Path Planning and Tracking Control for Unmanned Surface Vehicle Based on Adaptive Differential Evolution Algorithm

The path planning and tracking control scheme for unmanned vehicle using multi-dimensional Taylor network (MTN) is proposed. First, the reference path is designed by the A-star algorithm, which is a common method used as path planning. Second, design the MTN controller based on PID controller to control the unmanned vehicle tracking the reference path; and the improved BP algorithm is used as the learning of MTN controller. Finally, the simulation experiment of unmanned vehicle is given to verify the effectiveness of the proposed scheme. The simulation results show that the proposed scheme has optimal path planning and good tracking control performance.

Integrated path planning and control through proximal policy optimization for a marine current turbine

In this paper, we present an integrated dynamic path planning and trajectory tracking control strategy for electric vertical take-off and landing (eVTOL) unmanned aerial vehicles (UAVs) by using a receding horizon optimization (RHO) approach. Considering that the effective sensing range of onboard sensors is practically short, we formulate the path planning into minimum curvature-based RHO problems with a polynomial path template. By adding the contraction constraint derived from the backstepping controller, the proposed nonlinear model predictive control (NMPC), as an online optimization scheme, guarantees the closed-loop stability. It also achieves the optimal control performance by minimizing the tracking error and power consumption. The experimental results of the dynamic path planning and trajectory tracking demonstrate the effectiveness of the proposed control algorithm.

Unmanned vehicles are currently facing many difficulties and challenges in improving safety performance when running in complex urban road traffic environments, such as low intelligence and poor comfort performance in the driving process. The real-time performance of vehicles and the comfort requirements of passengers in path planning and tracking control of unmanned vehicles have attracted more and more attentions. In this paper, in order to improve the real-time performance of the autonomous vehicle planning module and the comfort requirements of passengers that a local granular-based path planning method and tracking control based on multi-segment Bezier curve splicing and model predictive control theory are proposed. Especially, the maximum trajectory curvature satisfying ride comfort is regarded as an important constraint condition, and the corresponding curvature threshold is utilized to calculate the control points of Bezier curve. By using low-order interpolation curve splicing, the planning computation is reduced, and the real-time performance of planning is improved, compared with one-segment curve fitting method. Furthermore, the comfort performance of the planned path is reflected intuitively by the curvature information of the path. Finally, the effectiveness of the proposed control method is verified by the co-simulation platform built by MATLAB/Simulink and Carsim. The simulation results show that the path tracking effect of multi-segment Bezier curve fitting is better than that of high-order curve planning in terms of real-time performance and comfort.

Aiming to address the tracking accuracy and anti-rollover problem of the unmanned mining truck path tracking process under the complex unstructured road conditions in mining areas, a coordinated control strategy for path tracking and anti-rollover based on topology theory is proposed. Moreover, optimal equilibrium weights are assigned to path tracking control and anti-rollover control to ensure that the path tracking accuracy of the mining vehicle can be effectively improved in a safe and stable driving state. Regarding the path tracking problem, a lateral preview error model is established, and a path tracking controller is designed using LQR (linear quadratic regulator) control theory. In the design of the anti-rollover controller, the effects of understeer and trip-type rollover on the stability of the vehicle are taken into account, and the ideal transverse swing angular velocity and trip-type rollover evaluation index are introduced for controller design, which reduce the effects of the curves and roadway excitation on the mining truck and improve the rollover motion. Based on a joint simulation using Trucksim and Simulink and the construction of a hardware-in-the-loop simulation platform for verification, the single control strategy and coordinated control strategy are compared and analyzed. The final simulation results show that the tracking error, yaw velocity, and center of mass side deviation angle are optimized by 45%, 32.5%, and 20%, respectively. Therefore, the Extension theory-based coordinated controller satisfies the complex road conditions in the mining area and improves the tracking accuracy to the maximum extent while ensuring the safety and smoothness of vehicle driving and exhibiting good adaptability and robustness.

In order to realize the path following control of the robot in the complex agricultural environment, an intelligent path following control method based on fuzzy PD (proportional derivative) is proposed. Firstly, in order to realize the task of path tracking and automatic steering control, the automatic navigation controller and the automatic steering method based on fuzzy PD control are constructed. The method of driving the robot hardware platform based on plant protection unmanned, developed automatic navigation control system based on laser radar, angle sensor, then according to the structure and control principle of automatic navigation control system, the robot kinematics model, two wheel vehicle control model, pure path tracking control method, finally, has carried on the the design of the tracking control principle and fuzzy PD control method is verified by MATLAB/simulink simulation platform. The results show that the maximum tracking error is only 5cm, and the average tracking error is 1.2cm when the robot tracks with 1.5m/s. The simulation and experimental results show that the control system can effectively control the robot walking on a predetermined path.

Obstacle avoidance problem for the autonomous vehicle has received more and more attention these years, especially for the autonomous heavy vehicle, which has the high gravity center, large carrying capacity and promising commercial prospect. However, the vehicle dynamic properties have been rarely considered for path planning, which is a crucial factor for driving safety. An integrated collision avoidance framework that consists of a new path planner and a tracking controller considering multiple dynamic constraints is proposed for an autonomous multi-axis distributed vehicle. In the upper level, a new optimal path generator based on the B-splines is designed for safety and stability purposes, and the collision avoidance path is optimized considering multiple dynamic constraints, including the tire nonlinear dynamic, lateral stability limits and the anti-slip constraints. Meanwhile, a safety assessment evaluator according to the time to collision calculation is designed for risk level recognition and path planning weight determination. In the lower level, a path tracking controller based on the nonlinear model predictive control (NMPC) is designed to improve the control accuracy, and a high-fidelity nonlinear dynamic predictive vehicle model with 16 degrees of freedom is established to depict the vehicle dynamic properties comprehensively. To solve the nonlinear optimization problem and get the optimal control steering angle output, an adaptive weight adjustment strategy and a varying predictive duration method are formulated. The optimization constraints related to steering actuator ability, plane stability limits, rollover prevention thresholds and tire adhesion requirements are constructed and converted as the bounds of the vehicle dynamic states. To verify the proposed framework, the simulation and HIL test platform are built and different driving scenarios are validated. The test results show the satisfactory performance of path planning and path tracking considering the dynamic constraints for safety and stability

Path planning and tracking control are important modules of mobile robots, which have outstanding advantages in improving the flexibility of mobile robots. However, in the existing applications, these two modules are usually processed separately, which makes the obstacle avoidance process of the mobile robot uncontrollable and reduces the adaptability of the application scenario. In order to realize collision-free high-precision trajectory tracking control of mobile robots in dynamic scenes, this paper proposes an adaptive MPC control method based on curvature constraints, which can improve the safety of operation and reduce the chattering caused by unreasonable paths in the process of operation. Firstly, according to the kinematic constraints of general mobile robots, the constraint model of mobile robot path planning is constructed. At the same time, the adaptive parameter adjustment rules are adopted to realize the balance between the calculation efficiency and the control cycle. Finally, a smooth safe path is obtained by re-fitting the planned path and reprocessing the nodes with excessive curvature. Compared with traditional methods, the proposed method has better advantages.

<abstract> <bold>Abstract. </bold>This paper focuses on path tracking and vibration reducing velocity control inside strawberry field furrows. A path tracking controller is developed which maintains the robot chassis in the center of the furrow and parallel to the furrow walls by minimizing the heading error between the robot’s velocity vector and a look ahead point placed at a constant distance ahead of the robot in the center of the furrow. This type of control is based on a method known as pure pursuit. The velocity controller developed implements a finite state machine which controls the velocity based on the vibration energy. When the vibration is higher or lower than different vibration thresholds, the velocity will be changed accordingly. The results of the experiments demonstrate that by reducing velocity when the robot enters an uneven terrain, the vibration energy of the robot stays within the range that it was in when the robot was on the even terrain. Furthermore, the results indicate that the path tracking controller was able to maintain a lateral error of less than 2 centimeters from the center of a 50 centimeter wide furrow and heading error of less than 3 degrees. Future experiments will include determining the threshold a fragile crop can experience without bruising damage so that a maximum velocity that will maintain the integrity of the crop can be determined.

Differential-steering based path tracking control and energy-saving torque distribution strategy of 6WID unmanned ground vehicle

The performance of the path tracking control system is poor when vehicles navigate under extreme conditions of high speed and large curvature due to the uncertainty of vehicle model parameters, modeling errors and disturbances. To address this issue, this paper introduces a Linear Model Predictive Controller (GP‐SOMPC) based on Gaussian Process (GP) and Snake Optimizer (SO) to achieve high‐performance trajectory tracking control under large curvatures through learning. This algorithm adopts a two‐degree‐of‐freedom vehicle dynamics model and models disturbances and unmodeled dynamics as Gaussian Processes (GP) using collected experimental data. Additionally, an Adaptive Weighting Coefficient Model Predictive Controller based on the Snake Optimizer (SO) method is presented to improve the poor adaptation of vehicle trajectory tracking accuracy according to reference path curvature under fixed weighting coefficients in traditional Model Predictive Control (MPC), which results in inadequate trajectory tracking precision. The simulation experiments have verified that the proposed GP‐SOMPC algorithm can enhance trajectory tracking precision under high‐speed, large curvature conditions and exhibits good adaptability to variations in path curvature.

This paper presents a method to design a path tracking controller with a constraint on tire slip angles under low-friction road conditions. On a low-friction road surface, a lateral tire force is easily saturated and decreases as a tire slip angle increases by a large steering angle. Under this situation, a path tracking controller cannot achieve its maximum performance. To cope with this problem, it is necessary to limit tire slip angles to a value where the maximum lateral tire force is achieved. The most commonly used controllers for path tracking, linear quadratic regulator (LQR) and model predictive control (MPC), are adopted as a controller design methodology. The control inputs of LQR and MPC are front and rear steering angles and control yaw moment, which have been widely used for path tracking. The constraint derived from tire slip angles is imposed on the steering angles of LQR and MPC. To fully verify the performance of the path tracking controller with the constraint on tire slip angles, a simulation is conducted on vehicle simulation software. From the simulation results, it is shown that the path tracking controller with the constraint on tire slip angles presented in this paper is quite effective for path tracking on low-friction road surface.

This paper proposes a novel adaptive path tracking and stability control strategy for autonomous vehicles based on intelligent tires technology that is introduced to estimate the tire-road contact states based on the in-tire sensor signals. Firstly, a tire finite element model was established based on ABAQUS software. On this basis, the Spearman correlation analysis method was used to acquire the optimal sensitive positions of the in-tire acceleration sensors. The feature values of the inputs of the tire-road contact states estimation model were determined through the PLS-VIP analysis method. Then, the tire slip angle and lateral force estimation models whose inputs are the in-tire sensor signals was constructed using the LSTM neural network. Subsequently, an adaptive MPC path tracking control strategy in which the tire cornering stiffness is calculated in real-time by the intelligent tires model was designed. Finally, an adaptive NFTSM lateral stability control strategy which uses the tire lateral force estimated by the intelligent tires model was designed to determine the direct yaw moment, and an efficient and concise algorithm was then designed to achieve torque distribution. The simulation results indicate that the proposed control strategy provides better path tracking accuracy and stability control effect in emergency lane change and high-speed evasive maneuvers under different road conditions.

JADE is an state-of-the-art adaptive differential evolution algorithm which implements “DE/current-to-pbest” as its mutation strategy, adapts its mutation factor and crossover rate, and uses an optional external archive to keep track of potential removed individuals in previous generations. This paper proposes MPADE, which extends JADE by using a multi-populated approach to solve high dimensional real-parameter optimization problems. This mechanism helps preventing the two well-known problems affecting the differential evolution algorithm performance, which are premature convergence and stagnation. The algorithm was tested using the benchmark functions in IEEE Congress on Evolutionary Computation 2014 test suite. MPADE was compared using Wilcoxon test to JADE algorithm and with other state-of-the-art algorithms that either use a multi-population approach or adapt their parameters. The experimental results show that the proposed new algorithm improves significantly its precursor and it is also suggested that other state-of-the-art algorithms could benefit from the multi-populated based approach.

A novel trajectory optimization technique has been proposed in this paper to generate reference trajectory for Satellite Launch Vehicle (SLV). For this purpose, a suitable objective function has been formulated subsuming parameters like height, velocity, injection angle and payload mass. The contribution of these parameters in evolving the objective function has been represented by assigning different weighting factors against the different parameters. Moreover, optimal selection of the setting of parameters has also been achieved by proper optimization of the weighting factors associated with the objective function. In the next step, an attempt has been made to optimize the objective function using the existing Differential Evolution (DE) scheme. As an enhancement of this work, a novel Self Adaptive Differential Evolution (SADE) algorithm has been proposed to optimize the trajectory in a more effective manner. Finally, a comparative study has been presented between the proposed SADE based design and the existing DE based design.