Simulation Performance Evaluation of Pure Pursuit, Stanley, LQR, MPC Controller for Autonomous Vehicles

Liu, Jia; Yang, Zhiheng; Huang, Zhejun; Li, Wenfei; Dang, Shaobo; Li, Huiyun

doi:10.1109/rcar52367.2021.9517448

Cited by 30 publications

(17 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Закладка не определена. [2][3][4][5][6][7][8]. The turning angle of the motor grader can be defined using only the location of the target point and angle φ between the machine course vector and the prediction vector.…”

Section: Research Resultsmentioning

confidence: 99%

“…The «pure pursuit» method consists of a geometric calculation of the radius of the circular arc connecting the location of the rear axle with the target point on a trajectory in front of the vehicle. The target point is determined based on the lookahead distance L 0 from the midpoint of the rear axis to the trajectory 1,2,3,4,5,7 [2][3][4][5][6][7][8].…”

Section: Pure Pursuit Methods Descriptionmentioning

confidence: 99%

“…One of the wellknown methods of controlling the self-driving cars is the «pure pursuit» method 1,2 . This method is used to control mobile robots 3 [2,3,4], unmanned vehicles 4,5 [5], agricultural machines [6], logging harvesters [7], underwater uninhabited vehicles [8], etc. However, there are no studies of this method when driving a grader.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Pure pursuit method use to control unmanned motor grader

Sukharev

2022

Vestn. SibADI

View full text Add to dashboard Cite

Introduction. A relevant objective of implementing the advanced systems of self-driving road construction vehicles can be accomplished by mathematical modelling. One of the important issues when creating a motion control system for a self-driving vehicle is to develop a trajectory following algorithm. The most well-known method of following the trajectory is a pure pursuit method, which is successfully used to control the movement of mobile robots.Materials and methods. Hence, the research objective has been defined and is to adapt the pure pursuit method to control an autonomous grader. To achieve the research objective, the task of a mathematical model of the motor grader movement with front steering wheels has been developed, and a mathematical model of the motor grader motion control system has been compiled. Besides, we propose an integral criterion to evaluate the efficiency of the motion control system of a unmanned grader. Some theoretical studies of the mathematical model have been carried out and the dependencies of the integral criterion on the design and operational parameters of the grader, as well as on the parameter of the control method (visibility range) have been obtained. Moreover, the optimal values of the visibility range for various values of the base length, base coefficient and machine speed have been defined according to the proposed efficiency criterion.Results. As a result of approximating the obtained optimal values, the pure pursuit method has been modified to control a self-driving motor grader, taking into account its design features and travel speed. The results obtained can be used to create the prototypes of unmanned control systems for road construction vehicles.

show abstract

Section: Research Resultsmentioning

confidence: 99%

Section: Pure Pursuit Methods Descriptionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Pure pursuit method use to control unmanned motor grader

Sukharev

2022

Vestn. SibADI

View full text Add to dashboard Cite

show abstract

“…Specifically, the increment Δδ is considered as the variation from ith control variable to i + 1th control variable, and Δδ is encoded as an 8 bits binary string. Consequently, each individual of GA is expressed as (22).…”

Section: Increment Encodingmentioning

confidence: 99%

“…is is accomplished by minimizing a multistage cost function with respect to the future control actions, considering a set of constraints both in the control actions and the plant outputs [21]. Different methods, such as PP, Stanley, Linear Quadratic Regulator (LQR), and MPC with Ackermann steering model are investigated [22], and these methods are tested on different shape paths in simulation experiments. It is demonstrated that the performance of the MPC controller is better than those using Pure Pursuit and Stanley controllers.…”

Section: Introductionmentioning

confidence: 99%

Path Tracking Method Based on Model Predictive Control and Genetic Algorithm for Autonomous Vehicle

Wang¹,

Chen²,

Yang

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Model predictive control (MPC) is often used for controlling the autonomous vehicle tracking the target path. But to apply MPC schemes, the nonlinear model of vehicle kinematics needs to be approximately converted to a linear format, and the path tracking problem has to be converted into certain formats in order to implement the solver of convex quadratic programming. To solve these issues, a control strategy combining MPC and genetic algorithm (GA) is put forward. The nonlinear predictive model is adopted to predict the future movement of a controlled vehicle. The objective function is established according to the future movement and target path. Instead of using a convex quadratic programming solver, GA is applied to solve the optimization problem. The proposed MPC-GA method can handle the arbitrary nonlinear problem and make the objective function more comprehensible and flexible. This method is applied in solving the path tracking problem of an autonomous vehicle. Both simulations and on-field tests are conducted. The results validate the efficiency of the proposed MPC-GA path tracking method in comparison with traditional methods. With the MPC-GA controller, the automatic driving on the park road is basically realized. The control strategy can be considered as an alternative method to solve the path tracking problem for an autonomous vehicle.

show abstract

Learning vision based autonomous lateral vehicle control without supervision

Khan

Sülö²,

Öcal³

et al. 2023

Appl Intell

View full text Add to dashboard Cite

Supervised deep learning methods using image data as input have shown promising results in the context of vehicle control. However, these supervised methods have two main disadvantages: 1) They require a copious amount of labeled training data, which is difficult and expensive to collect. 2) Such models do not perform well, when situations that are not in the distribution of the training set are encountered. This includes deviations from the designated driving behavior. We therefore provide a framework to mitigate these problems from merely an unlabeled sequence of images. Visual Odometry is first used to determine the vehicle trajectory. Model Predictive Control (MPC) then uses this trajectory to implicitly infer the steering labels. Meanwhile, synthesized images at deviated trajectories are included in the training distribution for enhanced robustness of the neural network model. Experimental results demonstrate that the performance of our network is at par with methods requiring additional data collection or supervision. Code and supplementary information is available here: https://github.com/idilsulo/nn-driving

show abstract

Simulation Performance Evaluation of Pure Pursuit, Stanley, LQR, MPC Controller for Autonomous Vehicles

Cited by 30 publications

References 13 publications

Pure pursuit method use to control unmanned motor grader

Pure pursuit method use to control unmanned motor grader

Path Tracking Method Based on Model Predictive Control and Genetic Algorithm for Autonomous Vehicle

Learning vision based autonomous lateral vehicle control without supervision

Contact Info

Product

Resources

About