Car-following Control Research Articles

Longitudinal car-following control strategy integrating predictive collision risk

Many controllers have been designed for the longitudinal car-following mode of connected and automated vehicles. The existing body of research shows that these controllers more or less have some deficiencies in controlling connected and automated vehicles, which directly hinder their development. To cope with these problems, we design a novel longitudinal car-following control strategy integrating predictive collision risk. Among the controllers for connected and automated vehicles, the intelligent driver model is one of the most widely adopted controller. There is evidence that the intelligent driver model controller will produce larger gap distance and slower response time. In the meantime, the string stability of CAVs platoon controlled by the intelligent driver model controller is poor. Therefore, to verify the effectiveness of this control strategy, we integrate proposed control strategy with intelligent driver model, and the predictive-intelligent drive model controller is formulated. Theoretical analysis is exerted by transfer function method, and some numerical simulation experiments are designed and carried out. Analytical results show that the proposed control strategy can improve the defects of intelligent driver model controller in poor string stability, larger gap distance and slower response. In the meantime, it can also moderate the stopping process of connected and automated vehicles and enhance the throughput of intersection. More importantly, it does not affect the structure of connected and automated vehicles, which suggests that it is possible to integrate it with other controllers to improve their performance in controlling connected and automated vehicles. All findings in this study provide a novel way to establish car-following control strategy improving traffic stability and efficiency and a set of theoretical frameworks for verifying the control effect of future proposed control strategy.

Physics-informed deep reinforcement learning-based integrated two-dimensional car-following control strategy for connected automated vehicles

Connected automated vehicles (CAVs) are broadly recognized as next-generation transformative transportation technologies having great potential to improve traffic safety, efficiency, and stability. Efficiently controlling CAVs on two-dimensional curvilinear roadways to follow preceding vehicles is denoted as the two-dimensional car-following process, which is highly critical; this process is challenging to implement owing to the complexity and varied nature of driving environments. This study proposes an innovative integrated two-dimensional control strategy for CAVs based on deep reinforcement learning (DRL), which efficiently regulates the two-dimensional car-following process of CAVs in terms of both stability-wise longitudinal control performance and accurate lateral path-tracking performance. Within the control framework, each CAV can receive the surrounding information from downstream vehicles and roadway geometry based on vehicle-to-everything (V2X) communication. To better utilize this information, we designed a physics-informed DRL state fusion approach and reward function, which efficiently embeds prior physics knowledge and borrows the merits of the equilibrium and consensus concepts from the control theory. Given the physics-informed information, the DRL-based controller outputs the integrated control instructions for both longitudinal and lateral control. For training, we constructed a roadway with a set of varying curvatures and embedded the ground-truth vehicle trajectory datasets to more effectively capture the realistic variations in the roadway geometry and driving environment. To facilitate value function approximation and enhance the policy iteration process in training, the distributed proximal policy optimization (DPPO) algorithm was applied, owing to its balanced performance. A series of simulated experiments were conducted to validate the controller’s lateral control accuracy and stability-wise oscillation dampening performance in diverse traffic scenarios, including extreme ones.

Autonomous Platoon Control With Integrated Deep Reinforcement Learning and Dynamic Programming

Deep Reinforcement Learning (DRL) is regarded as a potential method for car-following control and has been mostly studied to support a single following vehicle. However, it is more challenging to learn a stable and efficient car-following policy when there are multiple following vehicles in a platoon, especially with unpredictable leading vehicle behavior. In this context, we adopt an integrated DRL and Dynamic Programming (DP) approach to learn autonomous platoon control policies, which embeds the Deep Deterministic Policy Gradient (DDPG) algorithm into a finite-horizon value iteration framework. Although the DP framework can improve the stability and performance of DDPG, it has the limitations of lower sampling and training efficiency. In this paper, we propose an algorithm, namely Finite-Horizon-DDPG with Sweeping through reduced state space using Stationary approximation (FH-DDPG-SS), which uses three key ideas to overcome the above limitations, i.e., transferring network weights backward in time, stationary policy approximation for earlier time steps, and sweeping through reduced state space. In order to verify the effectiveness of FH-DDPG-SS, simulation using real driving data is performed, where the performance of FH-DDPG-SS is compared with those of the benchmark algorithms. Finally, platoon safety and string stability for FH-DDPG-SS are demonstrated.

Energy-Saving Optimization for Electric Vehicles in Car-Following Scenarios Based on Model Predictive Control

In this paper, an economy-oriented car-following control (EOCFC) strategy is proposed for electric vehicles in car-following scenarios. Specifically, a controller based on model predictive control (MPC) is developed to optimize the host vehicle’s speed for better energy economy while ensuring good car-following performance and ride comfort. The vehicle’s energy consumption is accurately quantified in the form of demand power, which is incorporated in the cost function for energy optimization. The proposed EOCFC strategy is evaluated using three standard test cycles, i.e., New European Driving Cycle (NEDC), Urban Dynamometer Driving Schedule (UDDS) and Worldwide Harmonized Light Vehicles Test Cycle (WLTC), in comparison with a typical multi-objective adaptive cruise control strategy. The evaluation results demonstrate that the proposed EOCFC improves the energy economy of the host vehicle by 0.53%, 3.33% and 1.51%, under the NEDC, UDDS and WLTC test cycles respectively.

A deep reinforcement learning based distributed control strategy for connected automated vehicles in mixed traffic platoon

This paper proposes an innovative distributed longitudinal control strategy for connected automated vehicles (CAVs) in the mixed traffic environment of CAV and human-driven vehicles (HDVs), incorporating high-dimensional platoon information. For mixed traffic, the traditional CAV control method focuses on microscopic trajectory information, which may not be efficient in handling the HDV stochasticity (e.g., long reaction time; various driving styles) and mixed traffic heterogeneities. Different from traditional methods, our method, for the first time, characterizes consecutive HDVs as a whole (i.e., AHDV) to reduce the HDV stochasticity and utilize its macroscopic features to control the following CAVs. The new control strategy takes advantage of platoon information to anticipate the disturbances and traffic features induced downstream under mixed traffic scenarios and greatly outperforms the traditional methods. In particular, the control algorithm is based on deep reinforcement learning (DRL) to fulfill car-following control efficiency and further address the stochasticity for the aggregated car following behavior by embedding it in the training environment. To better utilize the macroscopic traffic features, a general platoon of mixed traffic is categorized as a CAV-HDVs-CAV pattern and described by corresponding DRL states. The macroscopic traffic flow properties are built upon the Newell car-following model to capture the characteristics of aggregated HDVs' joint behaviors. Simulated experiments are conducted to validate our proposed strategy. The results demonstrate that the proposed control method has outstanding performances in terms of oscillation dampening, eco-driving, and generalization capability.

Cloud-based Connected Vehicle Control under Time-Varying Delay: Stability Analysis and Controller Synthesis

The emergence of connected vehicles and cloud-based control technologies promise great benefits to transportation systems. For practical application, time-varying delay from vehicular communication and edge/cloud computing has a critical influence on the vehicle control performance. To address this problem, this paper focuses on the stability analysis and controller design for connected vehicles under time-varying delay at the cloud-based control architecture. Particularly, connected car-following control and connected path-following control are under consideration as specific examples, where the cloud-unit assigns the control commands. A general switched system model has been established for connected vehicle control, where time-varying delay is imposed on partial system states. For stability analysis, an improved stability condition is proposed for the switched system under general case of time-varying delay with less conservative property compared with existing work. Further, based on Markov process assumption on time-varying delay, a quantitative stability evaluation method is introduced. Then, an <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathcal {H}_\infty$</tex-math></inline-formula> controller design method has been presented, which incorporates multiple requirements, including stability under delay, control error for safety, and control rapidity. Extensive numerical simulations validate the performance of the proposed control method at multiple traffic scenarios.

Research on mixed traffic flow model based on multi-node bilateral control model and chain stability analysis

With the development of wireless communication technology, vehicles can obtain more vehicle status information on the same road. From the control point of view, when the vehicle control needs to use the state information of a plurality of surrounding vehicles, it becomes an important problem to determine the weighting coefficients of the information of these different vehicles. Moreover, different vehicle status information should have different weight coefficients. In this paper, Gaussian curve is introduced as the objective function and the shape of curve is adjusted by parameters to determine the weight coefficients of vehicle nodes more flexibly. On this basis, considering the characteristics of multi-node bilateral control, bilateral control, and car-following control, a scalable hybrid control block model (CBMBC) is proposed. And the necessary condition of chain stability of the proposed bilateral hybrid control block scheme is given. Finally, the effectiveness of the proposed scheme is verified by simulation.

Multiobjective adaptive car-following control of an intelligent vehicle based on receding horizon optimization

Multiobjective adaptive car-following control of an intelligent vehicle based on receding horizon optimization

Two-Dimensional Car-Following Control Strategy for Electric Vehicle Based on MPC and DQN

For the coupling problem of longitudinal control and lateral control of vehicles, a two-dimensional (2-D) car-following control strategy for an electric vehicle is proposed in this paper. First, a 2-D car-following model for longitudinal following and lateral lane keeping is established. Then, a 2-D car-following control strategy is designed, and the longitudinal following control and lateral lane keeping control are integrated into one model predictive control (MPC) framework. The 2-D car-following strategy can realize the multi-objective coordinated optimization for longitudinal control and lateral control during the 2-D car-following process, and the multiple objectives are: safety, tracking, comfort, lane keeping, lateral stability and economy. In addition, the economy is important for electric vehicles. The weight matrix of the objective function in the MPC framework is symmetric, and the weight coefficients for the weight matrix have a great influence on the control. The contribution of this paper is: in order to adapt to different dynamic processes of lane keeping, the weight coefficients in the MPC framework are optimized in real-time based on the deep Q network (DQN) algorithm. Finally, to verify the 2-D car-following control strategy, a comparison strategy and two experimental scenarios are set, and simulation experiments are carried out. In scenario 1, compared with the comparison strategy, the lane keeping, lateral stability and economy of the proposed strategy are improved by 37.21%, 17.57% and 9.26%, respectively. In scenario 2, compared with the comparison strategy, the lane keeping, lateral stability and economy of the proposed strategy are improved by 36.45%, 16.66% and 18.52%, respectively. Therefore, compared with the comparison strategy, the 2-D car-following control strategy can have better lane keeping, lateral stability and economy on the premise of ensuring other performances during the 2-D car-following process.

Energy-oriented car-following control for a front- and rear-independent-drive electric vehicle platoon

In this paper, a cooperative multi-objective platoon control (CMOPC) strategy is proposed for a front- and rear-independent-drive electric vehicle (FRIDEV) platoon. Two major measures are taken in this approach to enhance platoon economy. Firstly, a novel multi-objective nonlinear model predictive control (NMPC) system is devised by combining car-following control for connected and automated vehicle platoons and torque distribution control for FRIDEVs to exploit the energy-saving potential of an FRIDEV platoon. Secondly, the total power of all vehicles in the platoon is considered in the cost function to better reflect the overall energy consumption of the platoon. The proposed CMOPC strategy is evaluated under three typical driving cycles, i.e. UDDS, WLTC and HWFET; the ecological cooperative adaptive cruise control strategy is employed as the benchmark of evaluation. The comparative simulation results demonstrate that the proposed CMOPC not only ensures equivalent car-following performance, but also improves the platoon economy by 3.0%, 1.6% and 4.7% respectively under UDDS, WLTC and HWFET driving cycles.

Visual Detection and Deep Reinforcement Learning-Based Car Following and Energy Management for Hybrid Electric Vehicles

Practical vision-based technology is essential for the autonomous driving of intelligent hybrid electric vehicles. In this article, a hierarchical control structure is proposed, which combines you only look once-based object detection and learning-based intelligent control by deep reinforcement learning. After modeling a typical car-following scene, the leading car is detected in the driving image, and the real-time distance between two cars is evaluated by vision-based distance measurement. Then, a deep Q-network is adopted to learn the car-following control strategy and energy management strategy, which achieves multiobjective control of the hybrid powertrain while maintaining a reasonable distance for the following car. When completing off-line training, the online processor-in-the-loop test by the edge computing device NVIDIA Jetson AGX Xavier is performed. Results show that the hierarchical control strategy gets a fuel economy of 5.76 L/100 km while keeping a safe following distance. Moreover, the time consumed to run a driving cycle of 1797 s in the embedded device is 476.87 s, which means that a control loop, including target recognition, distance measurement, car-following control, and energy management, takes 0.26 s. This study proves that vehicle vision can lay the technical foundation for intelligent driving, and the results illustrate that the hierarchical control structure is capable of achieving considerable computing efficiency on embedded devices and has the potential for real vehicle control.

Cooperative car-following control with electronic throttle and perceived headway errors on gyroidal roads

Gyroidal roads are not uncommon on mountainous freeways. In the provision of complex road information such as visual field and slope, some errors between the perceived headway and the real headway information may exist subject to the accuracy of sensors. With the penetration of automated and autonomous vehicles, there is an increasing need for developing a systematic controlling approach to ensure efficient and safe vehicular motion on gyroidal roads. This study contributes to devising a vehicle-to-vehicle communication-based feedback control method with such considerations. A modified car-following model considering perceived headway errors on gyroidal roads is presented. The neutral stability curves of the new model are derived according to the classical control method, which verifies the significant impact of the error coefficient, slope information, and perception time on the robustness of the model, and that the effect of the error coefficient and slope information is positive while that of the perception time is negative. Given the importance of electronic throttle angle information for vehicle-to-vehicle communication technology, a cooperative control signal is designed for the scenario when the above stability condition is unsatisfied. The numerical simulation example verifies the effectiveness of the controller in alleviating traffic congestion and improving road traffic efficiency.

Damping behavior analysis for connected automated vehicles with linear car following control

Connected automated vehicles (CAVs), built upon advanced vehicle control and communication technology, can improve traffic throughput, safety, and energy efficiency. Previous studies on CAVs control focus on instability and stability properties of CAV platoons; however, these analyses cannot reveal the damping platoon oscillation characteristics, which are important for enhancing CAV platoon reliability against variant continuous perturbations. To this end, this research seeks to characterize the damping oscillations of CAVs through exploiting the platoon's unforced oscillatory, i.e., damping behavior. Inspired by the mechanical vibration theory, the proposed approach is applied to a CAV platoon with linear car-following control formulated as Helly's model and the predecessor-following communication topology. The proposed approach is applied to a CAV platoon with the linear car-following control formulated as Helly's model and the predecessor-following communication topology. Numerical analysis results show that a periodic perturbation with the resonance frequency of the CAV platoon will amplify the oscillation and lead to the severest oscillatory traffic. Our analysis highlights the importance of preventing platoon oscillations from resonance in ensuring CAV platooning reliability.

Real-time energy-saving control for HEVs in car-following scenario with a double explicit MPC approach

The rapid growth of electrification, automation and connectivity in the transport industries puts forward higher requirements on control strategies to improve energy efficiency, traffic safety and driving comfort. Intense efforts have developed energy management strategies (EMS) in car-following scenarios for hybrid electric vehicles (HEVs) by adopting model predictive control (MPC). However, the computational complex online optimization intrinsic to MPC hinders its real-time implementation. This paper is thus proposed to develop a framework of energy-saving controller for HEVs based on explicit MPC, taking advantage of its online computational efficiency, to enable real-time control. To achieve this, the constrained finite-time optimization control (CFTOC) problems of car-following control and energy management strategy for a hybrid electric vehicle are formulated separately. The two problems are then shifted to explicit MPC by precomputing the explicit solutions offline and the control laws are coupled together to form the control framework. Numerical simulations show that the proposed controller can improve the energy efficiency, driving safety and comfort while reduce the online computational costs. Moreover, the result of the hardware-in-the-loop experiment demonstrates the real-time performance of the proposed controller.

Automatic Weight Determination in Model Predictive Control for Personalized Car-Following Control

Car-following control is a fundamental application of autonomous driving. This control has multiple objectives, including tracking a safe distance to a preceding vehicle and enhancing driving comfort. Model Predictive Control (MPC) is a powerful method due to its intuitiveness and capability to cover multiple objectives. MPC determines the relative importance of objectives through a set of weight factors, depending on which, the controller’s behavior changes even if the traffic situations are the same. However, determining the optimal weight is not a trivial problem because there is no benchmark to evaluate the performance of the weight, and searching for weight factors with repeated driving experiments is time-consuming. To solve this problem, we proposed an automatic tuning method to determine the weights of the MPC based on personal driving data. Personal driving data under naturalistic driving conditions provide car-following situations and driver’s behaviors. These data can generate a reference model to represent the driver’s driving style. Based on this model, the proposed method defined the automatic tuning problem as an optimization problem that minimizes the difference between the reference and the controller’s response using the optimal weight factors. This optimization problem was solved using the Particle Swarm Optimization algorithm. The proposed method was implemented with an embedded optimization coder in an offline fashion. Its performance was evaluated using personal driving data. From this, the proposed method can reduce the effort and time required for an engineer to find the optimal weight factors.

Stochastic Calibration of Automated Vehicle Car-Following Control: An Approximate Bayesian Computation Approach

Stochastic Calibration of Automated Vehicle Car-Following Control: An Approximate Bayesian Computation Approach

Stochastic Capacity Analysis for a Distributed Connected Automated Vehicle Virtual Car-Following Control Strategy

Stochastic Capacity Analysis for a Distributed Connected Automated Vehicle Virtual Car-Following Control Strategy

Self-delayed feedback car-following control with the velocity uncertainty of preceding vehicles on gradient roads

Uphill and downhill roads are prevalent in mountainous areas and freeways. Despite the advancements of vehicle-to-vehicle (V2V) communication technology, the driving field of vision could be still largely limited under such a complex road environment, which hinders the sensors from accurately perceiving the speed of front vehicles. As such, a fundamental question for autonomous traffic management is how to control traffic flow associated with the velocity uncertainty of preceding vehicles? This paper aims to answer this question by devising a cooperative control method for autonomous traffic to stabilize the traffic flow under such a complex road environment. To this end, this paper first develops a traffic flow model accounting for the uncertainty of preceding vehicle’s velocity on gradient roads and further devises a new self-delayed feedback controller based on the velocity and headway differences between the current time step and historical time step. The sufficient condition where traffic jams do not occur is derived from the perspective of the frequency domain via Hurwitz criteria and \(H_{\infty }\) norm of transfer functions. The Bode diagram reveals that the robustness of the closed-loop traffic flow model can be significantly enhanced. Simulation results show that the key parameters (control gain coefficient and delay time) of the designed controller contribute to the stability of traffic flow, which is consistent with the theoretical analysis conclusion.

An optimal control-based vehicle speed guidance strategy to improve traffic safety and efficiency against freeway jam waves

Freeway jam waves create many problems, including capacity reduction, travel delays, and safety risks. The development of cooperative vehicle infrastructure system (CVIS) has prompted numerous new strategies, which can resolve jam waves by implementing microscopic car-following control actions to individual vehicles. However, most of those strategies aimed at eliminating freeway jam waves without considering the safety risks induced by the car-following control. This paper proposes an optimal control-based vehicle speed guidance strategy to improve both traffic efficiency and safety against jam waves. The optimal controller is developed based on a discrete first-order traffic flow model formulated in Lagrangian coordinates. The optimization of vehicles’ driving speed is formulated as a linear programming problem, where the constraints concerning threshold safety measures are imposed. The proposed vehicle speed guidance strategy is tested using a modified Intelligent Driving Model (IDM+), which represents real traffic dynamics in CVIS environment. The proposed speed guidance strategy is compared with a state-of-the-art jam-absorption driving strategy, which also aimed to eliminate freeway jam waves. Simulation results show that the proposed strategy outperforms that strategy in terms of both total time spent saving and surrogate safety measures’ reduction. The time exposed time-to-collision (TET) is reduced by 31%, and the time integrated time-to-collision (TIT) is reduced by 9.5% on average. Furthermore, the computation time of the linear optimization is only a few seconds, which is fast enough for the online application of the proposed strategy.

Human–machine cooperative scheme for car-following control of the connected and automated vehicles

To address the out-of-the-loop problem of the automated driving, a human–machine cooperative scheme for car-following control of the connected and automated vehicles (CAVs) is proposed. The proposed scheme can keep the drivers always in the loop and improve the car-following performance. To be specific, the driving automation system (artificial driver) is assigned to the task of velocity tracking and the human driver is responsible for headway adjustment. For the velocity tracking task, a feedforward–feedback control strategy was designed firstly by considering the advantages of the accurate perception and communication of CAVs, then an H∞ suboptimal control method was developed to optimize the controller parameters according to the desired performance index, further the controller was fine-tuned based on the idea of human-simulated intelligent control (HSIC) to improve the dynamic performance of the velocity tracking. For the operator’s headway adjusting task, the stability analysis based on the Lyapunov function proved that the simple proportional feedback control can be assumed by the driver to ensure the system stability under the cooperation of automated velocity tracking. The experiments based on the driving simulator demonstrated that human–machine cooperative scheme for car-following can reduce the tracking error of vehicle distance effectively, and the human driver can be kept in the control loop with a smaller operating load.