Accurate Path Tracking Research Articles

Neural Active Disturbance Rejection Adaptive Lateral Manipulation Control Method for Unmanned Driving Robot

In this article, a neural active disturbance rejection adaptive lateral manipulation control method for an unmanned driving robot (UDR) is proposed to realize accurate and stable steering and path tracking. Combined with a model of the manipulated vehicle and steering manipulator, an integrated dynamics model of the vehicle manipulated by a UDR is established. Taking the error of the body heading angle and the lateral error of the vehicle as input, an active disturbance rejection controller is designed; it includes a tracking differentiator, nonlinear state error feedback (NLSEF) device, and an extended state observer. To achieve a better performance, the combination mode of the NLSEF is adjusted adaptively by a radial basis function NN. The network is then initialized by a particle swarm optimization algorithm. Finally, the results of simulations and experiments show that the proposed method effectively improves the performance of stable steering and path tracking of the UDR.

Emergency collision avoidance strategy for autonomous vehicles based on steering and differential braking

This paper develops a novel integrated collision avoidance strategy for autonomous vehicles in an emergency based on steering and braking. Specifically, the framework of the collision avoidance strategy is composed of two parts: an up-level decision-making layer and a low-level controller layer. The purpose of the up-level is to select the appropriate control strategy based on the vehicle information, and the low-level is to drive the vehicle according to the instructions generated by the up-level. More concretely, a novel control strategy is proposed by integrating four-wheel steering, active rear steering, and differential braking with guaranteed path-tracking accuracy and driving stability by adaptive model predictive control (AMPC). Finally, extensive co-simulations in MATLAB/Simulink and CarSim are conducted to verify the effectiveness of the proposed collision avoidance strategy in terms of tracking error, yaw rate, and roll angle.

Design and Experiments of Autonomous Path Tracking Based on Dead Reckoning

Path tracking is an important component of autonomous driving and most current path tracking research is based on different positioning sensors, such as GPS, cameras, and LIDAR. However, in certain extreme cases (e.g., in tunnels or indoor parking lots), if these sensors are unavailable, achieving accurate path tracking remains a problem that is worthy of study. This paper addresses this problem by designing a dead reckoning method that is solely reliant on wheel speed for localization. Specifically, a differential drive model is first used for estimating the current relative vehicle position in real time by rear wheel speed, and the deviation between the current path and the reference path is then calculated using the pure pursuit algorithm as a means of obtaining the target steering wheel angle and vehicle speed. The steering wheel and vehicle speed signals are then output by two PID controllers in order to control the vehicle, and the automatic driving path tracking is ultimately realized. Through exhaustive tests and experiments, the stop position error and tracking process error are compared under different conditions, and the effects of vehicle speed, look-ahead distance, starting position angle, and driving mode on tracking accuracy are analyzed. The experimental results show the average error of the end position to be 0.26 m, 0.383 m, and 0.505 m when using BMW-i3 to drive one lap automatically at speeds of 5 km/h, 10 km/h, and 15 km/h in a test area with a perimeter of approximately 200 m.

Autonomous driving using imitation learning with look ahead point for semi structured environments.

Semi-structured environments are difficult for autonomous driving because there are numerous unknown obstacles in drivable area without lanes, and its width and curvature considerably change. In such environments, searching for a path on a real-time is difficult, and localization data are inaccurate, reducing path tracking accuracy. Instead, alternative methods that reactively avoid obstacles in real-time using candidate paths or an artificial potential field have been studied. However, these require heuristics to identify specific parameters for handling various environments and are vulnerable to inaccurate input data. To address these limitations, this study proposes a method in which a vehicle drives toward drivable area using vision and deep learning. The proposed imitation learning method learns the look-ahead point where the vehicle should reach on a vision-based occupancy grid map to obtain a safe policy with a clear state action pattern relationship. Furthermore, using this point, the data aggregation (DAgger) algorithm with weighted loss function is proposed, which imitates expert behavior more accurately, especially in unsafe or near-collision situations. Experimental results in actual semi-structured environments demonstrated the limitations of general model-based methods and the effectiveness of the proposed imitation learning method. Moreover, simulation experiments showed that DAgger with the weight obtains a safer policy than existing DAgger algorithms.

Lateral control of intelligent vehicles using radial basis function neural networks with sliding mode control based on fractional order calculus

PurposeThis paper aimed a fractional-order sliding mode-based lateral lane-change control method that was proposed to improve the path-tracking accuracy of vehicle lateral motion.Design/methodology/approachIn this paper the vehicle presighting and kinematic models were established, and a new sliding mode control isokinetic convergence law was devised based on the fractional order calculus to make the front wheel turning angle approach the desired value quickly. On this basis, a fractional gradient descent algorithm was proposed to adjust the radial basis function (RBF) neuron parameter update rules to improve the compensation speed of the neural network.FindingsThe simulation results revealed that, compared to the traditional sliding mode control strategy, the designed controller eliminated the jitter of the sliding mode control, sped up the response of the controller, reduced the overshoot of the system parameters and facilitated accurate and fast tracking of the desired path when the vehicle changed lanes at low speeds.Originality/valueThis paper combines the idea of fractional order calculus with gradient descent algorithm, proposed a fractional-order gradient descent method applied to RBF neural network and fast adjustment the position and width of neurons.

High clearance four-wheel independent electric drive sprayer path tracking control based on self-correction controller

Most traditional agricultural machines use traditional mechanical transmission with fuel drive and front wheel steering, and most of them are manned, with low transmission efficiency, poor flexibility and low level of intelligence. This paper proposes a new high ground clearance sprayer with four-wheel independent drive (4WID) with dual front and rear steering axles. This sprayer is an oil-electric hybrid that not only saves energy, but also reduces the pollution to crops. In this study, a path tracking controller and a self-correcting controller are constructed based on the kinematic model of the sprayer, respectively. The model prediction controller is used as the main controller, and it outputs the desired steering angle and speed of the sprayer based on the current state of the sprayer and the desired path to achieve path tracking control. The self-correcting controller, as an auxiliary controller, adopts fuzzy control method and designs fuzzy control rules based on the driver’s experience to correct the wheel turning angle at the current moment, which not only retains the advantages of model prediction control in linear path tracking, but also improves the control effect in curved path tracking and enhances the path tracking accuracy in large curvature roads. The simulation shows that the maximum lateral deviation of 0.03 m can be achieved by the model predictive control alone, and the maximum lateral deviation is reduced to 0.0141 m after adding the self-correcting controller.

강화학습을 이용한 자율주행 트랙터의 가변형 전방주시거리 튜닝 알고리즘 개발

Robust path tracking is important for an autonomous tractor to accurately track a path, including straight and curved paths, with headland turning in farmlands. To improve the performance of a path-tracking method developed on the basis of fixed look-ahead distances, this paper presents a look-ahead distance tuning algorithm based on reinforcement learning (RL). The RL architecture is designed to provide variable look-ahead distances in real time based on navigation conditions caused by changes in the lateral deviations and heading errors. The RL agent performed self-learning in the simulation while following C-type turning-based paths. For more effective RL, a simulation model was built by applying the actual responses of a tractor steering system measured using a data acquisition system. An evaluation test was conducted in terms of the lateral deviation in response to the reference path. The proposed method improved the path-tracking accuracy of the lateral deviation by a root mean-squared error of about 62% compared to a path-tracking controller with fixed look-ahead distances.

Emergency steering collision avoidance control based on distributed driving intelligent vehicles

SummaryBased on the distributed drive intelligent electric vehicle, considering the collision avoidance effect of the planned path, the path tracking accuracy, and the body stability requirements in the process of steering collision avoidance, this article proposes a control strategy for emergency steering collision avoidance. First, the fifth‐order polynomial method is used to generate collision avoidance paths, and then a designed cost function is used to evaluate and select the optimal collision avoidance path. Second, a decision‐making strategy that integrates multiple risk judgment models is built. Based on the model prediction method, a path tracking controller is built, and an optimization objective function is established to improve the tracking accuracy. In order to ensure the stability of the vehicle body, a vehicle stability controller is designed based on fuzzy theory. Finally, a vehicle‐in‐the‐loop intelligent driving algorithm test platform is built, and the control algorithm is tested through this platform. The test results show that compared with the pure path tracking control method, the control strategy is reasonable and effective and can better reduce the path tracking error and improve the vehicle's driving stability in the collision avoidance process.

Research on tyre mechanics model for multi-axle coordinated steering of heavy vehicles

Compared with passenger cars, heavy vehicles have larger loads, longer bodies, more steering modes, and are more likely to cause improper steering angle relationships among the wheels, resulting in uncoordinated steering. This uncoordinated steering makes the tyres roll and drag, which results in abnormal lateral and longitudinal slips, changing the lateral and longitudinal mechanical characteristics of tyres and leading to low path tracking accuracy and poor steering performance of vehicles. Therefore, a tyre model containing lateral and longitudinal mechanical characteristics under heavy load is the key to solving the problem of uncoordinated steering in heavy vehicles. Firstly, with the physical tyre model, the lateral and longitudinal slip is described as carcass deflections. With the carcass deflections and contact pressure distribution of heavy load, the tyre forces under uncoordinated steering conditions are derived. Then, the tyre imprint parameters are obtained with a test bench, and a two-dimensional contact pressure distribution model is established to reproduce the contact pressure distribution of tyre under heavy loads and dynamic slips. The comparison results with Magic Formula (MF) and Trucksim are generally consistent, proving the effectiveness of the model. Finally, a lateral and longitudinal tyre force distribution control of vehicles is carried out based on the established model. The results of the Trucksim-Simulink co-simulation show that the path tracking accuracy of vehicles is significantly improved, which demonstrates that the tyre model incorporating lateral and longitudinal mechanical characteristics under heavy loads can provide a theoretical basis for solving the problem of uncoordinated steering in heavy vehicles.

Path tracking control of intelligent vehicles via a speed-adaptive MPC for a curved lane with varying curvature

When driving on a curved lane with varying curvature, human drivers usually make a small range of longitudinal speed adjustments to maintain a yaw response that feels more stable. Taking this type of response as a reference, intelligent vehicles must also make adjustments to their longitudinal speed within a small range during the path tracking process with curvature changes. The current variable curvature path tracking algorithm using model predictive control (MPC) basically assumes that the vehicle moves at a constant speed, which does not match the small-range adjustment of the longitudinal speed and thereby affects the accuracy of path tracking. In this paper, considering the small range of speed variation in the path tracking process, the path and speed decoupling control in Frenet coordinates are used to replace the longitudinal-lateral-yaw complex coupling dynamics control. Meanwhile, considering the problem that the steady-state error of the MPC controller caused by curvature variation in the path tracking process cannot be eliminated, the adaptive weight control (AWC) and adaptive feedforward (AFF) models based on BP neural network (BPNN) data learning are designed to dynamically adjust the lateral error weight and feedforward factors of the MPC controller. As a result, a more accurate path tracking effect is achieved. Simulation results in the joint CarSim-Simulink environment show that the proposed algorithm significantly improves the adaptive capability of the linear MPC controller in response to time-varying conditions and has a higher tracking accuracy.

Double-DQN-Based Path-Tracking Control Algorithm for Orchard Traction Spraying Robot

The precise path-tracking control of tractors and trailers is the key to realizing agricultural automation. In order to improve the path-tracking control accuracy and driving stability of orchard traction spraying robots, this study proposed a navigation path-tracking control algorithm based on Double Deep Q-Network (Double DQN). Drawing on the driver’s driving experience and referring to the principle of radar scanning and the principle of image recognition, a virtual radar model was constructed to generate a virtual radar map. The virtual radar map was used to describe the position relationship between the traction spraying robot and the planned path. Combined with the deep reinforcement learning method, all possible robot driving actions under the current virtual radar map were scored, and the best driving action was selected as the output of the network. In this study, a path-tracking algorithm was self-developed with a deep Q-network trained by driving the traction spraying robot in a simulated virtual environment. The algorithm was tested in both simulations and in a field to follow a typical ‘U’-shaped path. The simulation results showed that the proposed algorithm was able to achieve accurate path-tracking control of the spraying trailer. The field tests showed that when the vehicle speed was 0.36 m/s and 0.75 m/s, the maximum lateral deviation of the algorithm was 0.233 m and 0.266 m, the average lateral deviation was 0.071 m and 0.076 m, and the standard deviation was 0.051 m and 0.057 m, respectively. Compared with the algorithm based on the virtual radar model, the maximum lateral deviation was reduced by 56.37% and 51.54%, the average lateral deviation was reduced by 7.8% and 5.0%, and the standard deviation was reduced by 20.31% and 8.1%, respectively. The results showed that the Double-DQN-based navigation path-tracking control algorithm for the traction spraying robot in the orchard had higher path-tracking accuracy and driving stability, which could meet the actual operational requirements of traditional orchards.

Nonlinear Model Predictive Control with Terminal Cost for Autonomous Vehicles Trajectory Follow

This paper presents a nonlinear model predictive control with terminal cost (NMPC–WTC) algorithm and its open/closed-loop system analysis and simulation validation for accurate and stable path tracking of autonomous vehicles. The path tracking issue is formulated as an optimal control problem. In order to improve the squeezing phenomenon of traditional NMPC, a discrete-time nonlinear model predictive controller with terminal cost is then designed, in which the state error of last step is augmented. The cost function of NMPC–WTC consists of two parts: (1) the traditional NMPC cost function responding to tracking errors and controller output, and (2) the augmented terminal cost. The algorithm was implemented on CasADi numerical optimization framework, which is free, open-source and developed for nonlinear optimization. The open-loop and closed-loop simulation results are then presented to demonstrate the improved performance in tracking accuracy and stability compared to traditional model predictive controller.

Enhancing Feedback Steering Controllers for Autonomous Vehicles With Deep Monte Carlo Tree Search

Steering control is a vital function for autonomous vehicles, whose performance largely determines the driving safety. The widely used feedback steering controllers degrade significantly when vehicles drive at high speeds. This is mainly because these controllers can not effectively exploit nonlinear vehicle dynamics and future road information. Hence, the steering actions generated by these controllers can not achieve accurate and stable path tracking performance. To overcome this limitation, we propose a deep learning based Monte Carlo Tree Search (DeepMCTS) method to enhance the feedback controllers. Due to the accuracy of the learning-based model in characterizing nonlinear vehicle dynamics and the lookahead search ability of MCTS, the control performance of the feedback controllers can be enhanced significantly. Different from MPC methods, which leverage vehicle dynamics and future road information via online optimization, our method relies on the efficient tree search process. Hence, our method can avoid heavy computational burden. Testing results validate the proposed method can achieve better tracking accuracy and stability in high speeds scenarios.

Combining Uneliminated Algebraic Formulations With Sparse Linear Solvers to Increase the Speed and Accuracy of Homotopy Path Tracking for Kinematic Synthesis

Abstract The method of kinematic synthesis requires finding the solution set of a system of polynomials. Parameter homotopy continuation is used to solve these systems and requires repeatedly solving systems of linear equations. For kinematic synthesis, the associated linear systems become ill-conditioned, resulting in a marked decrease in the number of solutions found due to path tracking failures. This unavoidable ill-conditioning places a premium on accurate function and matrix evaluations. Traditionally, variables are eliminated to reduce the dimension of the problem. However, this greatly increases the computational cost of evaluating the resulting functions and matrices and introduces numerical instability. We propose avoiding the elimination of variables to reduce required computations, increasing the dimension of the linear systems, but resulting in matrices that are quite sparse. We then solve these systems with sparse solvers to save memory and increase speed. We found that this combination resulted in a speedup of up to 250 × over traditional methods while maintaining the same accuracy.

A Gain-Scheduled Robust Controller for Autonomous Vehicles Path Tracking Based on LPV System With MPC and H ∞

Due to the uncertainty of vehicle model parameters, modeling errors and external disturbances, the performance of path tracking control system is poor, especially under high velocity and large curvature extreme conditions. To address this issue, this paper presents a novel gain-scheduled robust control strategy based on linear parameter varying system with model predictive control (MPC) and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">H</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">∞</sub> . Firstly, fully considering the influence of the time-varying characteristics of vehicle velocity and tire cornering stiffness on the path tracking system model, a novel linear parameter varying system model is built for path tracking control of autonomous vehicle. Then, a path tracking robust controller is designed based on gain-scheduled approach, and the linear matrix inequality (LMI) is applied to solve optimization problem, in which MPC and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">H</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">∞</sub> robust control theory are applied to the controller design process. Finally, the simulation experiments have verified that the proposed novel robust control strategy can improve the path tracking accuracy and ensure the vehicle lateral and roll stability, especially under high velocity and large curvature extreme conditions. Meanwhile, the proposed robust controller shows superiority to suppress the parameters uncertainty, modeling error and external disturbance.

Path Tracking of a 4WIS–4WID Agricultural Machinery Based on Variable Look-Ahead Distance

Aiming to solve the problem of the low path-tracking accuracy of mobile robots in agricultural environments, the authors of this paper propose a path-tracking method for agricultural machinery based on variable look-ahead distance. A kinematic model of the four wheel independent steering–four wheel independent drive (4WIS–4WID) structure based on pure pursuit was constructed to obtain the functional equation of the current position and the four-wheel steering angle. The fuzzy controller, which takes the lateral deviation and heading deviation as input and the look-ahead distance in a pure pursuit model as output, was designed to obtain the look-ahead distance that changes dynamically with the deviation of mobile agricultural machinery. The path-tracking performance of 4WIS–4WID agricultural machinery in three scenarios (1 m, −90°; 1 m, 0°; and 0 m, 90°) with different initial deviations was tested using a pure pursuit model based on a variable look-ahead distance. The obtained field test results showed an average deviation of 19.7 cm, an average tracking time of 5.1 s, an average stability distance of 203.9 cm, and a steady state deviation of 3.1 cm. The results showed that the proposed method presents a significant path-tracking performance advantage over a fixed look-ahead distance pure tracking model and can be a reference for high-quality path-tracking methods in automatic navigation research.

Gain-Scheduled Steering and Braking Coordinated Control in Path Tracking of Intelligent Heavy Vehicles

Abstract In the context of intelligent transportation system and advanced vehicle control system, higher requirements for intelligent control and coordinated control of heavy vehicles (HVs) have been proposed. Automatic path tracking control is essential for automatic driving of heavy vehicles. However, uncertain lateral disturbances and time-varying characteristics of system parameters make it difficult to guarantee roll stability and path tracking accuracy during automatic path tracking. This paper investigates the coordination of active front steering (AFS) and direct yaw moment control (DYC) in the automatic path tracking system for intelligent heavy vehicles. The main idea is to adjust the braking action according to the rollover risk evaluated by a specific rollover index (RI). The coordination of steering and braking systems and the robustness of the system against time-varying parameters are achieved by a gain-scheduled linear parameter varying (LPV) controller. Based on the linear matrix inequality (LMI) framework, the LPV controller is synthesized to ensure the robust H∞ performance against external disturbances. Simulation results show that the proposed gain-scheduled LPV/H∞ control strategy can enhance roll stability and path tracking accuracy in the path tracking process of intelligent heavy vehicles.

Buffering time optimization for path tracking accuracy in remote vehicle control with digital twin computing

Buffering time optimization for path tracking accuracy in remote vehicle control with digital twin computing

Distributed Multi-Mobile Robot Path Planning and Obstacle Avoidance Based on ACO–DWA in Unknown Complex Terrain

Multi-robot systems are popularly distributed in logistics, transportation, and other fields. We propose a distributed multi-mobile robot obstacle-avoidance algorithm to coordinate the path planning and motion navigation among multiple robots and between robots and unknown territories. This algorithm fuses the ant colony optimization (ACO) and the dynamic window approach (DWA) to coordinate a multi-robot system through a priority strategy. Firstly, to ensure the optimality of robot motion in complex terrains, we proposed the dual-population heuristic functions and a sort ant pheromone update strategy to enhance the search capability of ACO, and the globally optimal path is achieved by a redundant point deletion strategy. Considering the robot’s path-tracking accuracy and local target unreachability problems, an adaptive navigation strategy is presented. Furthermore, we propose the obstacle density evaluation function to improve the robot’s decision-making difficulty in high-density obstacle environments and modify the evaluation function coefficients adaptively by combining environmental characteristics. Finally, the robots’ motion conflict is resolved by combining our obstacle avoidance and multi-robot priority strategies. The experimental results show that this algorithm can realize the cooperative obstacle avoidance of AGVs in unknown environments with high safety and global optimality, which can provide a technical reference for distributed multi-robot in practical applications.

Robust sliding mode prediction path tracking control for intelligent vehicle

Because of the characteristics of nonlinearity, strong coupling, fast time-varying, and uncertainty of the intelligent vehicle movement, the accurate path tracking control of the intelligent vehicle becomes a challenge. Considering a variety of complex constraints from the control system, this article combines sliding mode control and model prediction control to improve the intelligent vehicle real-time path tracking performance and proposes a robust sliding mode predictive controller for intelligent vehicle path tracking control. The sliding mode predictive controller uses the sliding mode surface in sliding mode control to construct the prediction model and corrects the sliding mode control output through continuous feedback correction and rolling optimization and then obtains the optimal control input which makes sure optimal performance control under system various constraints. The sliding mode predictive controller can simultaneously consider the tracking performance and system complex constraints, which effectively improves the dynamic performance and robustness of the control system. Related simulation results show that sliding mode predictive controller not only solves the problem of system constraints but also improves the accuracy of intelligent vehicle path tracking and the robustness of the system.