. Furthermore, the upper bound of the time delay is estimated to satisfy string stability of the platoon. Finally, the presented method is verified by some comparative experiments of a seven‐car platoon with representative traffic scenarios and communication topologies.

Decentralized Platoon Join-in-Middle Protocol Considering Communication Delay for Connected and Automated Vehicle.

Cooperative driving is an essential component of intelligent transport systems (ITSs). It promises greater safety, reduced accidents, efficient traffic flow, and fuel consumption reduction. Vehicle platooning is a representative service model for ITS. The principal sub-systems of platooning systems for connected and automated vehicles (CAVs) are cooperative adaptive cruise control (CACC) systems and platoon management systems. Based on vehicle state information received through vehicle-to-vehicle (V2V) communication, the CACC system allows platoon vehicles to maintain a narrower safety distance. In addition, the platoon management system using V2V communications allows vehicles to perform platoon maneuvers reliably and accurately. In this paper, we propose a CACC system with a variable time headway and a decentralized platoon join-in-middle maneuver protocol with a trajectory planning system considering the V2V communication delay for CAVs. The platoon join-in-middle maneuver is a challenging research subject as the research must consider the requirement of a more precise management protocol and lateral control for platoon safety and string stability. These CACC systems and protocols are implemented on a simulator for a connected and automated vehicle system, PreScan, and we validated our approach using a realistic control system and V2V communication system provided by PreScan.

Communication energy optimization of electric vehicle platoon on curved road

The cruising range of an electric vehicle is limited by its battery. Reducing the energy consumption of MES (main energy systems) or AES (auxiliary energy systems) of the vehicle battery is an effective means to increase the electric vehicle cruising range. Platoon driving can greatly reduce the wind resistance of the vehicle and then reduce the energy consumption of MES for electric vehicles. This paper proposes an adaptive communication energy optimization scheme based on road curvature radius to save the energy of AES for the electric vehicle platoon on curved roads. In this paper, the inter-vehicle distance error based on the car-like model in a two-dimensional space is established. Then, the inter-vehicle distance error is used to design a control law K to accomplish successful platooning. Next, three platooning control schemes based on different information flow topologies are discussed. Finally, the consensus of three platooning control schemes and the energy consumption of electric vehicle communication systems are analyzed by MATLAB’s Simulink. Simulation results show that the communication energy optimization scheme reduces the power consumption of AES as long as the platoon driving on curved roads.

A Learning Control Method of Automated Vehicle Platoon at Straight Path with DDPG-Based PID

Cooperative adaptive cruise control (CACC) has important significance for the development of the connected and automated vehicle (CAV) industry. The traditional proportional integral derivative (PID) platoon controller adjustment is not only time-consuming and laborious, but also unable to adapt to different working conditions. This paper proposes a learning control method for a vehicle platooning system using a deep deterministic policy gradient (DDPG)-based PID. The main contribution of this study is automating the PID weight tuning process by formulating this objective as a deep reinforcement learning (DRL) problem. The longitudinal control of the vehicle platooning is divided into upper and lower control structures. The upper-level controller based on the DDPG algorithm can adjust the current PID controller parameters. Through offline training and learning in a SUMO simulation software environment, the PID controller can adapt to different road and vehicular platooning acceleration and deceleration conditions. The lower-level controller controls the gas/brake pedal to accurately track the desired acceleration and speed. Based on the hardware-in-the-loop (HIL) simulation platform, the results show that in terms of the maximum speed error, for the DDPG-based PID controller this is 0.02–0.08 m/s less than for the conventional PID controller, with a maximum reduction of 5.48%. In addition, the maximum distance error of the DDPG-based PID controller is 0.77 m, which is 14.44% less than that of the conventional PID controller.

Ad-hoc platoon formation and dissolution strategies for multi-lane highways

Vehicle platooning, a coordinated and controlled vehicle-following strategy, addresses the issue of high fuel consumption of heavy-duty vehicles. This research considers platoons that are formed on the fly in an ad-hoc manner. We investigate two types of ad-hoc platoon formation and corresponding platoon dissolution strategies. The first approach forms a platoon greedily without considering the order of destinations of the platoon members. This approach enables a quick formation but imposes an overhead of platoon rebuilding, and consequently, additional fuel cost when platoon members leave. An alternative approach forms a platoon in the order of the destinations of its platoon members. This ordered approach incurs a comparatively higher formation time due to vehicles’ reorganization but does not lead to further overhead of platoon rebuilding. We investigate whether these ad-hoc formation and dissolution strategies can preserve the original fuel benefit of platooning, and which of the two ad-hoc formation strategies are more fuel-efficient. The experimental results show that the greedy formation of the platoon is more fuel-efficient for a multi-lane highway. The proposed prediction model provides 90.4% prediction accuracy for the greedy approach and 82.2% prediction accuracy for the ordered approach on average, for platoon sizes from two to six vehicles.

A non-linear disturbance observer-based cooperative adaptive cruise control for real traffic scenarios

Cooperative adaptive cruise control (CACC) has a strong potential to improvise highway traffic capacity and ease traffic disturbances. Extensive exploration is not carried out in the area of CACC for a cut-in maneuver. Contemporary control strategies proposed for CACC cannot regulate the peaking of control input and thus the acceleration/deceleration of following vehicles when applied for various real traffic scenarios. This paper aims to develop a non-linear disturbance observer-based sliding mode control to control a CACC system for various traffic scenarios. The proposed observer estimates the uncertainty present in the actuator dynamics and the preceding vehicle’s acceleration as the lumped disturbance at the same time, it adjusts the observer gain to alleviate the peaking of control input. The stability of individual vehicles and the string stability of vehicle platoon are derived The performance of the proposed scheme is validated with various traffic scenarios, that is, cut-in maneuver, cut-out maneuver, and non-zero initial conditions. The effectiveness of the proposed scheme is demonstrated by comparing it with a linear disturbance observer-based control.

Adaptive distributed finite‐time fault‐tolerant controller for cooperative braking of the vehicle platoon

Vehicle platooning can significantly reduce traffic accidents and enhance transportation safety. Among many subsystems and functionalities equipped in a vehicle platoon, cooperative braking is a safety-critical one. Besides, as actuator faults would deteriorate vehicle safety and stability, they pose a great challenge to the platoon, particularly during cooperative braking. To address the aforementioned problems, this study designed an adaptive distributed finite-time fault-tolerant controller for vehicle platoons under cooperative braking condition. First, based on the graph theory and vehicle longitudinal dynamics, the cooperative braking model of a platoon is constructed. Then, the models of hydraulic braking system and regenerative braking system are developed with malfunction analysis. Based on the vehicle's fault model and the representation of the platoon consensus errors, an adaptive finite-time sliding-mode fault tolerant controller is proposed to maintain consensus between vehicle's states during fault occurring. Further, a distributed adaptive law is presented considering the parameter estimation error and sliding-mode surface. The finite-time convergence property and the stability of the proposed controller are demonstrated. Numerical simulations are conducted under different conditions. The simulation results reflected by the control performance and actuators' responses validate the feasibility and effectiveness of the designed control method.

Distributed control under compromised measurements: Resilient estimation, attack detection, and vehicle platooning

We study how to design a secure observer-based distributed controller such that a group of vehicles can achieve accurate state estimates and formation control even if the measurements of a subset of vehicle sensors are compromised by a malicious attacker. We propose an architecture consisting of a resilient observer, an attack detector, and an observer-based distributed controller. The distributed detector is able to update three sets of vehicle sensors: the ones surely under attack, surely attack-free, and suspected to be under attack. The adaptive observer saturates the measurement innovation through a preset static or time-varying threshold, such that the potentially compromised measurements have limited influence on the estimation. Essential properties of the proposed architecture include: (1) The detector is fault-free, and the attacked and attack-free vehicle sensors can be identified in finite time; (2) The observer guarantees both real-time error bounds and asymptotic error bounds, with tighter bounds when more attacked or attack-free vehicle sensors are identified by the detector; (3) The distributed controller ensures closed-loop stability. The effectiveness of the proposed methods is evaluated through simulations by an application to vehicle platooning.

Decentralized arterial traffic signal optimization with connected vehicle information

This paper proposes a decentralized signal control algorithm that leverages connected vehicle information to improve traffic operations along arterials. The proposed algorithm obtains real-time vehicle locations and speeds, as well as information on pedestrians waiting to cross individual intersections, to optimize signal phasing and timing plans. Signal timing is optimized at individual intersections; however, information about vehicle platoons passing a given intersection is shared with neighboring intersections to facilitate natural coordination between adjacent intersections. The decentralized algorithm is compared to a centralized algorithm that optimizes signal timing at all intersections simultaneously, as well as a traditional coordination strategy. The proposed algorithm is shown both to be more computationally efficient than the centralized approach and provide better operational performance (in terms of person, vehicle and pedestrian delay) than both the centralized algorithm and the traditional strategy. The algorithm is robust to a range of demand patterns and can be applied under scenarios in which not all vehicles are connected or full information about pedestrian arrivals is not available.