Vehicle Trajectory-planning and Trajectory-tracking Control in Human-autonomous Collaboration System

This paper explores lane changing trajectory planning and tracking control for intelligent vehicle on curved road. A novel arcs trajectory is planned for the desired lane changing trajectory. A kinematic controller and a dynamics controller are designed to implement the trajectory tracking control. Firstly, the kinematic model and dynamics model of intelligent vehicle with non-holonomic constraint are established. Secondly, two constraints of lane changing on curved road in practice (LCCP) are proposed. Thirdly, two arcs with same curvature are constructed for the desired lane changing trajectory. According to the geometrical characteristics of arcs trajectory, equations of desired state can be calculated. Finally, the backstepping method is employed to design a kinematic trajectory tracking controller. Then the sliding-mode dynamics controller is designed to ensure that the motion of the intelligent vehicle can follow the desired velocity generated by kinematic controller. The stability of control system is proved by Lyapunov theory. Computer simulation demonstrates that the desired arcs trajectory and state curves with B-spline optimization can meet the requirements of LCCP constraints and the proposed control schemes can make tracking errors to converge uniformly.

The rapid development of autonomous driving technology has made it possible for autonomous vehicles to enter a wide range of people's daily lives. On the basis of realizing automatic driving, it is necessary to improve the comfort of autonomous driving in the future to meet the requirement of different people. In this paper, we presented trajectory planning and tracking control for autonomous vehicle. Then, based on the trajectory characteristics of the human driver's actual driving, the driver's personalized trajectory is planned. The simulation shows that the personalized autonomy can be achieved.

With the development of computer technology and semiconductor technology and the improvement of people’s living standards, automatic driving technology has attracted more and more attention from the industry. Compared with manual driving, able to drive vehicles can have higher perceived distance, higher operation accuracy and better compliance with traffic rules. As one of the key technologies in the field of intelligent driving, intelligent vehicle trajectory planning and control is the technical premise of realizing unmanned driving. Under the current technology, the complex coupling relationship between vehicle longitudinal and transverse motion limits the further rapid development of intelligent vehicle path tracking control. Scholars at home and abroad focus on the motion control of autopilot, which includes horizontal motion control, longitudinal motion control and multi vehicle cooperative control. Trajectory planning and tracking control are important parts to ensure the normal driving of intelligent vehicles. As the basic condition and key technology of realizing driverless vehicle, intelligent vehicle trajectory planning and control has important research significance. Therefore, it is of far-reaching research significance to formulate appropriate control methods to overcome the nonlinearity of vehicles and the complexity of driving conditions. In this paper, the Model Predictive Control, (MPC) theory is used to study the vehicle trajectory planning and control technology. Model predictive control has the ability to consider predictive information and deal with multiple constraints, which provides a new way for vehicle motion control with multiple application scenarios and multiple control targets. Therefore, it is of great significance to study the application of model prediction in vehicle tracking control to improve the tracking effect, driving stability and real-time solution of vehicles under multi-control targets. In the study, we will also consider the scenes that need to avoid parking, so that the trajectory planned by the algorithm is more in line with human driving habits, and can be applied to complex traffic scenes that need to avoid moving obstacles.

<div class="section abstract"><div class="htmlview paragraph">Autonomous driving technology represents a significant direction for future transportation, encompassing four key aspects: perception, planning, decision-making, and control. Among these aspects, vehicle trajectory planning and control are crucial for achieving safe and efficient autonomous driving. This paper introduces a Combined Model Predictive Control algorithm aimed at ensuring collision-free and comfortable driving while adhering to appropriate lane trajectories. Due to the algorithm is divided into two layers, it is also called the Bi-Level Model Predictive Control algorithm (BLMPC). The BLMPC algorithm comprises two layers. The upper-level trajectory planner, to reduce planning time, employs a point mass model that neglects the vehicle's physical dimensions as the planning model. Additionally, obstacle avoidance cost functions are integrated into the planning process. In the upper trajectory planner, the fifth-order polynomial algorithm is also used to smooth the planned trajectory to meet the requirements of vehicle dynamics and passenger comfort. The lower-level trajectory tracker is responsible for real-time trajectory tracking and control, and the paper conducts experiments comparing the Model Predictive Control (MPC) algorithm with the Linear Quadratic Regulator (LQR) algorithm, under the premise of considering the feasibility, cost and safety of the experiment, the front wheel steering Ackerman experimental car is selected as the experimental carrier to verify the reliability of the MPC trajectory tracking control algorithm and ensure the stable driving of the vehicle along the planned trajectory. To address complex road environments, a dynamic obstacle avoidance algorithm is incorporated during the trajectory planning phase. This algorithm allows the vehicle to rapidly generate collision-free trajectories when encountering obstacles, utilizing techniques such as envelope polygonal distance and anti-roll constraints. Compared with other trajectory planning algorithms, the MPC algorithm used in this paper can better adapt to the uncertainty of the system and has better robustness in the face of external disturbances. Finally, the proposed approach is validated through simulation experiments using the Carsim-Simulink co-simulation tool at four different speeds: 10 m/s, 20 m/s, 30 m/s, and 40 m/s. The results demonstrate that the BLMPC algorithm not only ensures safe and comfortable driving but also exhibits high planning efficiency and obstacle avoidance performance in complex road environments. This research provides valuable guidance for advancing autonomous driving technology and its practical implementation</div></div>

Following the Model-Driven Architecture (MDA) approach, we have modeled and implemented planar trajectory planning and tracking controllers for Autonomous Underwater Vehicles (AUVs). This model covers all steps including the requirements management, analysis, design, and implementation to conveniently realize controllers for most standard AUV platforms. It also allows the designed elements to be customizable and re-usable in the development of new control applications for various AUVs. The paper describes step-by-step the development lifecycle of planar trajectory-tracking controllers for AUVs. Based on this proposed model, a horizontal planar trajectory-tracking controller of a low-cost turtle-shaped AUV was developed and taken on trial trips with good feasibility.KeywordsAutonomous Underwater Vehicles (AUV)AUV controlModel-Based Systems Engineering (MBSE) designModel-Driven Architecture (MDA)Real-Time UML/MARTE

Trajectory planning and tracking control are two keys of collision avoidance for autonomous vehicles in critical traffic scenarios. It requires not only the system functionality, but also strong real-time. In this paper, we integrated trajectory planner and tracking controller for autonomous vehicle to implement trace planning and tracking for obstacle avoidance. The trajectory planner is based on the state lattice approach and the tracking controller is designed based on the model predictive control using the vehicle kinematics model. The simulation shows that the planner can generate smooth trajectories which could be selected as references for the controller. The maximum tracking error is less than 0.2 m when the vehicle speed is below 50 km/h. Additionally, the on field test shows that the test vehicle with this method is capable of following the reference path accurately, even at sharp corners.

This study proposes a global vision-based approach for trajectory planning and tracking control of Underactuated Unmanned Surface Vehicles (USVs). This scheme first utilizes global vision to obtain the position and surrounding environment information of USVs, and combines the A * algorithm with B-spline curves to generate trajectories that can be used for vehicle tracking and control. Next, design an extended state observer (ESO) to estimate the lumped disturbance and unmeasured velocity state. Based on ESO, design a model predictive controller and sliding mode controller that can achieve trajectory tracking control solely relying on position information and yaw angle information. Finally, simulation experiments were conducted on the Webots simulation platform, and the results showed the feasibility of the proposed solution.

Human-machine co-driving (HMcD) is a crucial technical architecture in the transitional stage of automobile intelligence development. However, a potential conflict due to inconsistent intentions between human drivers and autonomous driving (AD) systems enormously hinders the progress of intelligent vehicles, especially on curved roads. Even though there have been certain studies on human-like trajectory planning methods, few of them address from the perspective of driving behavior characteristics learning. This paper proposed a collaborative trajectory planning and tracking control scheme for HMcD in curve scenarios. Firstly, the data of skilled human drivers were collected under various curved conditions on a designed driver-in-loop (DiL) real-time simulation platform, and the steering behaviors and trajectory characteristics of human drivers were analyzed in terms of lane, roadside constraint and road curvature. Based on these characteristics, a sliding online human-like trajectory planning (SOHTP) model was proposed, path information, vehicle state, and driving outcome were identified as model input. In addition, a HMcD shared controller was designed on account of Nash equilibrium and optimal control theory. The dynamic disturbance, i.e., future time-varying curvature, was incorporated into the closed loop of human-vehicle-road planning and control. Finally, the performance comparisons and verification tests were designed and carried out. The results show that the constructed HMcD collaborative control system efficiently alleviates human-machine conflict, reduces driving burden, and improves driving satisfaction compared to completely manual driving.

Trajectory planning and tracking control for vehicles with tire blowout in complex traffic flows

This paper introduces a lane-changing strategy aimed at trajectory planning and tracking control for intelligent vehicles navigating complex driving environments. A fifth-degree polynomial is employed to generate a set of pot... | Find, read and cite all the research you need on Tech Science Press

An integrated approach for vehicle trajectory planning and tracking control is proposed in this paper, aiming at enhancing the ability to avoid obstacles by autonomous vehicles when they are in a complex dynamic environment. And the method combines the improved driving risk field model with model predictive control, and integrates speed planning, trajectory planning, and tracking control into a multi-objective optimization problem. First, considering the impact of dynamic traffic conditions on driving risk, an improved driving risk model is constructed by introducing the time to collision (TTC) indicator as well as the parameters of vehicle intrinsic properties and motion state attributes. Next, a dynamic vehicle model of three degrees of freedom (3DOF) is established. Based on the model predictive control (MPC) algorithm, the corresponding cost function and constraint conditions are designed by considering the multi-dimensional objectives of vehicle stability, comfortableness, driving safety, etc. Finally, different traffic scenarios were set up for simulation verification using the Simulink + Prescan + Carsim joint simulation platform. A comparative analysis was conducted between the integrated control method proposed in this study and the hierarchical control method and integrated control without considering TTC method, and the results indicate that the control method mentioned in this paper can achieve dynamic obstacle avoidance for autonomous vehicles in various traffic scenarios. And it can also achieve a more accurate and more stable driving trajectory and thus ensure the driving comfortableness and safety. And the improved driving risk field model mentioned in this paper draws a more accurate image of driving risks in a complex environment compared with the traditional driving risk field model which could improve the driving safety and applicability of autonomous vehicles in dynamic traffic environments.

To address the vehicle trajectory planning and tracking control problem in vehicular platoon control, we propose a two-layered hierarchical control framework based on deep deterministic policy gradient (DDPG) combined with incremental PID with switching function, considering the communication abnormal (packet-dropout, time delay, interruption) during the following process. Firstly, the vehicle dynamics model is constructed based on vehicle theory, secondly, the state space, action space, and multi-objective reward function are designed based on reinforcement learning theory for the decision-making of the RL-Agent, and finally, the effectiveness of the designed controller was validated through experimental simulations. The results show that: the controller designed in this paper, not only can realize the vehicle speed error, and vehicle space error quickly converge to zero, but also the communication time delay, the following vehicle can still smoothly follow the preceding vehicle, acceleration, and speed.

Trajectory planning and trajectory tracking control are the key problems of intelligent vehicle autonomous driving system. The traditional control method cannot simultaneously achieve precision,robustness, and constraint satisfaction in the presence of a complex environment and model uncertainties. Although Model Predictive Control (MPC) is able to deal with multiple constraints explicitly,its performance is very much dependent on the model's accuracy. The Learning-based MPC (LB-MPC), which combines the advantages of machine learning and MPC by using a data-driven manner to build or improve the prediction model,thus, it can greatly improve the robustness and accuracy of the control with security. Therefore, this paper provides an overview of methodology development and improvement theory on LB-MPC in intelligent driving path tracking. The main contribution is the following: (i) A hierarchical categorization into three levels for improved structure of LB-MPC with learning, controller paramter optimization, and safety integration mechanism;(2) formal mathematical analysis on the trade-offs between model accuracy and computation complexity in real-time control scenario;(3) rigorous analysis of the performance and robustness to unseen scenarios. Comparative literature review reveals that the LB-MPC methods achieve a performance gain of about 15%-40% over the standard MPC with respect to the tracking accuracy when model uncertainties are present:while keeping the rate of constraint violations above 95% for challenging problems. Yet it comes with an increase of 20-300% computation time according to the learning model's complexity,and their generalization performance degrades by 25-60% out of the training distribution. This systematic review points to the main open problems for safety verification, online adaptation, and theoretical stability guaranteeswhich can be used as the starting point to develop an autonomous driving controller.

Study on Intelligent Vehicle Trajectory Planning and Tracking Control Based on Improved APF and MPC

Planning the trajectory of an autonomous wheel loader and tracking its trajectory via adaptive model predictive control