Lateral Control Algorithm Research Articles

Engineering applications of artificial intelligence a knowledge-guided reinforcement learning method for lateral path tracking

Lateral Control algorithms in autonomous vehicles often necessitates an online fine-tuning procedure in the real world. While reinforcement learning (RL) enables vehicles to learn and improve the lateral control performance through repeated trial and error interactions with a dynamic environment, applying RL directly to safety-critical applications in real physical world is challenging because ensuring safety during the learning process remains difficult. To enable safe learning, a promising direction is to make use of previously gathered offline data, which is frequently accessible in engineering applications. In this context, this paper presents a set of knowledge-guided RL algorithms that can not only fully leverage the prior collected offline data without the need of a physics-based simulator, but also allow further online policy improvement in a smooth, safe and efficient manner. To evaluate the effectiveness of the proposed algorithms on a real controller, a hardware-in-the-loop and a miniature vehicle platform are built. Compared with the vanilla RL, behavior cloning and the existing controller, the proposed algorithms realize a closed-loop solution for lateral control problems from offline training to online fine-tuning, making it attractive for future similar RL-based controller to build upon.

Dynamic Modeling, Simulation, and Optimization of Vehicle Electronic Stability Program Algorithm Based on Back Propagation Neural Network and PID Algorithm

Dynamic Modeling, Simulation, and Optimization of Vehicle Electronic Stability Program Algorithm Based on Back Propagation Neural Network and PID Algorithm

Development of a real-time autonomous driving lateral control algorithm for an articulated bus using a model predictive control algorithm

Development of a real-time autonomous driving lateral control algorithm for an articulated bus using a model predictive control algorithm

Enhancing Autonomous Vehicle Lateral Control: A Linear Complementarity Model-Predictive Control Approach

Model-predictive control (MPC) offers significant advantages in addressing constraint-related challenges and plays a pivotal role in self-driving car technology. Its primary goal is to achieve precise trajectory tracking while prioritizing vehicle stability and safety. However, real-time operations often face challenges related to computational demands and low computational efficiency. To address these challenges, this paper introduces a novel lateral control algorithm for self-driving vehicles, which utilizes the linear complementarity problem (LCP) instead of the conventional quadratic programming (QP) method as the MPC optimization solution. This innovative approach incorporates the electric steering system into the vehicle dynamics model, allowing for precise torque regulation of the steering motor and enhancing control accuracy. The MPC algorithm adopts the LCP solution method to calculate control signals based on the vehicle’s state, ensuring both rapid and stable vehicle control. Simulation results demonstrate that the proposed MPC algorithm, utilizing the LCP solution method, effectively addresses efficiency issues in the lateral motion of self-driving cars. This leads to improvements in both driving stability and real-time performance. Overall, this innovative approach lays a solid foundation for the practical implementation of self-driving cars.

Coupled lateral and longitudinal trajectory tracking control with a modified vehicle kinematics model for autonomous vehicles

Abstract The paper proposes a coupled lateral and longitudinal trajectory tracking control algorithm based on model predictive control (MPC) to enhance the precision and stability of trajectory tracking of autonomous vehicles. The coupled MPC controller is developed based on a modified vehicle kinematics model, which simultaneously takes the steering angle and the longitudinal speed as control variables. The modified vehicle model and the coupled MPC controller are verified by CarSim and MATLAB/Simulink co-simulation experiments. Simulation results demonstrate that, at the cost of 12 percent increase in average computational time, the proposed coupled MPC controller leads to an approximate 48 percent reduction in tracking error compared to the benchmarking coupled lateral and longitudinal MPC controller based on the classic kinematics model.

Robust servo linear quadratic regulator controller based on state compensation and velocity feedforward of the spherical robot: Theory and experimental verification

There are few studies on the lateral motion of spherical robots. In this article, a new algorithm is proposed to solve the problem of low control accuracy of the lateral motion. A single lateral motion model is established, and the optimal solution of the linear quadratic regulator in infinite time domain is obtained. Aiming at the problems of longitudinal velocity and lateral angle coupling and low control precision, state compensation and velocity feedforward are carried out, and an improved robust servo linear quadratic regulator control algorithm is proposed. Experiments show that the proposed lateral control algorithm has strong adaptability and robustness to changing speeds and lateral angles, and the control effect is stable and reliable.

Research on automatic emergency steering collision avoidance and stability control of intelligent driving vehicle.

In view of the need for emergency steering to avoid collision when the vehicle is in a dangerous scene, and the stability control of the vehicle during collision avoidance. This paper proposes a planning and control framework. A path planner considering the kinematics and dynamics of the vehicle system is used to formulate the safe driving path under emergency conditions. LQR lateral control algorithm is designed to calculate the output steering wheel angle. On this basis, adaptive MPC control algorithm and four-wheel braking force distribution control algorithm are designed to achieve coordinated control of vehicle driving stability and collision avoidance safety. The simulation results show that the proposed algorithm can complete the steering collision avoidance task quickly and stably.

Intelligent electric vehicle trajectory tracking control algorithm based on weight coefficient adaptive optimal control

The track tracking effect of intelligent vehicle directly affects the safety of vehicle and passengers. In the process of intelligent vehicle track tracking, the track tracking accuracy is related to many factors such as track curvature, road friction coefficient, and longitudinal speed change. In this paper, a new lateral and longitudinal coupling control algorithm is proposed. Based on the vehicle dynamics model and the optimal control theory, combined with the fuzzy control theory, the Fuzzy Linear Quadratic Regulator (FLQR) lateral optimal controller is designed, and feed-forward control and predictive controller are added. According to the real-time tracking lateral error and fuzzy control algorithm fed back by the system, the weight coefficient of the lateral displacement deviation in the cost function is dynamically adjusted; considering the coupling effect of lateral and longitudinal controllers of vehicle trajectory tracking control, a model predictive control (MPC) longitudinal speed controller is designed based on MPC theory, considering acceleration constraint and acceleration variation constraint, and taking lateral stability as evaluation index. A joint simulation platform is built based on CarSim and Simulink. The simulation results show that the designed lateral and longitudinal coupling controller of FLQR + MPC has better track tracking accuracy and can improve the driving stability of the vehicle; finally, the tracking effect of the designed algorithm is verified by real vehicle experiments. The maximum error of the designed controller algorithm in real vehicle tracking is 0.56 m, and the tracking effect is good.

Lateral Vehicle Trajectory Planning Using a Model Predictive Control Scheme for an Automated Perpendicular Parking System

This article proposes a lateral vehicle trajectory planning and control algorithm using a model predictive control (MPC) scheme for an automated perpendicular parking system. Previous work showed that approximated clothoid-based local path planning using a virtual towing distance provides low computational time and the stability of lateral vehicle motion in a parking system. However, this approach cannot function in certain parking situations and may cause undesirable steering maneuvers due to state-dependent planning. We present a new approximated clothoid path based on lateral vehicle kinematics to cope with these problems. Using the proposed kinematic model, we formulate an MPC problem for path planning. Then, the proposed lateral vehicle trajectory planning becomes an MPC problem under constraints. Besides, we show that lateral vehicle motion for vertical parking can be implemented using simple kinematic lateral motion control. Experimental results show that the vehicle with the proposed method moves smoothly and completes the given parking mission under constraints, even under tight parking space conditions.

Lateral semi-trailer truck control using a parameter self-learning MPC method in urban environment

This paper analyzes the lateral control technology of autonomous semi-trailer trucks. Existing researches on the lateral control algorithm of semi-trailer trucks focus on making the head-truck or trailer follow a track well while ignoring the motion characteristics during the turning process, leading to specific security issues. Meanwhile, it is difficult to cope with the complex and uncertain factors influencing lateral control effect, such as the curvature of the desired trajectory, the load, and the velocity of the semi-trailer truck. This paper proposes a parametric self-learning model predictive control (MPC) based on the Proximal Policy Optimization of One Step (OSPPO) method to solve these problems. After modeling the kinematics of the semi-trailer truck, a lateral motion controller for the relationship between the head-truck and trailer based on the MPC method is established. The traditional MPC method has difficulty in adapting to the changeable influencing factors. Thus, a deep reinforcement learning algorithm named OSPPO is introduced to improve the flexibility of the MPC method. OSPPO establishes the nonlinear mapping relationship between the critical parameter of the MPC method and the factors influencing control effect by self-learning, avoiding a large amount of labeled data for training. In simulations, Trucksim and Matlab were used to conduct co-simulation to verify the usefulness of the control method. The method was implemented on an autonomous semi-trailer truck for many outdoor scenes. The actual experimental results showed the validity and advantages of the proposed method.

Comparing the performance of lateral control algorithms on long rigid vehicles in urban environments

Existing research on autonomous vehicle control is largely focused on how control algorithms perform on cars; long vehicles or buses have not been significantly investigated. Existing studies indicate that people display positive attitudes to using autonomous buses, indicating the value of researching control algorithms for autonomous buses. To provide insight on the performance of control algorithms on autonomous buses, we compared multiple lateral control algorithms on how well they maneuver a long vehicle around three courses resembling urban environments. We compared the Stanley and pure pursuit control algorithms and two new control algorithms which were improved versions of the Stanley and pure pursuit controllers. We compared the control algorithms in a kinematic simulation which recorded the steering angle and cross track error from the front axle for each controller driving the vehicle at 50 km/h around the course. We hypothesized that the Stanley control algorithm would perform the best due to its success in navigating existing vehicles. The Stanley control algorithm had a low cross track error, but it had a large steering angle and large changes in steering angle. The pure pursuit controller had smoother changes in steering angle, but the cross track error was larger than the Stanley controller. Our results suggest that none of the algorithms we tested were optimal, and that an algorithm which can utilize the ability of the Stanley controller to maintain a low cross track error while also keeping a low steering angle change will perform the best for long vehicles.

Lateral Stability Control of a 4-Wheel Independent Drive Electric Vehicle Using the Yaw Moment Contour Line Concept

This paper describes a new algorithm that independently manages braking and driving forces to improve the lateral stability of a vehicle equipped with independent drive motors on all wheels. In a similar way to previous research, the proposed algorithm controls yaw rate to improve lateral stability. However, unlike in previous research that only used differential braking, our algorithm controls both driving and braking forces on all four wheels independently to achieve the target yaw rate. The core contribution of this paper is the distribution logic that determines the braking and driving forces to apply at each wheel. To develop this distribution logic, we introduce the concept of yaw moment contour line. Using this concept, the optimal distribution strategy can be derived by considering yaw moment control performance, lateral movement performance, and deceleration minimization performance in eight different driving situations. Based on this strategy, we design a lateral stability control algorithm that is made up of a target yaw rate, a yaw moment controller, and a distributor. Simulations were performed to investigate the performance of the proposed algorithm using MATLAB/Simulink and the CarSim vehicle dynamics software. The simulation results show that the proposed control algorithm improves vehicle motion in terms of yaw rate tracking, lateral movement, and minimization of deceleration.

Lateral Control of an Autonomous and Connected Following Vehicle With Limited Preview Information

Lateral control of an autonomous and connected vehicle (ACV), especially in emergency situations, is important from the safety viewpoint. In these situations, the trajectory to be followed by an ACV must either be planned in real-time (e.g., for a possible evasion maneuver if the obstacle to be avoided is detected) or be communicated from its preceding vehicle. Typically, the trajectory information is available to the following ACV in the form of GPS time samples. From the viewpoint of lateral control, the lateral velocity information is not readily available and the feedback structure must reflect this reality. In this paper, we develop a methodology to synthesize a lateral control algorithm for a following ACV in a two-vehicle platoon in two steps: 1) From the limited preview information of the trajectory to be tracked via samples of GPS way points, we estimate the radius of curvature of the trajectory using “least-square” estimation and 2) develop a fixed-structure feedback control scheme for following the predecessor by synthesizing the set of stabilizing gains corresponding to lateral position error, heading error and heading rate error. Numerical simulation and experimental results corroborate the effectiveness of the proposed schemes.

Longitudinal and lateral control of autonomous vehicles in multi‐vehicle driving environments

Lane changes in multi-vehicle driving environments are one of the most challenging manoeuvres for autonomous vehicles. The key innovation of this study is to develop an integrated longitudinal and lateral trajectory planning and tracking control algorithm under vehicle-to-vehicle communication. This algorithm includes two levels: trajectory planning and path-following control. In the upper level, considering riding comfort, a collision-free lane-changing trajectory cluster is generated under different lane change durations. Then, the most appropriate trajectory from this cluster is provided by selecting the optimal lane change duration considering vehicle dynamics safety, collision avoidance of surrounding vehicles and driver preference. At the bottom level, a multiple-input multiple-output triple-step non-linear approach is proposed in the longitudinal and lateral path-following controller design. The stability of the closed-loop system is rigorously proven based on the Lyapunov function. Finally, the effectiveness of the proposed algorithm is verified with a high-fidelity and full-car model on the veDYNA platform.

Adaptive-Event-Trigger-Based Fuzzy Nonlinear Lateral Dynamic Control for Autonomous Electric Vehicles Under Insecure Communication Networks

This article presents a novel adaptive-event-trigger-based fuzzy nonlinear lateral dynamic control algorithm for autonomous electric vehicles under insecure communication networks. The integration of path following control and direct yaw moment control is considered to acquire a better lateral dynamic performance. To effectively tackle inherent nonlinearities of lateral dynamics, the Takagi-Sugeno fuzzy model approach is employed to approximate the nonlinear lateral dynamics. To avoid the infeasibility of state-feedback control due to the immeasurability of sideslip angle, a fuzzy output feedback control strategy is proposed via a useful transformation. To improve resource utilization of the band-limited communication networks, an adaptive event-triggered communication mechanism is proposed to save communication resource. Moreover, to enhance the robustness of the proposed controller, the insecure communication link is considered, which is described by the Bernoulli random distributed process. Finally, simulation results show the proposed adaptive-event-trigger-based fuzzy controller not only can save communication resource, but also achieve the perfect control performance.

Platoon Control of Connected Multi-Vehicle Systems Under V2X Communications: Design and Experiments

This paper focuses on platoon control of multi-vehicle systems in a realistic vehicle-to-vehicle/vehicle-to-infrastructure (V2V/V2I, or V2X) communication environment. To this end, the communication probability of the beacon transmission is analyzed based on the carrier sense multiple access with collision avoidance (CSMA/CA) mechanism. Then, a new car-following model is proposed by considering the communication probability to capture the car-following behavior of connected vehicles (CVs) equipped with V2X communications. The stability of the proposed car-following model is analyzed using the perturbation method. In addition, a nonlinear consensus-based longitudinal control algorithm is designed by considering the interactions between CVs, and an artificial function-based lateral control algorithm is presented. The convergence of the longitudinal and lateral control algorithms is analyzed using the Hurwitz stable theorem and Lyapunov technique, respectively. Also, the string stability of the vehicular platoon is performed based on the infinity-norm method. Finally, field experiments are conducted using four CVs under the scenarios of platoon forming, vehicle merging, and vehicle diverging. The results verify the effectiveness of the proposed method in terms of the trajectory and velocity profiles.

Lateral Stability Control of Four-Wheel Independent Drive Electric Vehicles Based on Model Predictive Control

Four-wheel independent drive electric vehicle was used as the research object to discuss the lateral stability control algorithm, thus improving vehicle stability under limit conditions. After establishing hierarchical integrated control structure, we designed the yaw moment decision controller based on model predictive control (MPC) theory. Meanwhile, the wheel torque was assigned by minimizing the sum of consumption rates of adhesion coefficients of four tires according to the tire friction ellipse theory. The integrated simulation platform of Carsim and Simulink was established for simulation verification of yaw/rollover stability control algorithm. Then, we finished road experiment verification of real vehicle by integrated control algorithm. The result showed that this control method can achieve the expectation of effective vehicle tracking, significantly improving the lateral stability of vehicle.

Design and analysis of lateral motion control algorithms for an unmanned aerial vehicle with two control surfaces

This paper considers control of an unmanned aerial vehicle with two horizontal aerodynamic control surfaces in the modes of angular stabilization and coordinated turn. We analyze the linear yaw angle control algorithms based on roll angle variation in terms of their performance. In addition, we suggest an algorithm that ensures a required performance of yaw angle control. Some simulation results are given.

Cloud Model Approach for Lateral Control of Intelligent Vehicle Systems

Studies on intelligent vehicles, among which the controlling method of intelligent vehicles is a key technique, have drawn the attention of industry and the academe. This study focuses on designing an intelligent lateral control algorithm for vehicles at various speeds, formulating a strategy, introducing the Gauss cloud model and the cloud reasoning algorithm, and proposing a cloud control algorithm for calculating intelligent vehicle lateral offsets. A real vehicle test is applied to explain the implementation of the algorithm. Empirical results show that if the Gauss cloud model and the cloud reasoning algorithm are applied to calculate the lateral control offset and the vehicles drive at different speeds within a direction control area of ±7°, a stable control effect is achieved.

Cooperative lateral vehicle control for autonomous valet parking

This paper presents a lateral vehicle control algorithm for autonomous valet parking (AVP). Under the assumption that the position and heading angle are provided via vehicle-to-infrastructure (V2I) communication, the lateral controller aims to conduct two different driving maneuvers, i.e., forward driving and backward parking, and to control various types of vehicles in a unified approach. Therefore, it is necessary for the lateral controller to be robust enough to track the desired trajectories for different driving maneuvers, as well as to compensate for the uncertainty caused by the need to consider various vehicle types. With the assumption of operating conditions such as a low speed and small slip angle, a nonlinear kinematic model with kinematic constraints is used for the design of the lateral control. Based on this nonlinear model, a nonlinear control technique called dynamic surface control (DSC) is applied to design the lateral controller, and its stability is analyzed in the framework of linear differential inclusion. Finally, the proposed lateral control algorithm is validated through vehicle simulations and field tests.